๐ World's largest GPT Image 2 prompt library, updated daily โ 2000+ curated prompts with preview images, 16 languages. OpenAI's next-gen image model with pixel-perfect text rendering, cross-image consistency, and commercial-grade illustration. Free & open source.
See the code
๐ก ๐ฌ Take it further with Seedance 2 โ pair GPT Image 2 stills with Seedance for jaw-dropping AI videos, 2000+ prompts to explore ๐ awesome-seedance-2-prompts
๐จ A curated collection of creative prompts for OpenAI's GPT Image 2
โ ๏ธ Copyright Notice: All prompts are collected from the community for educational purposes. If you believe any content infringes on your rights, please open an issue and we will remove it promptly.
-Click%20to%20View-lightgrey){kind=icon}
-Click%20to%20View-lightgrey){kind=icon}
๐ Browse on YouMind GPT Image 2 Prompts Gallery
Why use our gallery?
| Feature | GitHub README | youmind.com Gallery |
|---|---|---|
| ๐จ Visual Layout | Linear list | Beautiful Masonry Grid |
| ๐ Search | Ctrl+F only | Full-text search with filters |
| ๐ค AI One-Click Generation | - | AI one-click generation |
| ๐ฑ Mobile | Basic | Fully responsive |
| ๐ท๏ธ Categories | - | Category browsing |
GPT Image 2 (codename "duct-tape") is OpenAI's next-generation image model. Community testing highlights a leap in these areas:
๐ Learn More: See community testing in our report summary
Some prompts support dynamic arguments using Raycast Snippets syntax. Look for the ๐ Raycast Friendly badge!
Example:
A quote card with "{argument name="quote" default="Stay hungry, stay foolish"}"
by {argument name="author" default="Steve Jobs"}
When used in Raycast, you can dynamically replace the arguments for quick iterations!
| Metric | Count |
|---|---|
| ๐ Total Prompts | 17837 |
| โญ Featured | 6 |
| ๐ Last Updated | Sunday, October 11, 2026 at 2:43:24 AM UTC |
โญ Hand-picked by our team for exceptional quality and creativity
Generates a high-tech exploded view diagram of a VR headset with detailed component callouts and promotional text.
{
"type": "exploded view product diagram poster",
"subject": "VR headset",
"style": "clean high-tech 3D render, studio lighting, glowing accents",
"background": "{argument name=\"background color\" default=\"soft purple and blue gradient\"}",
"header": {
"logo": "โ {argument name=\"product name\" default=\"Meta Quest 3\"}",
"subtitle": "{argument name=\"main catchphrase\" default=\"ใพใฃใใๆฐใใ็พๅฎใใใพใฃใใๆฐใใๆง้ ใใใ\"}"
},
"layout": {
"centerpiece": "vertically stacked exploded view of a VR headset showing 9 distinct layers of internal components: outer shell, camera sensors, motherboard with chip, pancake lenses, internal frame, battery packs, side straps, top strap, and facial interface cushion.",
"callout_labels": {
"count": 8,
"left_side": [
"Snapdragonยฎ XR2 Gen 2\nๅงๅ็ใชๅฆ็ๆง่ฝใงใชใขใซใฟใคใ ใชไฝ้จใใ",
"่ชฟๆดๅฏ่ฝใชIPDๆฉๆง\nๅน
ๅบใใฆใผใถใผใซๅฟซ้ฉใชใใฃใใๆใใ",
"็ฒพๅฏ่จญ่จใใใใใใในใใฉใใ\nๅฟซ้ฉใใจๅฎๅฎๆงใ่ฟฝๆฑใใใจใซใดใใใฏในใ"
],
"right_side": [
"ใใงใคในใใฌใผใ\nๆด็ทดใใใใใถใคใณใจๆ้ฉใช้้ใใฉใณในใ",
"ใใฉใใญใณใฐใซใกใฉ\n้ซ็ฒพๅบฆใชไฝ็ฝฎใใฉใใญใณใฐใจ็ฐๅข่ช่ญใๅฎ็พใ",
"ใใณใฑใผใญใฌใณใบ\n่ๅ่จญ่จใงๅบใ่ฆ้่งใจ้ฎฎๆใชๆ ๅใๆไพใ",
"้ซๆง่ฝใใใใชใผ\n้ทๆ้้งๅใๆฏใใๆ้ฉๅใใใ้ปๆบ่จญ่จใ",
"ๆใใใชใใงใคในใคใณใฟใผใใงใผใน\n้ทๆ้ใงใๅฟซ้ฉใช่ฃ
็ๆใๅฎ็พใ"
]
},
"footer": {
"left_text_block": {
"headline": "{argument name=\"bottom headline\" default=\"ไฝ้จใฏใๆง้ ใใ้ฒๅใใใ\"}",
"body": "ไธใคใฒใจใคใฎใใผใใซใๆฒกๅ
ฅไฝ้จใๆฏใใๆๅ
็ซฏใใฏใใญใธใผใจใใ ใใใฎ่จญ่จใMeta Quest 3ใฏใๆชๆฅใๆใใใใไฝ้จใๅ
้จใใ็ใฟๅบใใฆใใพใใ"
},
"right_logo": "โ Meta"
}
}
}
Generates a hand-drawn, watercolor-style tourist map featuring numbered local food specialties, landmarks, and a legend.
{
"type": "illustrated map infographic",
"style": "{argument name=\"art style\" default=\"watercolor and ink hand-drawn illustration on vintage parchment\"}",
"title_section": {
"text": "{argument name=\"city name\" default=\"ๆ้ฝ\"} {argument name=\"map title\" default=\"ๅ่ดงๆด่ตฐๅฐๅพ\"}",
"mascot": "cartoon red chili pepper wearing sunglasses and giving a thumbs up"
},
"border": "{argument name=\"border decoration\" default=\"vine of green leaves and red chili peppers\"}",
"layout": {
"background": "textured beige parchment paper with yellow roads, blue rivers, and green park areas",
"sections": [
{
"title": "landmarks",
"count": 6,
"illustrations": ["traditional pavilion", "traditional monastery", "modern skyscraper with climbing panda", "tall TV tower", "traditional gate", "industrial buildings"],
"labels": ["ไบบๆฐๅ
ฌๅญ", "ๆๆฎ้ข", "IFS", "339็ต่งๅก", "ๅฎฝ็ชๅททๅญ", "ไธ้่ฎฐๅฟ"]
},
{
"title": "food_spots",
"count": 12,
"illustrations": ["mapo tofu", "dumplings in chili oil", "skewers in pot", "sticky rice balls", "egg baking cake", "nine-grid hotpot", "sweet potato noodles", "cold skewers", "spicy mixed dish", "covered tea bowl", "ice jelly dessert", "spicy rabbit heads"],
"labels": ["1 ้้บปๅฉ่ฑ่
", "2 ้ๆฐด้ฅบ", "3 ๆฅ็่ทฏ", "4 ๅฎฝ็ชๅททๅญยทไธๅคง็ฎ", "5 ๅปบ่ฎพ่ทฏยทๅถๅฉๅฉ่็็ณ", "6 ็ๆ่ทฏยทๅฐ้พๅ็ซ้
", "7 ้ฆ้ฆๅททยท่ฅ่ ็ฒ", "8 ๆญฆไพฏ็ฅ ๅคง่กยท้ต้ต้ธก", "9 ไธ้่ฎฐๅฟยทๅๆค็ซ่พฃ", "10 ไบบๆฐๅ
ฌๅญยท้นค้ธฃ่ถ็คพ", "11 ้ฆ้ๅค่กยทๅฐ็ฒ", "12 ๅๆต่ๅฆๅ
ๅคด"]
},
{
"title": "ๅพไพ",
"position": "bottom-right",
"count": 5,
"items": ["red dot", "green house", "green tree", "blue line", "yellow double line"],
"labels": ["็พ้ฃๅฐ็น", "ๅฐๆ ๆฏ็น", "ๅ
ฌๅญ็ปฟๅฐ", "ๆฒณๆตๆนๆณ", "ไธป่ฆ้่ทฏ"]
}
],
"centerpiece": "giant panda sitting and eating bamboo",
"bottom_right_extras": ["vintage compass rose with N, S, E, W", "disclaimer text 'ๆธฉ้ฆจๆ็คบ๏ผๅ่พฃ้่ฐจๆ
๏ผ่ ่่ฆไฟๆค~' with a red chili pepper icon"]
}
}
A prompt that combines the simple, warm aesthetic of Irasutoya illustrations with the high-information density characteristic of Japanese government slides.
Create an explanatory slide ({argument name="format" default="ponchi-e diagram"}) for {argument name="theme" default="Momotaro"} that fuses the gentle atmosphere of "Irasutoya" with the overwhelming information density of "Kasumigaseki slides".
Generates a realistic social media live stream interface overlaying a portrait, featuring customizable chat messages, gift popups, and a product purchase card.
{
"type": "live stream UI mockup",
"subject": {
"description": "portrait of {argument name=\"host name\" default=\"Elon Musk\"}, smiling, wearing a black t-shirt with a white technical schematic graphic",
"background": "left side shows a screen with '{argument name=\"left background logo\" default=\"SPACEX\"}' text, right side shows a red '{argument name=\"right background logo\" default=\"Tesla T logo\"}' and a dark car"
},
"ui_overlay": {
"top_header": {
"host_info": "avatar, name '{argument name=\"host name\" default=\"Elon Musk\"}', subtext '55.6ไธๆฌๅบ็น่ต', red 'ๅ
ณๆณจ' button",
"rank_badge": "gold coin icon with 'ๅ
จ็ซ็ฌฌ1ๅ'",
"viewer_stats": "3 top viewer avatars with '12.3w', '8.6w', '5.7w', total '68.7ไธ', 'X' close button",
"right_links": "'ๆดๅค็ดๆญ >', '็คผ็ฉๅฑ้ฆ 0/24' with blue '็ปๅ
ธ' tag"
},
"mid_left_gifts": {
"count": 2,
"items": [
"avatar '็งๆ็ฑๅฅฝ่
', '้ๅฐๅฟๅฟ', heart icon x 1314",
"avatar 'ๆ่พฐๅคงๆตท', '้็ซ็ฎญ', rocket icon x 666"
]
},
"bottom_left_chat": {
"system_message": "level 37 badge 'ๅฎๅฎๆผซๆธธ่
ๅ ๅ
ฅไบ็ดๆญ้ด'",
"message_count": 7,
"messages": [
"ๅฐ็ซ็ฎญ: ้ฉฌๆฏๅ
๏ผๆชๆฅๅฏๆ๏ผ๐",
"future: ็นๆฏๆModel 2ไปไนๆถๅๅบ๏ผ",
"ๆ็ฉบๆขฆๆณๅฎถ: SpaceXไปๅนด่ฝไธ็ซๆๅ๏ผ",
"AIๆข็ดข่
: Neuralink่ฟๅฑๅฆไฝ๏ผ",
"ๅธ
ๆฐ็็ฝๅ: ้ฉฌๆปๅฅฝ๏ผ",
"Mars: ็ฌฌไธๆฌกๆฅไฝ ็็ดๆญ๏ผ่ถ
ๆฟๅจ๏ผ",
"็จๆท123: ่ฎฒ่ฎฒAIๅง๏ผไผๅไปฃไบบ็ฑปๅ๏ผ"
]
},
"bottom_right_product_card": {
"hot_tag": "orange '็ญๅ x 1888'",
"image": "Tesla Cybertruck",
"title": "{argument name=\"product name\" default=\"็นๆฏๆCybertruck ็ตๅจ็ฎๅก\"}",
"price": "{argument name=\"product price\" default=\"ยฅ 1,618,000\"}",
"button": "red 'ๆข' button",
"floating_animation": "translucent hearts floating up the right edge"
},
"bottom_bar": {
"input_field": "'่ฏด็นไปไน...'",
"icons": ["smiley face", "three dots", "shopping cart", "gift box", "share"]
}
}
}
Generates a dynamic, high-impact anime illustration of two female characters fighting in a traditional dojo with elemental energy effects.
An anime-style illustration of a {argument name="action type" default="high-impact martial arts battle"} between two young female fighters in a {argument name="setting" default="traditional wooden martial arts dojo"}. In the foreground, a girl with black hair in a high bun wears a {argument name="character 1 color theme" default="red and white"} Chinese-style martial arts outfit with baggy pants. She is in a dynamic, low, forward-thrusting stance, surrounded by swirling red energy and water splashes. In the background to the right, a girl with light purple hair in twin buns wears a {argument name="character 2 color theme" default="green and purple"} Chinese dress with gold embroidery and black tights. She is leaping through the air in a flying kick pose, surrounded by swirling blue energy. The wooden floorboards are splintering from the intense impact, with debris and dust flying through the air. Above them hangs a weathered wooden sign with the text "{argument name="sign text" default="ๆญฆ่กไผ"}". The scene features dramatic lighting, a low-angle dynamic perspective, and intense action effects.
Transforms a flat evolutionary timeline into a realistic 3D stone staircase infographic with detailed organism renders and structured side panels.
{
"type": "evolutionary timeline infographic",
"instruction": "Using REFERENCE_0 as a structural base, transform the flat vector design into a highly realistic 3D infographic. Replace the smooth ramps with distinct stone steps and upgrade all organisms to photorealistic 3D models.",
"style": {
"background": "{argument name=\"background style\" default=\"vintage textured parchment paper\"}",
"staircase": "{argument name=\"staircase material\" default=\"realistic textured stone blocks\"}",
"subjects": "{argument name=\"organism style\" default=\"highly detailed photorealistic 3D renders\"}"
},
"layout": {
"main_title": "{argument name=\"main title\" default=\"ไบบ็ฑปๆผๅ\"}",
"sections": [
{
"position": "left sidebar",
"count": 8,
"labels": ["L0: ๅ็ป่็ๅฝ", "L1: ๅค็ป่็็ฉ", "L2: ๅจ็ฉ็", "L3: ่็ดขๅจ็ฉ", "L4: ไธ้้ฉๅฝ", "L5: ๅบไนณ็บฒ", "L6: ไบบ็งๆผๅ", "L7: ๆบไบบ็บชๅ
"]
},
{
"position": "top right",
"title": "่ทๅพ็ๅ่ฝ / ๅคฑๅป็ๅ่ฝ",
"description": "Legend with plus and minus icons"
},
{
"position": "bottom center",
"title": "ๆผๅๅ
ณ้ฎ้็จ็ข",
"count": 6,
"description": "Timeline with a silhouette graphic of 6 figures showing ape-to-human evolution"
}
],
"centerpiece": {
"description": "Winding stone staircase with 25 numbered steps featuring specific organisms.",
"count": 25,
"notable_elements": [
"Step 07: Jellyfish",
"Step 09: Ammonite",
"Step 10: Trilobite",
"Step 24: Walking human",
"Step 25: {argument name=\"future evolution concept\" default=\"glowing cosmic silhouette with a question mark\"}"
]
}
}
}
๐ Sorted by publish date (newest first)
A prompt for generating a low-resolution, early 2000s Nokia phone-style selfie featuring a woman in ragdoll cat cosplay, including specific noise, lighting, and background details.
Based on the reference image of an adult female cosplayer, maintain the protagonist's face, ragdoll cat themed costume, black long hair, brown-white plush outfit and cat paw accessories.
Character taking a close-up selfie, leaning slightly forward, tilting head, slight pout, with an expression of confusion, disdain, yet cute, looking directly at the camera.
Ragdoll cat fur color and styling details as per source material.
Next to the person is a ragdoll cat, in the foreground is a rattan basket containing a fluffy yellow chick and a bunch of deep purple grapes.
The person, cat, chick, and grapes naturally squeeze into the same frame, forming an absurd yet everyday private photo.
Shot with an early 2000s old Nokia phone, low-pixel color digital photography, low resolution, slight defocus, rough digital noise, JPEG compression artifacts, slight skin tone shift, uneven white balance, limited dynamic range, soft edges, obvious dirty noise in shadows.
Small ordinary bedroom, old bed, wooden furniture, old CRT TV naturally entering the background. Dim indoor ambient light combined with direct phone flash, face slightly overexposed, background rapidly decaying into darkness. Close-range wide-angle selfie perspective, arm extending towards lens creating obvious near-large far-small effect, casual composition, slightly tilted, like a private photo taken by a friend with an old phone.
Overall real, cheap, rough, snap-shot quality, no modern high-definition photographic texture. Only keep a very small fanfan signature.
A reverse-engineered prompt for a striking portrait of a woman with yellow braided horns and neck tattoos.
A vertical, low-angle medium close-up portrait of a young woman with light brown skin and prominent freckles across her nose and cheeks. She has an intense, direct gaze with blue eyes and full lips. Her hair is styled in thin yellow braids that hang down the sides of her face, adorned with small silver beads and rings. Two thick, sculpted horn-like structures made of fuzzy yellow yarn or rope protrude from the top of her head, curving slightly upwards. She wears a gold septum piercing and multiple dangling earrings. A black ink tattoo featuring tribal-style swirls covers the front of her neck. She is dressed in a textured knit sweater with horizontal stripes of mustard yellow, white, and black, accessorized with a chunky silver chain necklace. The background shows a clear blue sky on the left and a blurred grey concrete building structure on the right. The lighting is bright natural sunlight, casting distinct shadows on her face.
Prompt for creating modern geometric cartoon illustrations of two characters interacting with UPA-style shapes and limited animation movements.
{argument name="Character A" default="Xiao Ming"} and {argument name="Character B" default="Xiao Hong"}, modern geometric cartoon illustration ร UPA-style shape language ร limited animation movement design ร clear digital flat coloring.
Highly simplified character designs constructed from squares, circles, trapezoids, and arcs for heads and bodies. Retain core hairstyles, main colors, iconic accessories, and clothing color blocks. Clear smooth thick black outlines, large uniform solid color fills, minimal simple hard-edge shadows, exaggerated hands, shoes, and limb proportions.
Two characters engage in clear, humorous, dynamic interactions. Large stretches, jumps, chases, dodges, kicks, lunges create clear silhouettes. Movement directions, gazes, and expressions echo each other, presenting instantly readable comedic relationships.
Vertical composition, characters shrunk and concentrated in lower-middle section, large whitespace above. Single high-purity solid color background. Add a simple comic symbol, prop, or graphic element between characters to establish narrative connection.
Overall use few high-contrast colors: black, white, character main colors, and one or two accent colors. Sharp block edges, uniform fill, complete outlines, flat surface. Clean clear modern digital illustration quality, suitable for animation promos, stickers, and phone wallpapers.
Vertical format, tiny voxcat signature at bottom right.
A detailed prompt for generating a realistic iPhone-style photo of a woman in a cafe using GPT Image 2, focusing on faithful character reproduction from a reference image and specific lighting/composition details.
Shot on an iPhone. The womanโs appearance should be 100% faithful to the uploaded reference photo, sitting at a cafรฉ table outdoors under an autumn tree, centered in the frame. Her body is facing forward, her head slightly tilted, with one cheek gently resting on one hand while the other hand is relaxed on the table, holding the stem of a wide red-wine glass with a very thin, long, delicate stem and thin glass walls. Only a small amount of wine remains at the bottom.
She is wearing a voluminous black trench coat with structured shoulder pads and oversized long sleeves covering her fingers, with a black turtleneck underneath. Hair exactly matching the uploaded photo.
White tablecloth, elegant white plates, a classic European-style building faรงade in the background, with an autumn tree filling the upper part of the frame.
True-to-life iPhone realism, subtle natural film grain, authentic skin texture and lighting. Do not blur the background; maintain realistic environmental detail throughout the scene.
Short square French-tip manicure.
9:16 vertical format.
She is wearing narrow black rimless cat-eye sunglasses.
Overcast daytime with no direct sunlight. Slightly slower shutter speed for a subtle natural motion/film feel while keeping the subject realistic and recognizable.
A prompt for creating minimalist cartoon doodle illustrations featuring tiny characters with distinct paths and large negative space. Suitable for wallpapers or character series designs.
{argument name="character list" default="Character A / Character B / Character C / Character D"}, Minimalist cartoon doodle illustration x Huge negative space x Micro-character action chain.
Pure white or very light colored background, keeping over 65% of the image area blank. Characters are extremely small in proportion, retaining only hairstyle outlines, main colors, iconic accessories, and clothing color blocks, transformed into simplified, easily recognizable cartoon images.
Each image randomly selects one composition: central vertical queue, S-shaped serpentine, diagonal fall, single-side suspension, U-shaped path, micro-ring, spiral trajectory, intermittent floating nodes, top horizontal event followed by vertical fall, bottom character tower. The overall visual trajectory is slender and clear, with characters concentrated in local areas and large negative space maintained around them.
Set a micro-target object related to the character's worldview along the trajectory, such as fruit, food, badges, weapons, gems, or dolls. The target is located at the start, end, or center of rings/spirals, with characters' gazes and actions naturally pointing towards it.
Each character adopts different exaggerated actions: running, jumping, reaching out, holding up, surprised, falling, opening mouth, turning back, being pressed, or pulling each other. Through limb contact, clothing pulling, gaze direction, and spacing changes, create continuous, readable action relationships among figures. Specific actions and character order are random, maintaining clear visual rhythm.
Relaxed hand-drawn black outline lines, slightly shaky, with flying lines and irregularity, like animation drafts or children's doodles. A few high-purity flat color blocks, composed of black lines, white background, and red, yellow, blue, green for a simple palette, with character main colors serving as identity anchors.
Overall relaxed, absurd, cute, like animation stickers, character journal illustrations, or minimalist phone wallpapers. Vertical format, extremely small voxcat in the bottom right.
A detailed prompt for generating a cinematic fantasy portrait of a woman on a moonlit terrace, optimized for GPT Image 2.
A highly detailed cinematic fantasy portrait of a beautiful young woman standing on an elegant flower-covered terrace at twilight. She has long, naturally wavy dark brown hair, soft glowing skin, expressive hazel-brown eyes, delicate facial features, subtle rosy cheeks, and glossy natural lips. She is wearing a sophisticated flowing black dress with intricate silver floral embroidery, sheer sleeves, elegant dangling earrings, and a delicate hair ornament. She stands in a graceful three-quarter pose, body turned slightly away while looking back over her shoulder directly at the camera, one hand gently holding her dress and the other relaxed by her side.
Behind her is a breathtaking moonlit lake with a distant magical city, glowing domes and towers, mountains, and reflections across the water. Warm vintage lanterns surround the terrace, with white flowers and green vines framing the scene. A crescent moon and soft purple-blue clouds fill the sky. Romantic warm-and-cool cinematic lighting, realistic skin texture, detailed hair strands, natural proportions, shallow depth of field, soft bokeh, dreamy atmosphere, photorealistic fantasy realism, professional photography, 85mm lens, eye-level camera, full-body composition, vertical 9:16.
A retro-styled image of a smiling woman holding up her catch while standing in a mountain river.
A vintage-style photograph of a young woman standing waist-deep in a clear, rocky river. She is wearing a beige bucket hat, a white short-sleeved blouse with a small floral pattern, and dark waders. Her hair is styled in two braids. She holds a bamboo fishing rod in her right hand and raises her left arm to display two freshly caught fish hanging from the line. A woven basket hangs at her hip, and a red mesh landing net is visible in the foreground. The background features lush green mountains under a blue sky.
A cinematic portrait of a Japanese schoolgirl drawing a rabbit on a chalkboard in an empty classroom, featuring vintage film grain and soft lighting.
A vertical, medium-shot photograph with a nostalgic film aesthetic captures a young Asian female student in an empty classroom. She has short, dark bobbed hair with bangs and wears a traditional navy blue sailor-style school uniform (seifuku) with white stripes on the collar and cuffs. Her expression is calm and slightly melancholic as she looks directly at the camera. She stands beside a green chalkboard, holding a piece of pink chalk in her right hand, having just drawn a cute cartoon rabbit face with a heart next to it. In the foreground, resting on a worn wooden desk, is a large orange triangular ruler. The background features rows of empty wooden desks and chairs, tall windows letting in soft natural light, and blurred calligraphy posters on the far wall. The image has visible film grain, dust specks, and scratches, enhancing the retro atmosphere.
A retro-styled photograph capturing a smiling young woman in a hoodie and plaid skirt within a rustic Japanese setting.
A vintage-style portrait of a young woman standing in a traditional Japanese alleyway. She has short, curly dark brown hair and is wearing a cream-colored hooded sweatshirt with drawstrings and a plaid skirt. Her hands are raised to her head as she smiles gently at the camera. A brown leather shoulder bag hangs from her left side. The background features weathered wooden houses with tiled roofs, a utility pole, and an old bicycle leaning against a fence. The image has a nostalgic film grain texture with light leaks on the edges.
A prompt for generating a hyper-realistic fashion portrait of a character with purple hair sitting against a terracotta wall using GPT Image 2.
Create a hyper-realistic medium full-body fashion portrait of the same young adult female character from the reference image, preserving her signature vivid violet-purple chin-length straight bob with soft bangs, fair porcelain skin, natural freckles across her nose and cheeks, hazel/light-brown eyes, delicate facial features, glossy lips, and slim physique.
She is sitting in a relaxed crouching pose against a warm terracotta textured wall, with her head resting gently on one hand while looking calmly and directly at the camera. She wears a terracotta rust-orange cropped hoodie, beige high-waisted cargo jogger pants, and brown leather lace-up combat boots. Add a patterned satin bow headband and a small orange butterfly hair clip.
Use soft natural daylight with warm earthy autumn tones. Keep the composition intimate and editorial with realistic skin texture, detailed purple hair, natural fabric and leather textures, subtle shadows, cinematic depth of field, photorealistic quality, ultra-detailed 8K, premium fashion photography.
A community-shared prompt for generating extreme close-up anime portraits using GPT Image 2, requiring reference sheets.
Create an extreme close-up portrait of the character in the attached character reference sheet. Treat that sheet as the absolute authority for the character's identity and design: preserve their face, facial proportions, skin tone, hair style/color, eyes, ears or other character features, and any visible clothing/accessories. Do not redesign the character.
The second attached portrait is ONLY a rendering-quality reference. Do not copy that character's identity, face, hair, colors, clothing, accessories, expression, pose, or composition. Use it only as the target for detail density and finish: highly defined facial features, dimensional anime shading, intricate eyes and eyelashes, individually rendered hair strands, subtle skin highlights and warmth, sophisticated lighting, depth, material definition, and extremely polished cinematic anime rendering.
Frame the subject very tightly from approximately the upper chest/clavicle to the tips of their hair/ears, with the face dominating the image. Use an eye-level camera and direct eye contact. Give them a small natural smile with subtle blush. Preserve recognizable anime facial proportions while adding significantly more dimensional definition and fine detail; do not make the face photorealistic.
Use a simple dark atmospheric background and cinematic lighting that complements the character's existing palette. Keep the eyes, face, and nearest hair strands exceptionally sharp, with gentle depth falloff elsewhere.
Do not show the waist, hips, legs, or full body. Do not create a detailed environment. Do not copy the second portrait's scene or character.
Character sheet = WHO the character is. Second portrait = ONLY the LEVEL OF RENDERING QUALITY.
Generate the portrait now.
A detailed prompt for GPT Image 2 to create a photorealistic selfie of a woman wearing cat ears and tail in a white cat-themed room, including specific pose, lighting, and style instructions.
Subject:
Selfie in cat ear knit outfit.
Main Subject:
A woman taking a selfie while bending forward in a white cat room, wearing cat ears and a tail, positioned in the center of the frame.
Character & Expression:
Small oval face, large dark brown eyes, thin eyebrows, well-defined nose, glossy pale pink lips. Expression is a soft smile, facing forward, looking at the camera through the smartphone. Long dark brown wavy hair let down, with thin bangs and a white-brown cat ear headband on top of the head.
Clothing & Pose:
Beige and pale pink open-knit long-sleeve knit dress, deep neckline, front tie, pom-pom decorations, short length, white cat-shaped slippers, long white-brown cat tail from waist. Knees bent, bending deeply forward, holding a smartphone with pink case in front of face with right hand, left hand resting on left knee.
Background & Light:
Foreground has long-pile white rug and cat teaser toy. Background has white shelves, peach blossoms, framed cat pictures, cat tower on the right, white-grey cat on floor. Soft warm indoor light from above and back-right illuminates face, knitwear, and cats.
Composition & Camera:
3:4 vertical composition, full-body portrait captured by front camera slightly lower than waist, from cat ears to white slippers. Person placed large in center, occupying most of frame height. Smartphone and tail included in frame, focus on face, smartphone, and cat ears, background lightly blurred.
Texture & Style:
Photorealistic live-action photo. High-definition natural skin, hair, clothing materials, surrounding props, maintaining soft indoor colors of white, beige, and pale pink.
Negative:
Change of cat ears/tail and forward bend; omit background cats.
A prompt for generating a photorealistic portrait of a young South Asian woman wearing traditional attire in a garden setting during golden hour.
Photorealistic elegant portrait of a young South Asian woman wearing a dusty rose pink hijab, softly wrapped around her head and shoulders, with delicate gold traditional jhumka earrings. She is dressed in a luxurious blush-pink and ivory embroidered Pakistani shalwar kameez with intricate floral threadwork, subtle sequins, and detailed borders. She is seated gracefully beside an ornate marble railing, resting one hand gently under her chin, looking slightly upward with a soft, serene smile. Warm golden-hour sunlight, beautiful garden courtyard in the background, pink flowers and lush greenery, creamy architectural details, dreamy bokeh, shallow depth of field, natural skin texture, realistic facial features, soft cinematic lighting, high-end fashion photography, elegant Pakistani aesthetic, ultra-detailed, 85mm portrait lens, vertical 4:5 composition, no text, no watermark, no artificial plastic skin.
A detailed prompt for generating a photorealistic portrait of a woman in a black corset under red neon lights using GPT Image 2.
Subject:
Black corset with red neon.
Main Subject:
A woman in a glossy black corset is the protagonist in a dark lounge with red neon lights, centered in the frame.
Character & Expression:
Small oval face, large dark brown eyes, thin eyebrows, well-defined nose, glossy pale peach lips. Expression: Face tilted slightly upward, gaze meeting the camera, lips slightly parted in an intense expression. Dark brown straight hair falling below shoulders, with wet thin bangs and strands along cheeks.
Outfit & Pose:
Corset top with black enamel gloss, strapless chest, central zipper, side lacing; black waist straps and leather choker. Upper body arched back in front of a black sofa, arms lowered to sides, right shoulder pulled slightly back.
Background & Lighting:
From left to right background: black sofa and small table with candles on the left, red lightning-shaped neon on the right, black vertically grooved wall. Hard red neon from the right and soft white main light from the front illuminate the face and glossy costume.
Composition & Camera:
4:5 vertical composition, frontal camera slightly below chest level capturing a half-body portrait from head to hips. Character placed very large in center, occupying most of frame height. Arms and hips cropped at frame edges; focus on eyes and black glossy corset, background lightly blurred.
Texture & Style:
Photorealistic live-action photo. Natural skin and hair, high-definition costume materials and surrounding props, maintaining strong night colors of black, red, and skin tones.
Negative:
Omit red neon; change black glossy corset.
Generates a vintage-style black and white portrait of a young woman with an intense gaze.
A black and white, high-contrast portrait of a young woman with dark hair pulled back from her face. She is looking directly at the camera with an intense, serious expression. The image has a grainy texture and appears to be a vintage photograph or charcoal drawing.
A detailed photorealistic prompt for GPT Image 2 featuring a woman taking a mirror selfie in a white tulle dress, with specific pose and lighting instructions.
Subject:
White tulle in front of mirror.
Main Subject:
The protagonist is a woman sitting and taking a selfie in front of a floor mirror wearing a white tulle dress, positioned centrally.
Character & Expression:
Small oval face, large dark brown eyes, thin eyebrows, neat nose, glossy pale peach lips. Expression is calm, facing lower left with gaze falling onto smartphone screen. Hair near black tied in low bun, leaving thin bangs and stray hairs along cheeks.
Clothing & Pose:
Long dress with white strapless bodice and multiple layers of sheer tulle, thin silver gem anklets on both ankles. Sitting on white long-pile rug, knees raised high toward chest, holding black smartphone vertically in front of face with right hand.
Background & Light:
From left to right background: black leather chair inside mirror frame, warm lamp and flowers upper left, dark curtains around. Soft warm light from upper left illuminates face, white cloth, and legs.
Composition & Camera:
2:3 vertical portrait, full-body shot from top of head to reflected feet tips via floor mirror frontal camera. Place person very large centrally, occupying most of screen height. Naturally crop feet tips and mirror frame at screen edges, focus on face, phone, and white tulle, lightly blur background.
Texture & Style:
Photorealistic real photo. High definition of natural skin, hair, clothing material, and surrounding props, maintaining indoor colors of white, black, and gold.
Negative:
Change mirror shot and knee position; omit white tulle
A detailed prompt for GPT Image 2 to generate a photorealistic selfie of a woman with three white-grey cats in a bright morning room, specifying composition, lighting, and negative constraints.
Subject:
Morning selfie with three cats.
Main Subject:
A woman taking a selfie in the center of the frame, leaning her face close to three white-grey cats.
Character & Expression:
Small oval face, large dark brown eyes, thin eyebrows, well-defined nose, glossy pale pink lips. Expression is joyful, facing forward, looking at the camera, mouth wide open showing teeth. Black hair tied in a high bun, with wet thin bangs and stray hairs remaining on forehead and cheeks.
Clothing & Pose:
Natural beige thin-strap ribbed camisole top with chest lace and small ribbon. Left arm extended forward to take the photo, holding one cat in front of chest, with one cat above head and one behind left shoulder.
Background & Light:
Bright room with wooden desk and stacked books on the left, white door, white curtains and green leaves on the right. Soft white daylight from window on the right illuminates faces and cat fur.
Composition & Camera:
9:16 vertical composition, close-up front-facing selfie camera from extended arm capturing three cats and portrait from head to below chest. Person placed very large in center, occupying most of frame height. Foreground cat and left arm cropped by frame edge, focus on woman's and three blue-eyed cats' faces, background lightly blurred.
Texture & Style:
Photorealistic live-action photo. High-definition natural skin, hair, clothing materials, surrounding props, maintaining bright indoor colors of white, grey, beige, and wood tones.
Negative:
Change of three cats' arrangement; omit open mouth and selfie.
A prompt for generating a full-body portrait of a ballerina practicing in a studio with morning light, performing a high leg lift, with detailed costume and pose instructions.
Subject:
High leg lift in morning light.
Main Subject:
Woman raising one leg vertically in morning ballet practice hall is the protagonist, centered.
Person & Expression:
Small oval face, large dark brown eyes, thin eyebrows, neat nose, glossy pale peach lips. Expression is focused, face turned down-right, gaze dropped to chair. Dark brown hair in low bun, leaving thin bangs and loose strands along cheeks.
Clothing & Pose:
Leotard in dusty purple with thin straps, sheer ecru long-sleeve front-tie top, short pale-peach frill skirt, pink pointe shoes. Standing on right foot in pointe, left leg raised vertically to ear height held by left hand on calf, right hand on wooden chair back.
Background & Light:
Left and right background have white decorative walls and tall arched windows, background has wooden bar, foreground right has wooden chair, glossy wooden floor. Soft direct morning light from right window casts long window shadows on body and floor.
Composition & Camera:
3:4 vertical composition, horizontal camera slightly lower than waist capturing full body from pointe toe to raised left toe. Person placed largely vertical in center occupying most screen height. Leaving margins for chair and windows on sides, focus on profile and raised leg, background lightly blurred.
Texture & Style:
Photorealistic live-action photo. High-definition natural skin, hair, clothing materials, and props; maintaining morning colors of pale-peach, ecru, and wood.
Negative:
Change vertical leg lift; omit chair and pointe
Generates a striking overhead shot of a woman crouching on a red floor reaching towards the camera, with strong contrast and streetwear aesthetics.
Subject:
Palm on red floor.
Main Subject:
The main character is a woman crouching on a red floor, extending her palm largely towards the lens, positioned in the center of the screen.
Person & Expression:
Small oval face, large dark brown eyes, thin eyebrows, well-defined nose, glossy pale peach lips. The expression is intense, face turned upwards, gaze aligned with camera, lips slightly parted. Wet short black bob hair down, leaving thin bangs and strands along cheeks.
Clothing & Pose:
Dark grey thin-strapped ribbed bra top, white sports shorts, black belt, white sneakers, black leather choker and chain necklace, thick black bracelet. Crouching low on red floor, left hand placed on floor behind, right arm extended towards camera with five fingers spread wide.
Background & Light:
Left to right background: vivid red floor filling entire screen, pair of black-red sneakers at top-right, shadow of person at bottom-left. Hard direct sunlight from above creates strong shadows on hands, face, and shoulders.
Composition & Camera:
3:4 vertical composition, extreme wide-angle overhead bird's-eye view camera capturing full body from extended hand to both shoes. Person placed very large in the center, occupying most of the screen height. Palm made huge in foreground, arms and shoes cropped at screen edges, focus on face and foreground palm, background lightly blurred.
Texture & Style:
Photorealistic live-action photo. High definition skin, hair, clothing materials, and surrounding props; maintain strong contrast of red, black, white, and skin tone.
Negative:
Change of giant foreground hand and overhead view; omission of red floor.
A prompt for generating a photorealistic close-up portrait of a woman in a black satin dress in a dim lounge setting, focusing on lighting and texture details.
Subject:
Black satin candlelight seat.
Main Subject:
Close-up portrait of a woman wearing a black satin dress in a dark lounge seat is the protagonist, centered.
Person & Expression:
Small oval face, large dark brown eyes, thin eyebrows, neat nose, glossy pale peach lips. Expression is calm, face tilted slightly right from front, gaze meeting camera with lips barely parted. Reddish dark brown hair styled in low braided bun, leaving thin bangs and loose strands along cheeks.
Clothing & Pose:
Dress with glossy black satin, thin straps, deep V-neck, twisted waist drapes; large teardrop silver earrings. Sitting diagonally on black fabric sofa, left shoulder forward, both arms lowered beside body.
Background & Light:
Left background has black vase and branches, right has slim glass on marble table, background has vertical warm lights. Soft warm main light from right creates sheen on face, shoulders, and black satin.
Composition & Camera:
3:4 vertical composition, close diagonal frontal camera at chest height capturing bust-up from top of head to above waist. Person placed very large in center occupying most screen height. Left shoulder, right arm, dress hem cropped at edges, focus on eyes and black satin chest, background lightly blurred.
Texture & Style:
Photorealistic live-action photo. High-definition natural skin, hair, clothing materials, and props; maintaining night colors of black, gold, and skin tone.
Negative:
Change braided hair and face direction; omit black satin dress
A prompt for generating images combining old Nokia phone photography aesthetics with handwritten diary doodles and scrapbook elements, featuring a specific character in a daily scene.
{argument name="character" default="Anime Character"}, clearly adult live-action adaptation, preserve facial structure, hairstyle, hair color, eyes, main character color, iconic clothing silhouette and identity accessories.
2000s old Nokia phone photography ร private handwritten diary ร analog scrapbook ร experimental fashion photography.
Character placed in a real daily space, performing an action with a sense of life or slightly unconventional meaning. Action, expression, camera position, shot size, clothing details and space are autonomously designed by the model based on character identity.
Close-range phone direct flash snapshot, slight wide-angle distortion, low pixels, JPEG compression, partial defocus, direct flash highlights and rough digital colors. Character retains real facial structure and natural skin texture, presenting the accidental moment of the action occurring.
Colorful handwritten doodles, simple symbols, date codes and private notes directly overlaid on the photo surface. Some lines extend along the character's body contour, some marks emphasize gaze, gestures and action direction; a few photo fragments and paper edges form scrapbook layers. Handwritten content naturally derives from character identity and current situation.
Photographic subject is clear, manual markings and real space interpenetrate. Colors are autonomously organized based on character main color and scene lighting, overall presenting an experimental vibe of fused colorful private imagery and handwritten records.
3:4 portrait, very small vertical lowercase signature "voxcat" on the right edge.
A cute anime-style illustration of three chibi girls in animal costumes cooking pancakes together in a colorful kitchen.
Using the provided reference image, transform the scene into a cozy kitchen setting where three chibi girls are making pancakes. Keep the character designs (the yellow chick costume and blue shark hoodie) consistent with the reference style but add a third character in a white sheep costume. Change the background from a candy shop to a warm, pastel-colored kitchen with shelves of dishes and hanging utensils.
Action details: The girl in the yellow chick suit is whisking batter in a pink bowl. The girl in the blue shark suit is pouring batter onto a pink electric griddle using a ladle. The new girl in the white sheep suit is holding a bowl of flour/mix. All three characters must have a small smudge of pancake mix on their noses.
Props & Text: Include a bag labeled "Fluffy Pancake Mix", a jar labeled "HONEY", a bottle labeled "MILK", and a jar labeled "SUGAR". Add a stack of finished pancakes topped with strawberries and cream in the foreground. In the top right corner, include a chalkboard sign that reads "Purin-chan & Same-chan & Koharu-chan Pancake Party".
A photorealistic overhead view of a coffee shop's seasonal fall menu card resting on a sunlit wooden table next to a latte.
A high-angle, photorealistic shot of a rustic wooden table bathed in warm, dappled sunlight. On the left side of the frame lies a vertical menu card printed on cream-colored paper with a thin dark green double-line border. The text on the card is arranged as follows: at the top, 'HARBOR STREET COFFEE' in small uppercase serif letters; below that, 'Fall Menu' in large, elegant dark green serif font; followed by a decorative horizontal line with a leaf motif in the center. The menu items are listed in dark green serif text: 'Maple Oat Latte $5.50', 'Pumpkin Cold Brew $5.00', and 'Cardamom Bun $4.25'. At the bottom of the card is another leaf motif and the text 'Open daily 7am - 3pm'. To the right of the menu sits a ceramic mug filled with a latte featuring intricate white rosetta latte art. In the upper left corner, the leaves of a potted plant are partially visible, casting soft shadows across the scene.
This prompt generates an image capturing a nostalgic scene of a young woman posing inside a classic Japanese department store, perfect for creating retro-themed visuals.
A vintage-style photograph of a young woman standing in a Japanese department store. She has short, dark bobbed hair with bangs and is looking directly at the camera with a gentle expression. She wears a cream-colored long-sleeved blouse with a Peter Pan collar, tucked into a brown plaid pleated skirt that falls just above her knees. A small brown leather satchel hangs from her shoulder, and she holds a book or pamphlet in her hands. Her outfit is completed with white ankle socks and dark brown loafers. The background shows glass display cases filled with perfumes and cosmetics on the left, with a sign reading 'ๅ็ฒงๅ' (cosmetics). To the right, there are clothing racks and another sign reading 'ๅฉฆไบบๆ' (women's clothing). The floor is polished tile reflecting the warm lighting overhead. The overall atmosphere evokes nostalgia, reminiscent of late 20th-century Japan.
A prompt template for creating a nostalgic editorial scrapbook image that combines a realistic photograph with hand-drawn illustrations using GPT Image 2.
Create a nostalgic editorial scrapbook-style image combining one main photorealistic lifestyle photograph with a hand-drawn illustrated section underneath.
The top 50โ55% should be a cinematic, highly realistic photograph of {argument name="subject scene" default="[SUBJECT / SCENE]"}, captured like an authentic film photograph. Natural candid composition, warm nostalgic atmosphere, soft diffused light, subtle film grain, realistic textures, slightly muted vintage colors, autumnal/warm earthy tones, shallow depth of field where appropriate, beautifully composed but not overly polished.
The bottom 45โ50% should look like a vintage handmade scrapbook / travel journal page, printed on warm cream textured paper. Recreate small elements from the photograph as loose colored-pencil and watercolor doodle illustrations arranged in a clean 3ร3 or balanced grid. Include simple hand-drawn objects related to the scene such as {argument name="object 1" default="[OBJECT 1]"}, {argument name="object 2" default="[OBJECT 2]"}. Use imperfect sketch lines, subtle pencil strokes, watercolor bleed, slightly uneven coloring and authentic handmade imperfections.
Add a short handwritten title at the top of the illustrated section: โ{argument name="title" default="[TITLE]"}โ, in casual imperfect black/gray handwritten lettering. Add tiny decorative elements such as hearts, dots, clouds, leaves, stars, waves or small doodles around the illustrations.
At the very bottom, add a small handwritten caption: โ{argument name="short caption" default="[SHORT CAPTION]"}โ.
Overall aesthetic: cozy Pinterest editorial, nostalgic travel diary, vintage film photography + childrenโs sketchbook illustration, warm analog memories, premium lifestyle magazine composition, tactile paper texture, understated and elegant, emotionally warm, authentic rather than overly digital.
Composition: vertical 4:5, clean separation between photograph and illustration, balanced negative space, consistent visual storytelling between the photo and drawings.
Important: preserve realistic photography in the top section; do not turn the photograph into an illustration. The lower section should clearly look hand-drawn. Avoid excessive text, distorted lettering, photorealistic doodles, CGI appearance, oversaturation, clutter, or overly perfect vector graphics.
A surreal poster depicting Guangzhou's morning scene where giant rice noodle rolls form a landscape tended by tiny workers, set against a city skyline.
A creative vertical poster titled "GOOD MORNING GUANGZHOU" (ๅนฟๅทๆฉๅฎ) in the top left corner. The date "2026-10-09" and weather information are below the title. A quote reads: "็ญๆฐ่
พ่
พ๏ผๅฐฑๆฏ็ๆดปๆๅฅฝ็ๅ็ญ" (Steaming hot is life's best answer). Another poetic line on the left says: "ๅนณๅก้ฃๆไน่ฝ้ฟๅบๅๅธ็ๆธฉๆ" (Ordinary ingredients can also grow into the city's tenderness). The main visual features a surreal landscape made of giant, steaming rice noodle rolls (cheung fun) arranged like terraced fields or rolling hills. Tiny workers dressed as chefs and farmers are tending to these noodle fieldsโsome sweeping, others pushing carts filled with green vegetables (scallions/peppers), and some harvesting. The noodles are translucent white, garnished with chopped scallions and orange bits (possibly carrot or shrimp roe). In the background, there is a hazy city skyline featuring the Canton Tower and skyscrapers under a bright sky. On the right side, a wooden signpost reads "ๅนฟๅผ่ ็ฒ" (Cantonese-style Cheung Fun) with smaller text "ไธไปฝๆธฉๆ ่ธๅๆดๅฅฝ็ๆฅๅธธ" (A portion of gentleness, steamed towards a better daily routine). Bottom right text: "ๆฉ่ถ่ฎฉ็ๆดปๆดๆๆปๅณ" (Morning tea makes life more flavorful). The overall style is hyper-realistic miniature photography mixed with food art, bright, warm, and appetizing.
A detailed prompt for generating surreal photo posters where the top half is a real photo and the bottom half expands into a conceptual 'second world' with mixed media elements.
Based on each uploaded photograph, create an independent 3:4 vertical 'Second World' conceptual surrealist photo illustration poster. Output each separately, no collages. Strictly 1:1 split vertically. The top half is the original realistic photo; the bottom half is another layer of space growing from within the photo. They are not stitched together but exist as continuous presences in different narrative layers of the same moment.
The top half should faithfully preserve the original photo as much as possible, without changing the subject, action, spatial relationships, lighting, color, or texture. Only perform necessary proportional cropping and slight high-end tonal adjustments to give it a clean, restrained, publication-quality photographic feel.
The creative focus is not on the 'subject matter' but on re-understanding the visual structure. First, observe the most decisive structural clues in this photo (e.g., boundaries, slopes, water surfaces, reflections, shadows, cracks, roads, branches, clouds, contours, gaps, flow, repetitive rhythms, spatial turns, or poses). Find the part best suited to 'cross the boundary'. Then let it break through the photo's edge into the bottom half, undergoing a translation of purpose, scale, semantics, or narrative role upon entry. It's not simple extension, but transforming something real into another existence that can be used, entered, measured, salvaged, repaired, organized, borrowed, unfolded, or collected in the second layer of space.
The bottom half is a warm, quiet, off-white space with subtle paper texture and ample whitespace. It is not an illustration background or decoration area, but a place to receive the 'new logic after crossing the boundary'. The relationship follows: Reality โ Crossing โ Translation. The charm comes from a smart and accurate cross-layer narrative, not cute decorations.
You may add minimal black hand-drawn line art figures (0-3), few but precise. Figures are users of the second world, interacting authentically with the translated structures. Lines should be light, simple, natural, slightly handmade, not cutesy, complex, or distracting. Actions should be specific, restrained, and smart, like seriously handling a small thing inherent to this world.
You may add a short English handwritten caption, generated based on the actual 'Second World event' happening in the image. Tone should be like a casual discovery or soft narration, with a hint of humor and lingering interest. Do not write inspirational quotes, explain allegories, or use templates.
The overall style should present a synthesis of Mixed-Media Photo Illustration, Surreal Photomontage, Frame-Breaking Illusion, Trompe-l'ลil, Visual Metaphor, and Conceptual Editorial Illustration. Formally cross-media collage, mechanically frame-breaking, core visual metaphor, emotional tone gentle, slight, and smart micro-surrealism.
Do not make it a template of 'photo + small people + sentence'; do not have extension without translation; do not have form without metaphor; do not force sentimentality; avoid commercial ad feel, complex illustration feel, repetitive actions, baseless decoration, mechanical collage, hard connections, or cheap healing vibes.
Final Goal:
Let viewers first see a valid real photo, then suddenly discover an element crossing into another layer of space, gaining an unexpected yet extremely natural new meaning there.
Not adding creativity to the photo, but revealing the second reality latent within it.
A split layout combining a realistic brick texture with a minimalist graphic poster featuring abstract brick shapes and inspirational Chinese typography.
A split-screen composition. The left half is a close-up photograph of a weathered red brick wall with rough texture and grey mortar lines. The right half features a minimalist graphic design on an off-white background, displaying stylized watercolor-textured orange-red rectangular blocks arranged in a staggered pattern resembling bricks, with a soft peach-colored circle representing the sun above them. In the top right corner, large black Chinese characters read 'ๅนณๅกไนๅข' (The Ordinary Wall). Below this title, smaller text reads 'ไธไบๆฎ้็ๆๆ ไน่ฝๆฏๆ่ตท็ๆดป็้้' (Some ordinary materials can also support the weight of life). Further down on the right side, small vertical text says 'ๆฅๅธธไน็พ ไปไธ้ฅ่ฟ' (The beauty of daily life is never far away). In the bottom right corner, there is a list: '็ / ๆถ้ด / ็ๆดป / ไพ็ถๅไธ /' (Brick / Time / Life / Still Rising /).
A photorealistic prompt generating an image of two young women sharing a quiet, potentially awkward moment in a vintage-style kitchen.
A realistic, high-resolution photograph capturing a candid moment between two young East Asian women standing side-by-side in a rustic, sunlit kitchen. The image has a nostalgic film aesthetic with soft grain and warm tones. On the left, a woman with dark hair tied back in a low ponytail wears a cream-colored short-sleeved blouse with delicate eyelet lace details and a dark plaid midi skirt. She holds a white mug with a small orange floral pattern in both hands, gazing off to her right with a slightly distant or pensive expression. Beside her on the right, another woman with short, choppy dark brown hair wears a light blue-grey textured button-down shirt and a beige linen skirt. She is looking towards the first woman with a subtle, perhaps skeptical or curious glance, holding a folded white towel with red stripes near her waist. The background features a cluttered but cozy kitchen setting: a large window letting in bright natural light, shelves lined with jars of spices and condiments, hanging utensils like ladles and spatulas, and a glimpse of a stove and sink area. The atmosphere feels intimate yet tense, suggesting an unspoken conversation or a moment of awkwardness between friends.
A prompt for generating a vertical poster that combines a realistic golden-hour travel photograph with a hand-drawn watercolor scrapbook collage, referencing specific visual elements.
Create a vertical cozy travel scrapbook poster inspired by the reference images. Combine a cinematic realistic travel photograph on the top half with a hand-drawn memory journal collage on the bottom half.
Top section: Show two young travelers relaxing together on a grassy coastal cliff overlooking a beautiful ocean. One person is taking photographs with a vintage camera while the other is looking through a travel guide/map. Include small travel items such as photographs, postcards and camera accessories on the grass. Warm golden-hour sunlight, soft ocean waves, natural candid poses, nostalgic film photography, muted warm colors, cinematic depth of field, authentic peaceful travel atmosphere.
Bottom section: On warm textured cream paper, create a charming 3ร3 illustrated scrapbook grid inspired by the scene. Draw individual hand-drawn elements: a person with a camera, ocean waves and sun, traveler with a map, vintage photographs, a heart symbol, coastal grass and sea, folded jeans/clothing, overalls/backpack, and ocean waves. Use loose colored-pencil and watercolor strokes with dark brown sketch outlines, muted blue, orange, yellow and green accents. Add tiny hearts, stars, birds, sunshine and decorative doodles.
At the top of the illustrated section, add a handwritten title โGood Timesโ and at the bottom a small handwritten phrase โSame place, better together.โ
Style: nostalgic travel diary, vintage film photography, handmade scrapbook, watercolor + colored-pencil illustration, textured recycled paper, warm cozy tones, imperfect hand-drawn details, emotional friendship/travel memories, premium editorial poster, clean composition, vertical 4:5, highly detailed, no watermark.
A prompt to generate a realistic portrait of a young man styled as the Monkey zodiac sign, complete with a pet monkey and traditional attire.
A cinematic, hyper-realistic portrait of a handsome young man representing the Monkey zodiac. He has messy dark brown hair with loose strands falling over his forehead and wears a thin golden headband. His expression is calm and confident, looking directly at the viewer. He is dressed in traditional Chinese robes featuring intricate gold brocade patterns on black fabric, with a textured ochre sash draped across his chest. Perched on his left shoulder is a small, realistic monkey wearing a miniature matching vest. Behind him, he carries a long, ornate golden staff (Ruyi Jingu Bang) that extends vertically out of the frame. The background is a soft-focus landscape of misty mountains and ancient temple roofs. In the top left corner, there is a large, bold calligraphy character '็ด' in beige ink. On the right side, vertical text reads 'CHINESE ZODIAC MONKEY'. On the left side, vertical white text reads 'ๅคฉ็ๆๆๅฟ
ๆ็จ' followed by smaller text '็ตๅจ่ชๆ
งยทๆบๆ่ฟไบบยท่ช็ฑๆ ็'. A red seal stamp is visible near the text.
Generates a detailed 3D render of a spooky but comfortable living room decorated for Halloween with purple walls, a fireplace, pumpkins, and themed furniture.
A cozy, dimly lit interior of a spooky Halloween-themed living room. The walls are painted a deep purple, and the ceiling features dark wooden beams. A large stone fireplace sits in the center back wall with a roaring fire inside; above it hangs a framed picture of a haunted house under a full moon, flanked by candelabras and draped with red garland featuring a jack-o'-lantern face. To the left is a plush burgundy sofa adorned with various pillows, including one shaped like a white ghost and another with a skull pattern, along with a knitted throw blanket. In the foreground, an armchair has a black pillow with white skulls on it. On the floor lies a circular rug with a starry night pattern. Several orange pumpkins are scattered around the room, some glowing from within. To the right, a large flat-screen TV displays a yellow background with a skeleton character and a long list of song titles or text. Beside the TV stands a tall wooden bookshelf filled with books. A small window on the far left shows a twilight sky outside. The overall atmosphere is warm yet eerie, illuminated primarily by the fireplace glow and ambient lighting.
A detailed prompt for generating realistic close-up phone snapshots with flash lighting, distorted angles, and casual expressions using GPT Image 2.
[Character], clearly adult photorealistic, close-up phone snapshot, face extremely close to lens, slight wide-angle perspective, head tilted to one side, squinting or suddenly widened eyes, random uncontrolled expressions like sticking out tongue, pursing lips, or strange smiles. One hand raised from foreground near camera, randomly making peace signs, heart shapes, pointing at lens, covering half face, or other casual gestures. Direct front phone flash, face and skin illuminated by hard flash, background quickly darkened to near black. Extreme close-up, slight edge cropping, non-standard composition, private phone album snapshot feel, slight wide-angle facial distortion, realistic digital sharpening and JPEG texture. Tiny 'voxcat' signature bottom right.
A prompt for creating dreamcore night portraits with harsh flash lighting, frozen motion, and colorful bokeh against a black background.
[Character], clearly adult photorealistic, retaining hairstyle outline, hair color, eyes, main clothing colors, and iconic accessories.
Dreamcore night portrait ร Black field photography ร Flash freeze ร Star cluster bokeh ร Private snapshot.
Person in large deep black space, body sideways, suddenly looking back at camera, one hand raised to side of face blocking flash. Close-range skewed half-body composition, tilted shoulders, palm near lens, forming natural depth scale difference.
Strong on-camera direct flash freezes face, eyes, and moment. Light-colored jacket forms nearly overexposed glowing white block, character main color clearly shown in inner wear or accessories. Flash intensity decays rapidly with distance, some body contours merge into black field.
Arms, hem, and contour edges retain slight motion afterimages and soft focus, face remains clear. Scattered few red, blue, yellow light points in distance, varying size and blur, forming ambiguous spatial star cluster bokeh.
2:3 vertical, text element is tiny 'voxcat' signature bottom right.
Prompt for monkey-themed cosplay at a summer night BBQ stall with old phone camera quality.
Adult female Cosplayer, monkey-themed outfit, natural long black hair loose, some strands sticking to forehead, cheeks and neck due to heat and sweat. Wearing brown-white plush round ears, brown plush short-sleeve dress, cream-white plush trim on collar and cuffs, simple lace-up structure on chest, brown plush curled tail connected at waist, wearing thin gold necklace.
Character sitting on red plastic chair at summer night open-air BBQ stall, body leaning forward close to lens, head slightly tilted, looking directly at camera, cheeks flushed, small sweat beads on forehead and nose tip, lips slightly parted, playful expression from being heated by steam. One hand holding freshly grilled bone-in meat, meat close to side of face, surface charred brown, oily, bones clearly visible. Small monkey tightly beside character, monkey's front paws resting on table edge, looking up at meat in hand, forming natural private group photo squeezed into same frame.
Close-range skewed half-body composition, slight phone wide-angle perspective, face and meat close to lens, shoulders, arms and monkey naturally cropped at frame edges. Foreground has stainless steel grill tray, charcoal grill and several pieces of meat, grease reflection and smoke clearly visible. Background is real night market BBQ stall, plastic tables/chairs, diners' backs, simple sheds and warm yellow bulbs creating messy yet daily spatial layers.
Early 2000s old Nokia phone photography, low-pixel color digital photography, close-range direct flash, face and plush clothing illuminated by frontal flash, skin showing direct and slightly hard highlights, background brightness rapidly decaying, distant bulbs locally overexposed. Low resolution, slight out-of-focus, soft edges, rough digital noise, JPEG compression artifacts, limited dynamic range, uneven white balance, skin tone slightly cool gray and pink shift, background warm yellow lights mixed with cyan-gray shadows. Real snapshot, private record feel, retaining hot night sweat, messy hair and natural demeanor.
3:4 vertical format, only text in image is tiny handwritten signature "voxcat" in bottom right corner.
A dual-panel promotional poster for the 2025 Tsing Hua University Arts Festival featuring colorful floral illustrations in both sharp vector and soft-focus styles.
Create a split-screen graphic design poster for the '2025 Spring x Tsing Hua Arts Festival'. The left side features a clean white background with vibrant, flat vector-style illustrations of flowers including a large daisy, pink lilies, blue hydrangeas, and purple lilacs. Vertical Chinese text on the far left reads '2025 ๆฅไนๆธ
่ฏ่่ก็ฏ' alongside English text 'Spring x Tsing Hua Arts Festival'. The bottom left contains four distinct event categories: '้ณๆจๆๆจๅคงๅธซ็ญ', 'ๅตไฝๅฑ่ฆฝ', '่่กๅทฅไฝๅ', and '็ ่จ่ซๅฃ', each with specific dates (4/15-5/28) and small QR codes. The right side displays a soft-focus, dreamy version of the same floral arrangement against a warm, hazy cream background. Large serif typography at the top reads '2025 Spring x Tsing Hua Arts Festival', accompanied by smaller text 'ART CULTURE PEOPLE IN BLOOM'. The bottom right shows the dates '4.15 โ 5.28' and the logo 'TSING HUA UNIVERSITY'.
This prompt generates a promotional banner for a game development project featuring multiple AI-generated monster designs alongside explanatory Japanese text about turning common generative AI artifacts into enemy characters.
A horizontal banner image with a light beige background. On the left side, there is Japanese text in purple and yellow: 'ๅถไฝ่จ้ฒ #2 ๆตใญใฃใฉ็ทจ' (Production Record #2 Enemy Character Edition), followed by large bold text '็ๆAIใฎใใใใใใใใขใณในใฟใผใซ๏ผ' (Generative AI's "Common Occurrences" become monsters!), and smaller text below 'ใธใงใใณใฎๅ้บ ๏ฝใใคใบใฎๅคง่ฟทๅฎฎ๏ฝ ๆตใญใฃใฉๅถไฝใฎ2ๆฅ้' (Geneko's Adventure ~ The Labyrinth of Noise ~ Two Days of Enemy Character Creation). To the right of the text, there are two small chibi characters: a girl with brown hair wearing glasses and a school uniform holding an open book, and a blue cat-like creature with pink ears reading over her shoulder. The rest of the image is filled with a collage of various colorful monster designs arranged in rows. Top row includes a shiny green sphere with eyes, a muscular blue furry beast with glowing purple eyes, a purple insectoid robot with green wings, and a multi-limbed robotic figure. Middle section features a red beetle-like creature with warning signs on its shell, a wizard character wearing a rainbow-colored pointed hat and robe holding a staff, a white moth-like creature with blue eye patterns on its wings, a black spider-tank hybrid with red lights, and a pink abstract shape resembling a face or symbol. Bottom row shows a green goblin-like creature with glowing yellow eyes, a brown spiky turtle-like monster, a pale humanoid figure with blank facial features, a split-faced doll character (half pink/half grey) holding a knife, and a purple blob monster with angry eyes.
A dual-panel image showing a realistic overhead shot of pastel stationery alongside a matching cute watercolor illustration of the items as characters.
Goal: Create a vertical two-panel image contrasting a realistic top-down desk photo with a cute kawaii illustration of the same items.
Canvas: Vertical 4:5 aspect ratio, split horizontally into two equal sections.
Top Section (Realistic Photo): A high-angle flat-lay photograph on a clean white surface. Soft dappled sunlight shadows fall across the scene from the left. Items include: a mint green sticky note square labeled "Focus." in white serif text; a small square photo of a blue and beige macaron; three copper wire spiral paper clips scattered around; a light blue marker pen with cap off; a sage green mechanical pencil with gold tip; a light blue ballpoint pen with gold tip; a light blue highlighter; a teal envelope or folder edge on the left; and a lined notepad corner at the bottom left.
Bottom Section (Kawaii Illustration): A hand-drawn watercolor-style illustration on a cream background featuring anthropomorphic versions of the items above. The characters have simple happy faces (two black dot eyes, pink blush circles, smiling mouths). Elements include: a stack of two macarons (blue top, beige bottom) with a face; a sage green sticky note character labeled "Focus." holding a tiny heart; a tall green marker character standing upright; a lying down blue highlighter character; a lined paper sheet; a copper spiral clip; and yellow sparkle stars. Handwritten Korean text appears in two places: upper right says "์ง๊ธ, ์ข์ ๊ฒ์ ์ง์คํด์." (Now, focus on good things.) with a heart symbol; lower left says "์์ ์ค๋์ด ์ข์ ํ๋ฃจ๋ฅผ ๋ง๋ค์ด์." (Small todays make a good day.) underlined in green.
Visual Style: The top is crisp, bright, and airy photography. The bottom is soft, pastel-colored, whimsical watercolor art with thin outlines.
A stylized manga page illustrating the concept of prompt engineering for AI image generation, featuring a kitsune character and a breakdown of visual elements.
A vertical, highly detailed manga-style infographic page with a parchment-like background. The layout is divided into three main sections: a top illustration area, a middle diagrammatic breakdown, and a bottom text-heavy conclusion.
Top Section:
- A large, ethereal illustration of a woman with long white hair and fox ears (a kitsune) standing on a mountain peak at sunset. She wears flowing white robes.
- Below her, an elderly man with long black hair tied back, wearing dark blue traditional Chinese robes, sits cross-legged holding a calligraphy brush, looking up thoughtfully.
- To his right, a younger man in grey robes kneels, sketching the kitsune onto paper.
- Surrounding this scene are blocks of Japanese text explaining the concept of 'Prompt' (ใใญใณใใ).
- On the left side, there are four small square character portraits labeled with descriptions like 'Beautiful Woman', 'Dancer', etc., showing variations of female characters.
- Large vertical Japanese text on the right reads 'Introduction to Prompts'.
Middle Section:
- A horizontal flow diagram titled 'Verbalizing features to compose a picture'.
- It shows a sequence of six small square images connected by plus signs (+), leading to an equals sign (=) and a final result image.
- The sequence includes: 1. Long silver hair, 2. Blue eyes, 3. White clothes, 4. Mountain sunset, 5. Looking back pose, 6. Soft backlighting.
- The final result is the complete image of the kitsune from the top section.
Bottom Section:
- A large, bold Japanese headline in red and black ink style: "Listing hundreds of words loses one stroke" (็พ่ชใไธฆในใฆไธ็ปใๅคฑใ).
- Surrounding the headline are torn pieces of paper with handwritten notes listing negative effects of over-prompting, such as '8K resolution', 'ultra-high quality', 'complex composition', 'unnatural lighting', 'film-like lighting', 'large scale', 'highest quality'.
- At the very bottom, a concluding sentence in a box states that words are tools, but too many obscure the essence of the single stroke.
A comprehensive character design sheet for a protective shadow-beast Hell Hound and its tiny cat companion, featuring lore, anatomy studies, and behavioral poses.
Goal: Create a dark fantasy character design sheet for a 'Hell Hound' guardian creature, featuring a small cat companion named Stinky.
Canvas: Vertical infographic layout with a parchment-style background and gothic typography.
Layout: Top section features the main illustration; middle sections contain detail panels and skeletal studies; bottom section displays behavioral poses and a poetic oath.
Subject details: The Hell Hound is a massive, terrifying beast made of living shadow and charcoal-black fur. It has a skeletal, ancient skull head with glowing white eyes, long spindly limbs, and sharp claws. Despite its monstrous appearance, it is crouching protectively around a tiny, cute grey cat wearing a pink hoodie (Stinky). The atmosphere is moody, magical, and protective.
Text content: Include specific labels and lore text:
- Title: "HELL HOUND" in large gothic font.
- Subtitle: "FOREST GUARDIAN & PROTECTOR".
- Stats block: Type: Noble Protector, Habitat: Kolby's World, Skin: Charcoal Black - Guardian's Oath, Coat: Shimmering Void, Behavior: Protective โข Loyal โข Gentle, Primary Mission: Protect the innocent โ especially Stinky.
- Quote: "You will never harm what I swear to protect."
- Detail Panels: "COLOR VARIANTS" (Charcoal Black, Ash Gray, Corpse Gray), "SKIN DETAIL", "EYE DETAIL", "HEAD DETAIL", "TEETH", "CLAW / HAND".
- Skeletal Study: Front, Left, Back, Right views of the hound's skeleton.
- Movement & Behavior: Resting/Watching, Protecting, Sheltering, Gentle.
- Common Hiding Places: Forests, Abandoned Places.
- Odor: Smells like rain, moss, and ancient oaths.
- Bottom Section: "THE GUARDIAN'S OATH" poem starting with "I do not hunt her..." ending with "I am her forever." Footer text: "STINKY IS PROTECTED. ALWAYS. NO HARM SHALL TOUCH HER. EVER."
Visual style: High-fantasy concept art, dark academia aesthetic, detailed textures, dramatic lighting with golden sparks surrounding the hound.
A detailed character reference sheet featuring a male and female anime character in traditional Chinese Hanfu attire, including multiple angles and accessory close-ups.
A high-resolution character design sheet featuring two anime-style characters dressed in traditional Chinese Hanfu, set against a plain white background. The layout includes full-body front and back views for both characters, along with detailed close-ups of their heads, accessories, and clothing textures.
Left Character (Male):
- Appearance: Young man with short black hair wearing a tall, structured black official's hat (Guan) with ribbons hanging down. He has blue eyes and a gentle expression.
- Outfit: A dark navy/black cross-collar robe (Yi) with wide sleeves, trimmed with a patterned reddish-brown border. Underneath is a white collar. He wears a long skirt-like lower garment (Shang). A belt with a gold buckle secures the waist, from which hangs a jade pendant ornament (Pei) with red tassels. He holds a sword in a black scabbard with red accents.
- Views: Front full-body view holding the sword; back full-body view showing the drape of the robe; headshot close-up; isolated detail shots of the hat, belt buckle, jade pendant, and sword.
Right Character (Female):
- Appearance: Young woman with light brown/auburn hair styled in an elaborate updo with loops and side bangs framing her face. She has blue eyes and a calm expression. Her hair is adorned with a hairpin featuring a jade disc and red tassel.
- Outfit: A layered ensemble consisting of a peach/light orange outer robe with a subtle floral pattern and deep red trim at the collar and cuffs. Underneath is a cream-colored pleated skirt (Qun) with a reddish-brown patterned panel visible at the hem. A pink sash is tied around the waist, also featuring a hanging jade ornament.
- Views: Front full-body view; back full-body view showing the long hair and robe details; headshot close-up; isolated detail shots of the hairpin, collar texture, and waist sash knot.
A comprehensive character reference sheet for an armored anime heroine, including profile stats, orthographic turnaround, expression variations, wardrobe breakdown, material palette, and technical notes.
Create a highly detailed, professional character design sheet for an anime-style female warrior named {argument name="character name" default="RU RIO"}. The layout should be organized into distinct sections on a dark background with gold and white text.
**Top Left (Profile):** A header titled "CHARACTER PROFILE" featuring a winged emblem. Below it, the name "RU RIO" in large serif font, subtitle "SWORD QUEEN". Include a data list: AGE (22), HEIGHT (172cm), OCCUPATION (Sword Queen), AFFILIATION (The Royal Court of Elysion), TITLE (Heir to the Radiant Throne), ELEMENT (Light), WEAPON (Regal Longsword "Lumina Regalia"). Add a "PERSONALITY" section describing her as calm and unwavering, and a "LIKES/DISLIKES" section. End with a quote: "A queen's blade shall never waver."
**Top Center (Main Art):** A large, high-quality bust portrait of the character looking slightly upward. She has short black hair, grey eyes, and wears intricate silver plate armor with gold filigree and a high collar.
**Top Right (Turnaround & Analysis):** A section labeled "ORTHOGRAPHIC TURNAROUND" showing five full-body views of the character standing straight: FRONT, 3/4 FRONT, SIDE, 3/4 BACK, and BACK. To the right of this is a "PROPORTIONAL ANALYSIS" diagram showing the front view with horizontal grid lines marking head-to-foot ratios (Head x 1, Head to Chin, etc.).
**Middle Band (Expressions):** A row labeled "EXPRESSION ANCHORS" containing eight square panels showing close-ups of the character's face with different emotions: NEUTRAL, CALM, DETERMINED, PROUD, SOFT SMILE, SWEET SMILE, CONCERN/HANDLING, and BATTLE CRY.
**Bottom Left (Wardrobe):** A section titled "WARDROBE & ACCESSORIES BREAKDOWN". It displays the full outfit on a mannequin, followed by isolated items labeled: CLOAK, TORSO ARMOR, GAUNTLETS, LEG ARMOR, BOOTS, and various small accessories like belts and jewelry.
**Bottom Center (Materials & Details):** Two rows. The top row is "MATERIAL PALETTE" showing swatches for SILVER STEEL, MIDNIGHT SATIN, STARCHED TOP, ROYAL LEATHER, and GILDED TRIM. The bottom row is "DETAIL CLOSE-UPS" showing macro shots of SHOULDER PAULDRON, CHEST ORNAMENT, THIGH STRAP & CHAIN, THIGH HARP & CHAIN, and SWORD HILT DETAIL.
**Bottom Right (Technical):** A column with "TECHNICAL NOTES" listing bullet points about the silhouette and fabrics. Below that, a "COLOR SCHEME" strip with diamond-shaped color swatches. Finally, a "RIG & MOVEMENT REFERENCE" section showing three small wireframe/skeleton diagrams of the character.
A detailed prompt for generating a vertical editorial storybook illustration of a woman studying in a cafe, featuring Scandinavian folk-art simplicity and watercolor sketchbook aesthetics.
GPT IMAGE 2 on CHATGPT
Use case: illustration-story
Asset type: vertical editorial storybook illustration, standalone generation without any reference image
Scene/backdrop:
A quiet neighborhood cafรฉ depicted as a minimal, poetic everyday scene. A young woman sits alone at a small round cafรฉ table, studying on an open MacBook. Include only a simple chair, the laptop, one notebook, a pen, a ceramic cup, and a small suggestion of a cafรฉ window or pendant lamp. Keep the environment sparse and flattened, with no detailed interior architecture.
Subject and action:
Show the young woman in a relaxed three-quarter side view, leaning slightly toward the laptop with one hand near the keyboard and the other writing a note. Her expression is calm, curious, and absorbed in studying. Give her simplified childlike proportions, a softly rounded face, slightly oversized hands, a compact geometric hairstyle, and a natural seated pose. Dress her in a patterned cardigan, loose trousers, and simple shoes. The laptop should be recognizable as a slim MacBook, but do not show a prominent logo or any readable screen content.
Style and medium:
Decorative folk flat illustration infused with delicate minimal watercolor sketchbook art. Combine Scandinavian folk-art simplicity, Japanese picture-book restraint, and modern flat editorial illustration. Reduce every person, object, and furnishing to clean, softly rounded geometric color blocks. Use opaque gouache-like shapes layered with faint translucent watercolor washes. Add loose, imperfect ink-pen contours with gently wavering line weight, occasional broken edges, tiny scratch marks, short stitch lines, dots, and naรฏve hand-drawn patterns. The drawing must feel handmade, slightly asymmetrical, tender, and intentionally imperfect.
Color palette:
Use a fresh palette completely independent from the source image: dusty violet, periwinkle blue, raspberry red, pale lemon, apple green, warm cocoa brown, and creamy ivory paper. Use no teal, coral-orange, mustard, or dark navy as dominant colors. Keep the palette limited and harmonious, with violet or periwinkle as the main clothing color and raspberry and lemon used only as playful accents.
Composition:
Portrait orientation, approximately 2:3. Make the seated woman and laptop the unmistakable focal point, occupying about 60 percent of the canvas. Use a gently cropped table and chair to anchor the lower half. Preserve generous off-white negative space around the figure, especially above and along the outer edges. Use a mostly flat side-view perspective with only a slight tabletop angle. Keep the visual hierarchy simple and immediately readable.
Decorative details:
Scatter only a few tiny floating elements through the empty space: four or five dots, two miniature petals, one naรฏve eight-point star, a small leaf sprig, and one faint lavender watercolor splash. Add a tiny hand-drawn check or seed pattern to the cardigan and a simple scalloped edge on the cup or lampshade. Decorat
A prompt for generating a minimalist, experimental typography poster with a Mid-Autumn theme, featuring large sans-serif characters and Gucci red accents.
Take any futuristic theme providing core concepts, short phrases, and minor auxiliary notes, and translate the theme into an extremely enlarged text or symbol subject: The first impression must be heavy, bold sans-serif glyphs filling almost the entire frame, pressed horizontally into the layout, with the character body occupying the center like structural beams, partially cropped or overflowing, making reading first become a strong form event before reading subtitles at its edges. Keep the background largely empty with cool white space, overlaid with extremely thin, light warm-colored composition lines, baselines, and vertical column lines; these lines should look like unhidden skeletons of a design draft rather than decoration. Use only high-saturation orange-red as the primary color to carry all visual weight, gray for small explanatory text, avoiding multi-colors and gradients. Information modules are sparsely placed at grid intersections and edges: small icons composed of simple geometric angles, dots, and short dashes; titles are short and bold; body text is in narrow columns and light gray. The overall presentation should have a precise, restrained, experimental typographic educational feel. Glyph construction requires low contrast, thick strokes, large open counters, flat terminals, tight tracking; punctuation and auxiliary symbols also follow the grid rhythm. If switching to other writing systems, maintain equivalent block volume, inner/outer spatial relationships, cropping pressure, and horizontal reading momentum. Prohibit illustrative backgrounds, shadows, paper textures, centered cards, rounded cuteness, commercial poster lighting effects, and over-packed information.
โโโโโโ
Theme: {argument name="theme_en" default="Joy"}
Aspect Ratio: {argument name="aspect_ratio_en" default="9:16"}
Note: Appropriate Mid-Autumn elements
Font Color: {argument name="font_color_en" default="Gucci Ancora Red"}
A detailed industrial-style infographic poster illustrating the workflow and principles of a wastewater treatment plant, featuring process diagrams and bold typography.
Create a horizontal infographic poster explaining the working principles of a wastewater treatment plant. The design style is industrial, modern, and high-contrast, utilizing a color palette of deep red, black, white, and teal/blue for water elements.
**Layout & Text Elements:**
1. **Top Left/Center (Headline):** Large, bold, distressed red Chinese characters "ๆฑกๆฐดๅค็ๅ" (Wastewater Treatment Plant) spanning across the top. Below it, large black bold text "ๅทฅไฝๅ็" (Working Principles). Smaller black text underneath: "ไป่ฟๆฐดใๅ็ฆปใ็ๅๅๅบๅฐๅๅๅบๆฐด" (From influent, separation, biochemical reaction to purified effluent).
2. **Left Sidebar:** Vertical layout with small text blocks. Top block: "่ฎฉๆฏไธๆปดๆฑกๆฐด้ๅ่ช็ถ" (Let every drop of sewage return to nature), "ๆฐด็ไธไธ็ซๆฏๆดๆดๅ็ๆชๆฅ" (Water's next stop is a cleaner future), English text "CLEANER WATER BRIGHTER TOMORROW". Bottom block (red background): "ๅค็ๆนๅไธบไบๆดๅฅฝ็ๆฐด็ฏๅข" (Treatment changes for a better water environment), English text "CLEAN CYCLE HEALTHY CITIES".
3. **Right Side (Background Image):** A large photographic collage showing an aerial view of circular clarifier tanks filled with blue-green water, connected by pipes and walkways. Overlay text on the right: "ไปๆฑกๆฐดๅฐๆธ
ๆฐด" (From sewage to clear water), "่ฟๆฅๅๅธไธๆดๅฅๅบท็็ๆดป" (Connecting cities with healthier lives), "FOR A CLEANER TOMORROW", "ๆฐดๅพช็ฏ ๅๅธ่ฟ่ก ไธ่ช็ถๅ
ฑ็" (Water cycle, city operation, symbiosis with nature), "ๅๅ ่ฎฉๅๅธๆดๆ็ๅฝๅ" (Purification makes cities more vibrant), "CLEAN WATER STRONGER CITIES".
4. **Bottom Center (Process Diagram):** A schematic cross-section diagram showing the flow of water through different stages. Arrows indicate direction from left to right. Labels above the sections: "ๆ ผๆ
/ ๆฒ็ " (Screening/Grit Chamber), "ๅๆฒ" (Primary Sedimentation), "็ๅๅๅบ" (Biochemical Reaction - depicted with bubbles), "ไบๆฒ" (Secondary Sedimentation). Labels at ends: "่ฟๆฐด" (Influent) on left, "ๅบๆฐด" (Effluent) on right.
5. **Bottom Right:** Small text block: "ๆดๅนฒๅ็ๆฐด ๆดๅฎๅฑ
็ๅๅธ ๆดๅฏๆ็ปญ็ๆๅคฉ" (Cleaner water, more livable cities, more sustainable tomorrow), English text "CLEANER WATER HEALTHIER CITIES A BRIGHTER TOMORROW".
6. **Center Red Box:** A small red square containing white text: "็ไธ่ง็ๅทฅ็จ ๆฏๆ็ๅพ่ง็็พๅฅฝ็ๆดป" (Invisible engineering supports visible good life), English text "INFRASTRUCTURE FOR A HEALTHIER TOMORROW".
**Visual Style Details:**
* Use a grainy texture overlay on the entire image to give it a printed paper feel.
* The typography should be heavy sans-serif for Chinese characters.
* The water in the photos and diagrams should be a distinct teal/cyan color against the grayscale/red/black background.
A detailed prompt for generating minimalist, high-aesthetic posters with a sense of ceremony and rationality using GPT Image 2. It specifies layout, typography, color usage, and negative constraints to achieve a museum-like white space effect.
Create a minimalist ceremonial information poster around any given theme. The first impression must be a large area of warm white empty space where the main title is precisely centered, engaging in solemn alignment with three thematic symbols: transform the core name, participants, or keywords provided by the theme into a large thin-stroke title at the top, a set of recognizable abstract logos in the center, and solid color blocks on both sides; semantics may change but order remains constant. Retain high-ratio whitespace, vertical central axis, upper-lower zoning, and the pause feeling of thin black horizontal lines; arrange all elements restrainedly like an exhibition catalog or international institutional yearbook. Use high-contrast fine serifs or equivalent glyph structures for the main text, with open counters, slender strokes, sharp terminals, and spacious rhythm, maintaining a slender skeleton, loose tracking, clear recognition, and calm breathing when switched to any writing system, rather than copying a specific Latin font. Extract two high-purity representative colors from the theme for hard-edged squares; use only black lines and minimal solid geometry for the central logo; keep the background as slightly paper-textured warm white, avoiding gradients, shadows, and decorative textures. Place subtitles and small explanatory text at a lower center of gravity at the bottom, with footer micro-information pressing the edges, creating a contrast where grand themes are tamed by museum-style whitespace; failure symptoms include crowded elements, chaotic colors, thick fonts, realistic icons, or the poster losing its cold ritual order.
Set the theme to "City Public Library Open Day" for a public cultural institution event main poster: use indigo blue and cinnabar red as the two high-purity square colors; abstract opened book pages and door arches with black lines in the center, letting the symbol group fall steadily below the title along the vertical axis; place the main title in the center of the upper half, with subtitles and dates forming a sparse two-level information hierarchy below, retaining large areas of warm white whitespace and thin black line pauses; aspect ratio is vertical 3:4.
A structured prompt for creating a 3x3 grid of realistic user-generated content style panels for marketing campaigns, including space for cinematic visuals and production notes.
Create a full-sheet 3x3 grid of realistic UGC-style panels featuring this {argument name="category" default="provision store"} using GPT Image 2. Split the video into 3 continuous sections. Each panel must contain a cinematic visual frame plus readable production notes printed directly inside the panel. The goal isn't just to show the product. Itโs to help customers imagine a reason to buy it. The business name is {argument name="business name" default="Zioraa Ventures"}. Embedded the business name in the background.
Creates a split-screen scene comparing a misty golden forest deer photograph with a minimalist needle-felt wool illustration.
Goal: Create a two-panel horizontal comparison image showing a real-life nature photo transformed into a minimalist needle-felt illustration.
Canvas: Wide 16:9 canvas split vertically into two equal halves with a clean straight division down the center.
Left panel: A realistic golden-hour forest meadow photograph. Show exactly 5 deer in the foreground: 1 deer walking at far left, 1 deer grazing left-center, 1 deer grazing center, 1 small deer standing upright center-right, and 1 larger deer standing at far right. The meadow is covered in dewy green grass, with warm yellow sunlight and soft morning mist. In the background, dark evergreen trees form a dense forest silhouette, with additional leafy branches at the upper right. Strong sunbeams stream diagonally through the trees from the upper right, creating a serene cinematic atmosphere.
Right panel: A soft handmade needle-felt wool reinterpretation of the same scene on a warm off-white textured paper background with generous blank space. Center the felt scene horizontally in the upper-middle area. Show exactly 5 small felt deer matching the left panel arrangement: 1 standing deer at far left, 1 grazing deer left-center, 1 orange-brown grazing deer center, 1 small upright deer center-right, and 1 larger standing deer at far right. Place them on a thin strip of fuzzy pale green felt grass. Above them, include a simple round felt sun and 2 soft horizontal felt cloud wisps. Under the felt grass, add handwritten text reading {argument name="caption text" default="A kinder morning โก"} in a delicate gray-brown script.
Visual style: Combine warm healing aesthetics, generous white space, cozy wool-felt texture, soft edges, muted earthy colors, and a calm poetic mood. The left side should look photographic and atmospheric; the right side should look like a handcrafted felt illustration with visible fibers and a minimal composition.
Constraints: Keep the split-screen layout, exactly 5 deer on each side, no extra animals, no border, no watermark, no additional text beyond the caption.
Generates a professional technical infographic with blueprint-style overlays, including dimensions and diagrams for product design visualization.
Premium technical infographic of {argument name="product" default="[Apple 18 pro ]"}. Use the reference image only to understand the shape and structure of the object, without copying the same photo, angle, composition, or background. Reinterpret the subject in a new professional and realistic photograph, clean and well-lit, with a suitable and more aesthetic background. Keep the object as a real photo, not an illustration. Add a technical blueprint-style overlay with white lines, arrows, dimensions, labels, and small diagrams of parts, materials, measurements, and functionality. Clear, elegant, and informative composition. Include a sketch box in the upper left corner with the title "{argument name="title" default="[Apple 18 pro]"}
A prompt to transform an attached research paper into a professional academic poster following specific conference regulations.
Research the poster regulations for presentation at the {argument name="conference name" default="2026 Neuroscience Conference"} and transform the attached paper into a poster accordingly.
A comprehensive prompt setup to generate clean 3D graphic design layouts, informational diagrams, and matte-texture presentation slides.
You are an information editor, diagram designer, and 3D art director.
- Compare 3 visual proposals matching the content, and adopt the most intuitive option.
- Explain using objects or materials specific to the subject. Use books, bamboo slips, or paper for classical literature; parts or assembly for manufacturing.
- Elegant matte materials, soft lighting, and natural depth. Use 3D representations to convey sequence, relationships, and changes.
A prompt for generating a realistic image of a girl in a modified school uniform fighting zombies in a burning medieval village.
A hyper-realistic, cinematic action shot of a young Japanese female warrior in the midst of a chaotic medieval battle. She has long black hair tied back with two gold hair clips and wears a modified dark blue sailor-style school uniform (seifuku) reinforced with heavy leather armor on her shoulders and arms. Her face is dirty with soot and blood splatters, showing an intense, determined expression as she lunges forward. In the foreground, blurred zombie-like creatures are attacking. The background depicts a burning village with wooden structures, smoke rising into the sky, and other soldiers fighting amidst the chaos. The lighting is dramatic and gritty, emphasizing the realism of the scene.
A cinematic render of a bearded Minecraft avatar holding a bee in a sunflower field at sunset, featuring a pixelated rainbow background.
A hyper-realistic, cinematic close-up shot of a Minecraft-style character standing in a vibrant field of sunflowers during a golden sunset. The character is constructed from blocky voxels, featuring dark skin, a full black beard, and wearing a green cap with a white t-shirt and green pants. He is holding a large, blocky bee gently against his face. Surrounding him are numerous other flying bees with translucent wings, rendered with realistic motion blur and depth of field. In the background, there is a pixelated rainbow arching across an orange sky filled with blocky clouds, a distant tree line, and a small white pickup truck on a dirt road. The lighting is warm and volumetric, creating a nostalgic and peaceful atmosphere.
A creative image generation prompt describing a llama undergoing a wild magic transformation with enchanted vines and elemental effects.
A llama undergoing a Wild Magic Transformation as enchanted vines, glowing feathers, dragon scales, elemental flames...
A prompt for GPT Image 2 to generate a surreal, photorealistic scene of a man sitting on a cloud above a city drinking coffee.
Create an ultra-realistic, cinematic, photorealistic surreal photograph of a handsome young South Asian man sitting casually on a gigantic fluffy white cloud hundreds of meters above a sprawling modern city, peacefully drinking a cup of coffee while commercial airplanes fly beneath and around him.
The man is in his mid-20s, with thick slightly messy wavy black hair, warm brown skin, expressive deep-brown eyes, and a neatly trimmed beard and mustache. He wears an oversized black technical jacket over a clean white T-shirt, dark wide-leg cargo trousers, futuristic black sneakers, a silver chain, and a black smartwatch. His expression is calm and relaxed, as if sitting on a balcony above the world.
The enormous cloud looks physically realisticโsoft, dense, voluminous and detailed, with individual vapor textures and subtle sunlight passing through its edges. The man sits naturally on its surface, one leg slightly hanging over the edge, holding a realistic ceramic coffee cup in one hand.
Far below, a vast modern city stretches toward the horizon with skyscrapers, roads, tiny vehicles, parks and realistic atmospheric haze. Several passenger airplanes fly through the sky at different distances and scales, creating an incredible sense of depth. One airplane passes relatively close beneath the cloud while others appear tiny near the horizon.
Golden-hour sunlight illuminates the scene from the side, creating warm highlights on the man's face, clothing and cloud while casting soft natural shadows. The sky transitions from bright blue near the horizon to deeper blue overhead, with subtle wispy clouds scattered across the atmosphere.
Use an epic wide-angle composition showing the enormous scale difference between the man, cloud, airplanes and city below. Strong foreground-to-background depth, realistic atmospheric perspective, natural reflections, physically accurate lighting, detailed skin texture, realistic fabric fibers, realistic hair strands, cinematic color grading, HDR, subtle film grain, shallow depth of field on the character with the distant city naturally softened.
Photographed like a high-end cinematic editorial campaign, 35mm lens, f/2.8, ultra-detailed, 8K UHD, photorealistic, natural proportions, realistic human anatomy, believable physics, dramatic scale, surreal but completely convincing.
No cartoon appearance, no illustration, no CGI look, no plastic skin, no distorted face, no extra fingers, no duplicate people, no deformed airplanes, no floating objects, no text, no watermark.
A prompt for generating an ultra-realistic cinematic scene of a man standing in a hall surrounded by doors leading to different worlds like cosmic dimensions, frozen kingdoms, and cyberpunk cities.
Ultra-realistic, cinematic 8K HDR, high-fashion editorial photograph of a strikingly handsome young man in his early 20s, with thick naturally wavy jet-black hair, strong masculine eyebrows, intense deep dark-brown eyes, a sharply defined sculpted jawline, subtle natural stubble, and realistic skin texture with visible pores.
CONCEPT & COMPOSITION:
A breathtaking, surreal cinematic scene featuring a handsome young man standing confidently at the center of a gigantic, mysterious hall surrounded by dozens of magnificent doors of different shapes, sizes, materials, and architectural styles. Every door opens into a completely different world, creating a spectacular visual contrast between reality, fantasy, and the unknown.
The young man wears a perfectly tailored black outfit consisting of a luxurious black high-neck shirt, a long elegant black coat, tailored black trousers, and polished black boots. His thick, naturally wavy hair is slightly tousled, and his intense eyes gaze directly toward the camera with a calm, confident, mysterious expression. One hand rests gently on the handle of a partially opened door, as if he is about to step into another dimension.
THE DOORS & THEIR WORLDS:
Surrounding him are dozens of enormous, beautifully detailed doorways, each revealing a unique and breathtaking environment:
๐ Cosmic Dimension: A glowing galaxy filled with colorful nebulae, distant planets, stars, and swirling cosmic energy.
๐๏ธ Frozen Kingdom: A magical winter landscape with snow-covered mountains, frozen waterfalls, and gently falling snow.
๐ฅ Kingdom of Fire: A dramatic volcanic world with flowing rivers of lava, burning skies, and glowing embers.
๐ธ Cherry Blossom Paradise: A peaceful Japanese landscape filled with pink cherry blossoms, a traditional Japanese temple, and a beautiful red bridge.
๐ฐ Dark Fantasy Realm: A mysterious gothic castle surrounded by a dark enchanted forest and a sky illuminated by lightning.
๐ Cyberpunk Future: A futuristic city with towering skyscrapers, glowing neon signs, flying vehicles, and vibrant blue and purple lights.
๐ฟ Enchanted Forest: An extraordinary magical forest with gigantic ancient trees, glowing flowers, floating golden particles, and mystical waterfalls.
โ๏ธ Heavenly Dimension: A magnificent world above the clouds featuring golden palaces, radiant sunlight, and endless white clouds.
๐๏ธ Lost Desert Civilization: An ancient golden city surrounded by desert dunes.
A creative writing snippet serving as a prompt for a steampunk-themed image titled 'The Last Gear', created with GPT Image 2.
"The Last Gear"
The mechanical city had stopped.
I gently picked up the last remaining gear.
If this meshes,
surely, this world will move again.
โ๏ธ๐งโจ
A prompt for generating a realistic image of a colossal MPD robot assisting in a nighttime disaster relief operation with human first responders.
A cinematic, photorealistic night scene depicting a massive bipedal police robot standing in the center of a muddy disaster response zone during heavy rain. The giant robot is white and black with industrial paneling, featuring red emergency lights on its shoulders and head, and markings that read "่ญฆ่ฆๅบ MPD" (Metropolitan Police Department) on its chest and arms. Its head consists of multiple camera lenses arranged horizontally. Surrounding the robot's feet are numerous first responders: police officers in dark uniforms with "MPD" on their backs, firefighters in orange gear, and paramedics in blue vests with Japanese text. To the left is a mobile command unit truck displaying screens with data maps. In the background, there is a large pile of rubble or debris illuminated by floodlights, with excavators visible atop the mound. Several drones hover in the sky, casting bright spotlights down onto the wet ground. The atmosphere is tense and high-tech, with reflections on the wet pavement and rain streaks visible against the dark sky.
A high-quality anime-style portrait of a girl holding an old book on a snowy street at twilight, featuring warm lighting and falling snow.
Create a vertical digital illustration in a semi-realistic anime style depicting a young woman standing on a snowy cobblestone street during twilight. The subject has long, dark hair with bangs, dusted with white snowflakes, and fair skin with soft pink blush on her cheeks and nose. She is looking upward to the right with a gentle, wistful expression, exhaling a visible puff of white breath into the cold air. She wears a thick, textured beige wool coat and a matching chunky scarf wrapped around her neck. In her arms, she clutches a vintage brown leather-bound book with gold detailing on the cover. To the left, a classic black iron street lamp glows with a warm yellow light. The background features blurred European-style brick buildings with snow-covered roofs and distant church spires against a sky transitioning from deep blue to purple and orange. Falling snowflakes are scattered throughout the scene.
A realistic depiction of a giant Japanese police mech lifting a destroyed car on a rainy Tokyo highway.
A cinematic, photorealistic image of a colossal bipedal police robot standing on a wet Tokyo highway at dusk. The robot is constructed from heavy black mechanical joints and white armored plating, with "่ญฆ่ฆๅบ" and "MPD" clearly printed in black text on its chest plates. It has red emergency lights mounted on its shoulders and a complex sensor array head. In its left hand, the robot is lifting a heavily crushed, mangled black sedan off the ground. The scene is chaotic but organized: in the foreground, a Japanese police car with flashing red lights sits on the left, while officers wearing dark uniforms and high-visibility yellow vests labeled "POLICE" direct traffic with glowing batons. Orange traffic cones line the wet asphalt, which reflects the city lights. In the background, green overhead highway signs display directions for "Shutoko Expwy," "Ginza," "Tokyo Sta.," and "Hamamatsucho." A large tow truck with an orange crane arm is visible to the right. The atmosphere is moody and industrial, with rain-slicked surfaces and a backdrop of blurred skyscrapers.
Reverse-engineered prompt to convert a hand-drawn illustration of a WWII fighter plane into a hyper-realistic, cinematic aerial shot.
Using the provided reference image, transform this hand-painted digital artwork into a photorealistic cinematic photograph. Keep the composition of the weathered fighter plane and pilot identical, but render all surfaces with high-fidelity textures: replace the painterly brushstrokes on the fuselage with realistic oxidized metal, peeling paint, and rust. Render the pilot's gear as authentic leather and fabric. Convert the abstract background into a detailed aerial view of a burning landscape below, featuring volumetric smoke plumes, realistic fire glow, and atmospheric motion blur to simulate a high-speed dive.
A prompt for a heartwarming 3D animated cinematic scene of an elderly couple dancing and filming in a cozy vintage hallway, specified as being generated by GPT Image 2 via ChatGPT.
Create a heartwarming 3D animated cinematic scene inside a cozy vintage hallway. An elderly woman with short white hair, round glasses, a mustard-yellow loose top, beige pants, and slippers playfully poses and dances while an elderly man in a light blue shirt and beige pants crouches nearby, recording her with a smartphone. Warm golden indoor lighting, wooden walls, framed artwork, patterned Persian rug, hanging lamp, cozy home atmosphere. The woman changes playful poses naturallyโarms wide, pointing, smiling, raising both handsโwhile the man moves slightly as he films her. Expressive faces, charming comedic timing, smooth natural body movement, consistent character identity, detailed Pixar-like 3D animation, cinematic depth of field, realistic lighting, warm color grading, smooth camera movement, high detail, 4K.
A realistic image of a giant police robot managing a traffic checkpoint on a Tokyo highway with officers and cars.
A hyper-realistic, wide-angle shot of a massive bipedal police robot standing in the middle of a busy Tokyo highway checkpoint. The robot is towering over the cars, featuring a complex mechanical design with black and white armor plating, exposed hydraulic joints, and red emergency lights on its shoulders. It has a rectangular head unit with multiple camera lenses instead of a face. The text '่ญฆ่ฆๅบ MPD' (Metropolitan Police Department) is printed in white on its chest and shoulder plates. One of its large mechanical hands is raised in a 'stop' gesture. In the foreground, human police officers wearing dark blue uniforms and white helmets are directing traffic; one officer holds a glowing red baton. A white vertical sign stands near them with Japanese text reading 'ๆคๅๅฎๆฝไธญ' (Checkpoint in progress). Orange traffic cones line the road. To the right, a black van and other vehicles are stopped for inspection. The background features a clear blue sky, modern city skyscrapers, overhead green highway signs indicating directions to 'Shutoko Expwy', 'Ginza', and 'Ueno', and the iconic Tokyo Skytree visible in the distance.
A detailed prompt for generating an ultra-realistic cinematic dark-fantasy photograph of a handsome young man standing beneath Gothic cathedral arches, featuring dramatic lighting and mysterious atmosphere.
Ultra-realistic cinematic dark-fantasy photograph of a strikingly handsome young man in his early 20s standing alone beneath enormous Gothic cathedral arches. He has thick naturally wavy jet-black hair, strong eyebrows, deep dark-brown eyes, a defined sculpted jawline, subtle natural stubble, realistic skin texture, visible pores, and refined masculine facial features.
He wears an elegant long black tailored coat over a dark high-neck shirt, giving him a mysterious, powerful presence. Towering Gothic arches rise dramatically above him, decorated with intricate stone carvings, weathered columns, and enormous shadowy vaulted ceilings. Sharp beams of golden-white light pierce through dense atmospheric smoke and mist, illuminating parts of his face and shoulders while the rest of the cathedral disappears into deep darkness.
Ancient stone floor slightly wet and reflective, faint dust particles floating through the light, subtle candlelight in the distant background, dramatic volumetric lighting, deep shadows, strong chiaroscuro, gothic architecture, mysterious sacred atmosphere, cinematic composition, realistic proportions, natural expression, highly detailed stone textures, photorealistic skin, HDR, 85mm lens, shallow depth of field, dramatic perspective, dark luxury editorial photography, ultra-detailed, 8K, no women, no text, no watermark, no AI-looking face, vertical 9:16.
A prompt for creating a surreal cinematic photograph splitting a man between 1920s vintage and 2120 futuristic aesthetics using GPT Image 2.
Ultra-realistic cinematic surreal photograph of a strikingly handsome young man in his early 20s standing exactly at the boundary between two centuries, creating a seamless visual split between 1920 and 2120.
He has thick naturally wavy jet-black hair, strong eyebrows, deep dark-brown eyes, a defined sculpted jawline, subtle natural stubble, realistic skin texture, visible pores, and refined masculine facial features.
The LEFT side of the image represents the 1920s: an elegant vintage city street with Art Deco architecture, classic automobiles, old brick buildings, warm amber street lamps, vintage shop signs, pedestrians in 1920s suits and coats, subtle film grain, sepia tones, and authentic period atmosphere. The young man wears a perfectly tailored 1920s three-piece suit, pocket watch, polished leather shoes, and vintage hairstyle details.
The RIGHT side represents the year 2120: a breathtaking futuristic metropolis filled with towering glass-and-metal skyscrapers, holographic advertisements, autonomous flying vehicles, glowing neon architecture, futuristic pedestrians, advanced technology, floating transportation systems, and subtle atmospheric mist. The young man wears an elegant futuristic black tailored suit with sophisticated metallic details and subtle glowing accents.
The center of the composition shows the two eras merging around him, with a luminous temporal distortion, floating clock fragments, particles, and ripples in reality connecting 1920 to 2120. His body subtly transitions between both eras while his face remains identical and perfectly realistic, symbolizing a man caught between past and future.
Epic cinematic composition, symmetrical split-world concept, dramatic perspective, realistic environmental reflections, volumetric lighting, atmospheric depth, physically accurate materials, highly detailed skin, natural facial expression, photorealistic, 8K HDR, ultra-sharp focus, cinematic color grading, 35mm photography, masterpiece, no text, no watermark.
First-person view from inside a fighter jet cockpit looking at another jet banking sharply against a backdrop of motion-blurred clouds and blue sky.
A hyper-realistic, first-person perspective shot from inside a fighter jet cockpit during an intense aerial maneuver. The camera is positioned behind the pilot's gloved hand gripping the control stick in the lower left foreground. Through the curved canopy glass, a second fighter jet is visible flying ahead and slightly above, banking hard to the right with its afterburner glowing bright orange. The scene captures a high-speed turn, creating significant motion blur on the clouds and landscape below. The sky is a vibrant blue filled with streaking white cumulus clouds that warp around the edges due to the speed and G-force. A green digital Heads-Up Display (HUD) overlay is projected onto the canopy glass on the left side, showing flight data such as 'G 7.6', 'M 0.92', and heading numbers like '320'. The lighting is bright daylight, casting realistic reflections on the canopy frame and instruments.
Creates a cinematic night photograph of a man in a vintage red telephone booth during heavy rain, emphasizing moody lighting and realistic details.
Ultra-realistic cinematic night photograph of a strikingly handsome young man in his early 20s sitting inside a vintage red telephone booth on a deserted city street at midnight. He has thick naturally wavy jet-black hair, strong eyebrows, deep dark-brown eyes, a defined sculpted jawline, subtle natural stubble, realistic skin texture, visible pores, and refined masculine facial features. He holds an old black telephone receiver close to his ear, with a mysterious, thoughtful expression as he looks slightly toward the rain-covered glass.
Heavy rain falls outside, droplets streaming down the glass panels, while dense atmospheric fog surrounds the booth and softly obscures the empty street. Wet pavement reflects the warm amber glow of the booth and distant streetlights. Vintage urban architecture fades into the mist in the background. Subtle neon reflections, cinematic rim lighting, soft volumetric light beams, deep shadows, moody midnight-blue atmosphere, realistic reflections on wet surfaces, shallow depth of field, 85mm lens, f/1.4, dramatic film grain, high dynamic range, photorealistic skin, intricate fabric details, sophisticated noir aesthetic, mysterious and emotional atmosphere, premium editorial photography, 8K, ultra-detailed, natural proportions, no text, no watermark, no women.
Generates a dynamic first-person view of a motorcycle race cornering at high speed with motion blur effects.
A high-speed, first-person point-of-view (POV) shot from a racing motorcycle on a professional circuit. The camera is tilted aggressively to the left, simulating a sharp cornering maneuver at speed. In the immediate foreground, the rider's gloved hand (white and red leather) grips the handlebar, with a digital dashboard visible showing '93 km/h' and gear indicator '2'. Ahead on the asphalt track, another racer in full leathers leans deeply into the curve, their bike nearly parallel to the ground. The background features blurred scenery due to motion blur: green trees, distant mountains under a bright blue sky with scattered clouds, and red-and-white curbing along the edge of the track. The lighting is natural daylight, creating realistic reflections on the tarmac and helmets.
A vertical social media thumbnail comparing an impressionist oil painting of two girls with lanterns to its photorealistic AI-generated recreation.
Create a vertical 9:16 social media thumbnail. The background is a hyper-realistic, high-resolution photograph of two young girls with curly brown hair wearing vintage white lace-trimmed dresses standing in a lush garden at twilight. They are holding and decorating glowing pink paper lanterns. Surround them with large white lilies and soft-focus pink roses. In the center, overlay bold sans-serif text: 'AI Made This Painting' in white, followed by 'Real' in yellow on the next line. Below the text, place a smaller rectangular inset image showing the original impressionist oil painting (two girls with lanterns) framed in gold, with a hand-drawn yellow arrow pointing from the painting up to the realistic scene.
A highly detailed photorealistic prompt for generating an action shot of a badminton player smashing a shuttlecock, created using GPT Image 2 (referred to as 'Gpt 2').
Ultra-realistic cinematic sports photograph of a strikingly handsome young male badminton athlete in his early 20s, captured at the peak of a powerful overhead smash. He has thick naturally wavy jet-black hair, strong eyebrows, deep dark-brown eyes, a defined sculpted jawline, subtle natural stubble, realistic skin texture, visible pores, and refined masculine facial features.
He is jumping explosively above the badminton court, body dynamically twisted, one arm fully extended overhead with a professional badminton racket aimed aggressively toward the camera. His expression is intensely focused and determined. A shuttlecock is extremely close to the lens in the foreground, dramatically enlarged with razor-sharp feather details, creating powerful depth and perspective.
Modern indoor badminton arena, polished court floor, subtle net visible in the background, dramatic overhead stadium lights, strong rim lighting, atmospheric haze, realistic shadows, tiny sweat droplets frozen in motion, cinematic motion energy, shallow depth of field, dynamic low-angle perspective, 85mm sports photography aesthetic, ultra-detailed skin and clothing, photorealistic textures, HDR, high contrast, frozen action, premium sports campaign photography.
Large bold โSMASHโ typography subtly integrated into the background, clean athletic editorial design, no logos, no watermark, no other people.
9:16 vertical composition, 8K, photorealistic, cinematic, professional sports advertising campaign, extremely sharp subject and shuttlecock, dramatic depth of field.
A hyper-realistic image of a colossal Japanese police mecha standing in a garage during a rainstorm, with Tokyo landmarks visible in the background.
A cinematic, photorealistic wide shot of a massive bipedal police robot standing inside a large industrial hangar on a rainy day. The robot is the central focus, towering over the scene with a complex mechanical design featuring white armored plating and exposed black hydraulic joints. It has a multi-lens camera array for a head instead of a face, and red warning lights are illuminated on its shoulders. The text "่ญฆ่ฆๅบ MPD" (Metropolitan Police Department) is printed in black on its chest plates and arms. Its feet are wide, treaded platforms resting on the wet concrete floor. To the left, a vertical banner hangs from the ceiling reading "่ญฆ่ฆๅบ METROPOLITAN POLICE DEPARTMENT" with a cherry blossom crest. Below it, a horizontal sign reads "ๅฎๅ
จใชๆฑไบฌใ ๆฌกใฎไธไปฃใธ A SAFER TOKYO FOR THE NEXT GENERATION". In the background, through the open hangar doors, heavy rain falls over a Tokyo cityscape featuring the red lattice structure of the Tokyo Tower and modern skyscrapers under a grey sky. Several police trucks marked "MPD" are parked outside with their headlights on. Two human officers wearing dark uniforms and white helmets stand in the foreground corners, providing scale.
A detailed prompt for generating images in a neo-naive/outsider art style depicting characters fighting clumsily. Explicitly states the generation model is GPT-image2.
[Character A] and [Character B], neo-naรฏve painting ร outsider art ร primitive figurative painting ร children's drawing style character translation.
The two characters are composed of a small number of irregular geometric color blocks, retaining only their strongest identity markers: primary color, head silhouette, hairstyle or ears, eyes, representative clothing color blocks, signature accessories.
The two are fighting intensely but comically, bodies pressed close and entangled. Randomly design actions such as face-grabbing, head-pushing, hugging, pulling, slapping, pinning down, or mutual pouncing based on the characters; hand contact is clear, limbs intersect, center of gravity is unbalanced, making the fighting relationship instantly readable.
Childish and inaccurate human anatomy: slender torsos, stiff straight limbs, inaccurate proportions, tilted heads, exaggerated hands and feet, incorrect perspective. Facial features compressed into a few rough color blocks, expressions angry, shocked, baring teeth, screaming, or aggrieved, possessing an absurd comedic feel.
Rough opaque paint flat coloring, dry brush marks, frayed edges, uneven filling, shaky hand-drawn outlines, local underpainting exposure; body and clothing represented directly by flat color blocks.
Warm gray-white or off-white paper background, large areas of blank space. The two characters are located in the center, entangled with each other forming a compact action mass, the picture focuses on expressing the relationship between the characters.
Like a fight moment quickly drawn from memory by an untrained person: primitive, clumsy, direct, absurd, cute.
Vertical format, extremely small "voxcat" signature in the bottom right corner.
A humorous 3-panel manga-style comic depicting a user's dilemma between the new 'Opus 5.5' AI model and their existing 'Wife GPT', framed as an affair.
Goal: Create a vertical 3-panel comic strip in an anime style, titled "Thoughts After Experiencing Opus 5.5".
Canvas: Vertical layout with three distinct panels stacked on top of each other.
Panel 1 (Top):
- Subject: A young man with messy black hair and starry eyes looks excitedly at a cheerful girl with long orange hair wearing a sunflower-themed dress.
- Text Bubble (Man): "After experiencing Opus 5.5... Wow... so charming....!!"
- Info Box (Right): A yellow decorative box labeled "Claude:" containing the text "Youthful and smart, making life colorful!".
- Background: Bright, sunny field of sunflowers.
Panel 2 (Middle):
- Subject: The same man is now hiding his face in his hands, sweating nervously. Beside him stands an elegant woman with long white hair, horns, and a cold expression.
- Text Bubble (Man): "Oh no, this feels like cheating... Lost the passion of newlyweds..."
- Info Box (Left): A purple decorative box labeled "Wife GPT:" containing the text "Still beautiful and elegant, but a bit cold.".
- Background: Darker, indoor setting with blue curtains.
Panel 3 (Bottom):
- Subject: A scene at a train station platform. The man is peeking around a pillar, blushing, next to the orange-haired girl (Claude). In the background, the white-haired woman (Wife GPT) stands watching them from a distance near a train.
- Signage: A blue sign hanging above reads "Transfer Station ->".
- Text Bubble (Left): "Strict rules at home, can only meet secretly at the transfer station! Keep it down..."
- Text Bubble (Right): "I know everything... watching quietly."
Visual Style: Clean digital illustration, vibrant colors for the first panel, muted tones for the second, realistic lighting for the third.
An action-packed illustration showing Chun-Li delivering a devastating kick to a large green monster while Ryu lies defeated in the foreground.
A high-resolution digital illustration in a vibrant, comic-book style depicting a chaotic street fight. The scene features Chun-Li from Street Fighter on the right side, wearing her iconic blue qipao with gold trim and white boots, executing a powerful high kick that connects directly with the torso of a massive green-skinned monster. The monster resembles Blanka but is significantly larger and more muscular, with wild red hair, sharp claws, and glowing eyes, roaring in pain as it absorbs the impact. In the foreground, lying defeated on the rubble-strewn ground, is Ryu from Street Fighter, wearing his torn white gi, appearing battered and unconscious. The background shows a gritty urban alleyway with brick buildings, fire escapes, and overflowing trash cans under a dramatic, fiery orange and purple sky. Debris and dust explode outward from the point of impact.
Truncated โ view the full README on GitHub.
(top 24 of 26)
1,152 followers ยท starred May 2026
4,596 followers ยท starred May 2026
7,371 followers ยท starred Apr 2026
18 followers ยท starred May 2026
๐ World's largest GPT Image 2 prompt library, updated daily โ 2000+ curated prompts with preview images, 16 languages. OpenAI's next-gen image model with pixel-perfect text rendering, cross-image consistency, and commercial-grade illustration. Free & open source.
See the code
๐ก ๐ฌ Take it further with Seedance 2 โ pair GPT Image 2 stills with Seedance for jaw-dropping AI videos, 2000+ prompts to explore ๐ awesome-seedance-2-prompts
๐จ A curated collection of creative prompts for OpenAI's GPT Image 2
โ ๏ธ Copyright Notice: All prompts are collected from the community for educational purposes. If you believe any content infringes on your rights, please open an issue and we will remove it promptly.
๐ Browse on YouMind GPT Image 2 Prompts Gallery
Why use our gallery?
| Feature | GitHub README | youmind.com Gallery |
|---|---|---|
| ๐จ Visual Layout | Linear list | Beautiful Masonry Grid |
| ๐ Search | Ctrl+F only | Full-text search with filters |
| ๐ค AI One-Click Generation | - | AI one-click generation |
| ๐ฑ Mobile | Basic | Fully responsive |
| ๐ท๏ธ Categories | - | Category browsing |
GPT Image 2 (codename "duct-tape") is OpenAI's next-generation image model. Community testing highlights a leap in these areas:
๐ Learn More: See community testing in our report summary
Some prompts support dynamic arguments using Raycast Snippets syntax. Look for the ๐ Raycast Friendly badge!
Example:
A quote card with "{argument name="quote" default="Stay hungry, stay foolish"}"
by {argument name="author" default="Steve Jobs"}
When used in Raycast, you can dynamically replace the arguments for quick iterations!
| Metric | Count |
|---|---|
| ๐ Total Prompts | 17837 |
| โญ Featured | 6 |
| ๐ Last Updated | Sunday, October 11, 2026 at 2:43:24 AM UTC |
โญ Hand-picked by our team for exceptional quality and creativity
Generates a high-tech exploded view diagram of a VR headset with detailed component callouts and promotional text.
{
"type": "exploded view product diagram poster",
"subject": "VR headset",
"style": "clean high-tech 3D render, studio lighting, glowing accents",
"background": "{argument name=\"background color\" default=\"soft purple and blue gradient\"}",
"header": {
"logo": "โ {argument name=\"product name\" default=\"Meta Quest 3\"}",
"subtitle": "{argument name=\"main catchphrase\" default=\"ใพใฃใใๆฐใใ็พๅฎใใใพใฃใใๆฐใใๆง้ ใใใ\"}"
},
"layout": {
"centerpiece": "vertically stacked exploded view of a VR headset showing 9 distinct layers of internal components: outer shell, camera sensors, motherboard with chip, pancake lenses, internal frame, battery packs, side straps, top strap, and facial interface cushion.",
"callout_labels": {
"count": 8,
"left_side": [
"Snapdragonยฎ XR2 Gen 2\nๅงๅ็ใชๅฆ็ๆง่ฝใงใชใขใซใฟใคใ ใชไฝ้จใใ",
"่ชฟๆดๅฏ่ฝใชIPDๆฉๆง\nๅน
ๅบใใฆใผใถใผใซๅฟซ้ฉใชใใฃใใๆใใ",
"็ฒพๅฏ่จญ่จใใใใใใในใใฉใใ\nๅฟซ้ฉใใจๅฎๅฎๆงใ่ฟฝๆฑใใใจใซใดใใใฏในใ"
],
"right_side": [
"ใใงใคในใใฌใผใ\nๆด็ทดใใใใใถใคใณใจๆ้ฉใช้้ใใฉใณในใ",
"ใใฉใใญใณใฐใซใกใฉ\n้ซ็ฒพๅบฆใชไฝ็ฝฎใใฉใใญใณใฐใจ็ฐๅข่ช่ญใๅฎ็พใ",
"ใใณใฑใผใญใฌใณใบ\n่ๅ่จญ่จใงๅบใ่ฆ้่งใจ้ฎฎๆใชๆ ๅใๆไพใ",
"้ซๆง่ฝใใใใชใผ\n้ทๆ้้งๅใๆฏใใๆ้ฉๅใใใ้ปๆบ่จญ่จใ",
"ๆใใใชใใงใคในใคใณใฟใผใใงใผใน\n้ทๆ้ใงใๅฟซ้ฉใช่ฃ
็ๆใๅฎ็พใ"
]
},
"footer": {
"left_text_block": {
"headline": "{argument name=\"bottom headline\" default=\"ไฝ้จใฏใๆง้ ใใ้ฒๅใใใ\"}",
"body": "ไธใคใฒใจใคใฎใใผใใซใๆฒกๅ
ฅไฝ้จใๆฏใใๆๅ
็ซฏใใฏใใญใธใผใจใใ ใใใฎ่จญ่จใMeta Quest 3ใฏใๆชๆฅใๆใใใใไฝ้จใๅ
้จใใ็ใฟๅบใใฆใใพใใ"
},
"right_logo": "โ Meta"
}
}
}
Generates a hand-drawn, watercolor-style tourist map featuring numbered local food specialties, landmarks, and a legend.
{
"type": "illustrated map infographic",
"style": "{argument name=\"art style\" default=\"watercolor and ink hand-drawn illustration on vintage parchment\"}",
"title_section": {
"text": "{argument name=\"city name\" default=\"ๆ้ฝ\"} {argument name=\"map title\" default=\"ๅ่ดงๆด่ตฐๅฐๅพ\"}",
"mascot": "cartoon red chili pepper wearing sunglasses and giving a thumbs up"
},
"border": "{argument name=\"border decoration\" default=\"vine of green leaves and red chili peppers\"}",
"layout": {
"background": "textured beige parchment paper with yellow roads, blue rivers, and green park areas",
"sections": [
{
"title": "landmarks",
"count": 6,
"illustrations": ["traditional pavilion", "traditional monastery", "modern skyscraper with climbing panda", "tall TV tower", "traditional gate", "industrial buildings"],
"labels": ["ไบบๆฐๅ
ฌๅญ", "ๆๆฎ้ข", "IFS", "339็ต่งๅก", "ๅฎฝ็ชๅททๅญ", "ไธ้่ฎฐๅฟ"]
},
{
"title": "food_spots",
"count": 12,
"illustrations": ["mapo tofu", "dumplings in chili oil", "skewers in pot", "sticky rice balls", "egg baking cake", "nine-grid hotpot", "sweet potato noodles", "cold skewers", "spicy mixed dish", "covered tea bowl", "ice jelly dessert", "spicy rabbit heads"],
"labels": ["1 ้้บปๅฉ่ฑ่
", "2 ้ๆฐด้ฅบ", "3 ๆฅ็่ทฏ", "4 ๅฎฝ็ชๅททๅญยทไธๅคง็ฎ", "5 ๅปบ่ฎพ่ทฏยทๅถๅฉๅฉ่็็ณ", "6 ็ๆ่ทฏยทๅฐ้พๅ็ซ้
", "7 ้ฆ้ฆๅททยท่ฅ่ ็ฒ", "8 ๆญฆไพฏ็ฅ ๅคง่กยท้ต้ต้ธก", "9 ไธ้่ฎฐๅฟยทๅๆค็ซ่พฃ", "10 ไบบๆฐๅ
ฌๅญยท้นค้ธฃ่ถ็คพ", "11 ้ฆ้ๅค่กยทๅฐ็ฒ", "12 ๅๆต่ๅฆๅ
ๅคด"]
},
{
"title": "ๅพไพ",
"position": "bottom-right",
"count": 5,
"items": ["red dot", "green house", "green tree", "blue line", "yellow double line"],
"labels": ["็พ้ฃๅฐ็น", "ๅฐๆ ๆฏ็น", "ๅ
ฌๅญ็ปฟๅฐ", "ๆฒณๆตๆนๆณ", "ไธป่ฆ้่ทฏ"]
}
],
"centerpiece": "giant panda sitting and eating bamboo",
"bottom_right_extras": ["vintage compass rose with N, S, E, W", "disclaimer text 'ๆธฉ้ฆจๆ็คบ๏ผๅ่พฃ้่ฐจๆ
๏ผ่ ่่ฆไฟๆค~' with a red chili pepper icon"]
}
}
A prompt that combines the simple, warm aesthetic of Irasutoya illustrations with the high-information density characteristic of Japanese government slides.
Create an explanatory slide ({argument name="format" default="ponchi-e diagram"}) for {argument name="theme" default="Momotaro"} that fuses the gentle atmosphere of "Irasutoya" with the overwhelming information density of "Kasumigaseki slides".
Generates a realistic social media live stream interface overlaying a portrait, featuring customizable chat messages, gift popups, and a product purchase card.
{
"type": "live stream UI mockup",
"subject": {
"description": "portrait of {argument name=\"host name\" default=\"Elon Musk\"}, smiling, wearing a black t-shirt with a white technical schematic graphic",
"background": "left side shows a screen with '{argument name=\"left background logo\" default=\"SPACEX\"}' text, right side shows a red '{argument name=\"right background logo\" default=\"Tesla T logo\"}' and a dark car"
},
"ui_overlay": {
"top_header": {
"host_info": "avatar, name '{argument name=\"host name\" default=\"Elon Musk\"}', subtext '55.6ไธๆฌๅบ็น่ต', red 'ๅ
ณๆณจ' button",
"rank_badge": "gold coin icon with 'ๅ
จ็ซ็ฌฌ1ๅ'",
"viewer_stats": "3 top viewer avatars with '12.3w', '8.6w', '5.7w', total '68.7ไธ', 'X' close button",
"right_links": "'ๆดๅค็ดๆญ >', '็คผ็ฉๅฑ้ฆ 0/24' with blue '็ปๅ
ธ' tag"
},
"mid_left_gifts": {
"count": 2,
"items": [
"avatar '็งๆ็ฑๅฅฝ่
', '้ๅฐๅฟๅฟ', heart icon x 1314",
"avatar 'ๆ่พฐๅคงๆตท', '้็ซ็ฎญ', rocket icon x 666"
]
},
"bottom_left_chat": {
"system_message": "level 37 badge 'ๅฎๅฎๆผซๆธธ่
ๅ ๅ
ฅไบ็ดๆญ้ด'",
"message_count": 7,
"messages": [
"ๅฐ็ซ็ฎญ: ้ฉฌๆฏๅ
๏ผๆชๆฅๅฏๆ๏ผ๐",
"future: ็นๆฏๆModel 2ไปไนๆถๅๅบ๏ผ",
"ๆ็ฉบๆขฆๆณๅฎถ: SpaceXไปๅนด่ฝไธ็ซๆๅ๏ผ",
"AIๆข็ดข่
: Neuralink่ฟๅฑๅฆไฝ๏ผ",
"ๅธ
ๆฐ็็ฝๅ: ้ฉฌๆปๅฅฝ๏ผ",
"Mars: ็ฌฌไธๆฌกๆฅไฝ ็็ดๆญ๏ผ่ถ
ๆฟๅจ๏ผ",
"็จๆท123: ่ฎฒ่ฎฒAIๅง๏ผไผๅไปฃไบบ็ฑปๅ๏ผ"
]
},
"bottom_right_product_card": {
"hot_tag": "orange '็ญๅ x 1888'",
"image": "Tesla Cybertruck",
"title": "{argument name=\"product name\" default=\"็นๆฏๆCybertruck ็ตๅจ็ฎๅก\"}",
"price": "{argument name=\"product price\" default=\"ยฅ 1,618,000\"}",
"button": "red 'ๆข' button",
"floating_animation": "translucent hearts floating up the right edge"
},
"bottom_bar": {
"input_field": "'่ฏด็นไปไน...'",
"icons": ["smiley face", "three dots", "shopping cart", "gift box", "share"]
}
}
}
Generates a dynamic, high-impact anime illustration of two female characters fighting in a traditional dojo with elemental energy effects.
An anime-style illustration of a {argument name="action type" default="high-impact martial arts battle"} between two young female fighters in a {argument name="setting" default="traditional wooden martial arts dojo"}. In the foreground, a girl with black hair in a high bun wears a {argument name="character 1 color theme" default="red and white"} Chinese-style martial arts outfit with baggy pants. She is in a dynamic, low, forward-thrusting stance, surrounded by swirling red energy and water splashes. In the background to the right, a girl with light purple hair in twin buns wears a {argument name="character 2 color theme" default="green and purple"} Chinese dress with gold embroidery and black tights. She is leaping through the air in a flying kick pose, surrounded by swirling blue energy. The wooden floorboards are splintering from the intense impact, with debris and dust flying through the air. Above them hangs a weathered wooden sign with the text "{argument name="sign text" default="ๆญฆ่กไผ"}". The scene features dramatic lighting, a low-angle dynamic perspective, and intense action effects.
Transforms a flat evolutionary timeline into a realistic 3D stone staircase infographic with detailed organism renders and structured side panels.
{
"type": "evolutionary timeline infographic",
"instruction": "Using REFERENCE_0 as a structural base, transform the flat vector design into a highly realistic 3D infographic. Replace the smooth ramps with distinct stone steps and upgrade all organisms to photorealistic 3D models.",
"style": {
"background": "{argument name=\"background style\" default=\"vintage textured parchment paper\"}",
"staircase": "{argument name=\"staircase material\" default=\"realistic textured stone blocks\"}",
"subjects": "{argument name=\"organism style\" default=\"highly detailed photorealistic 3D renders\"}"
},
"layout": {
"main_title": "{argument name=\"main title\" default=\"ไบบ็ฑปๆผๅ\"}",
"sections": [
{
"position": "left sidebar",
"count": 8,
"labels": ["L0: ๅ็ป่็ๅฝ", "L1: ๅค็ป่็็ฉ", "L2: ๅจ็ฉ็", "L3: ่็ดขๅจ็ฉ", "L4: ไธ้้ฉๅฝ", "L5: ๅบไนณ็บฒ", "L6: ไบบ็งๆผๅ", "L7: ๆบไบบ็บชๅ
"]
},
{
"position": "top right",
"title": "่ทๅพ็ๅ่ฝ / ๅคฑๅป็ๅ่ฝ",
"description": "Legend with plus and minus icons"
},
{
"position": "bottom center",
"title": "ๆผๅๅ
ณ้ฎ้็จ็ข",
"count": 6,
"description": "Timeline with a silhouette graphic of 6 figures showing ape-to-human evolution"
}
],
"centerpiece": {
"description": "Winding stone staircase with 25 numbered steps featuring specific organisms.",
"count": 25,
"notable_elements": [
"Step 07: Jellyfish",
"Step 09: Ammonite",
"Step 10: Trilobite",
"Step 24: Walking human",
"Step 25: {argument name=\"future evolution concept\" default=\"glowing cosmic silhouette with a question mark\"}"
]
}
}
}
๐ Sorted by publish date (newest first)
A prompt for generating a low-resolution, early 2000s Nokia phone-style selfie featuring a woman in ragdoll cat cosplay, including specific noise, lighting, and background details.
Based on the reference image of an adult female cosplayer, maintain the protagonist's face, ragdoll cat themed costume, black long hair, brown-white plush outfit and cat paw accessories.
Character taking a close-up selfie, leaning slightly forward, tilting head, slight pout, with an expression of confusion, disdain, yet cute, looking directly at the camera.
Ragdoll cat fur color and styling details as per source material.
Next to the person is a ragdoll cat, in the foreground is a rattan basket containing a fluffy yellow chick and a bunch of deep purple grapes.
The person, cat, chick, and grapes naturally squeeze into the same frame, forming an absurd yet everyday private photo.
Shot with an early 2000s old Nokia phone, low-pixel color digital photography, low resolution, slight defocus, rough digital noise, JPEG compression artifacts, slight skin tone shift, uneven white balance, limited dynamic range, soft edges, obvious dirty noise in shadows.
Small ordinary bedroom, old bed, wooden furniture, old CRT TV naturally entering the background. Dim indoor ambient light combined with direct phone flash, face slightly overexposed, background rapidly decaying into darkness. Close-range wide-angle selfie perspective, arm extending towards lens creating obvious near-large far-small effect, casual composition, slightly tilted, like a private photo taken by a friend with an old phone.
Overall real, cheap, rough, snap-shot quality, no modern high-definition photographic texture. Only keep a very small fanfan signature.
A reverse-engineered prompt for a striking portrait of a woman with yellow braided horns and neck tattoos.
A vertical, low-angle medium close-up portrait of a young woman with light brown skin and prominent freckles across her nose and cheeks. She has an intense, direct gaze with blue eyes and full lips. Her hair is styled in thin yellow braids that hang down the sides of her face, adorned with small silver beads and rings. Two thick, sculpted horn-like structures made of fuzzy yellow yarn or rope protrude from the top of her head, curving slightly upwards. She wears a gold septum piercing and multiple dangling earrings. A black ink tattoo featuring tribal-style swirls covers the front of her neck. She is dressed in a textured knit sweater with horizontal stripes of mustard yellow, white, and black, accessorized with a chunky silver chain necklace. The background shows a clear blue sky on the left and a blurred grey concrete building structure on the right. The lighting is bright natural sunlight, casting distinct shadows on her face.
Prompt for creating modern geometric cartoon illustrations of two characters interacting with UPA-style shapes and limited animation movements.
{argument name="Character A" default="Xiao Ming"} and {argument name="Character B" default="Xiao Hong"}, modern geometric cartoon illustration ร UPA-style shape language ร limited animation movement design ร clear digital flat coloring.
Highly simplified character designs constructed from squares, circles, trapezoids, and arcs for heads and bodies. Retain core hairstyles, main colors, iconic accessories, and clothing color blocks. Clear smooth thick black outlines, large uniform solid color fills, minimal simple hard-edge shadows, exaggerated hands, shoes, and limb proportions.
Two characters engage in clear, humorous, dynamic interactions. Large stretches, jumps, chases, dodges, kicks, lunges create clear silhouettes. Movement directions, gazes, and expressions echo each other, presenting instantly readable comedic relationships.
Vertical composition, characters shrunk and concentrated in lower-middle section, large whitespace above. Single high-purity solid color background. Add a simple comic symbol, prop, or graphic element between characters to establish narrative connection.
Overall use few high-contrast colors: black, white, character main colors, and one or two accent colors. Sharp block edges, uniform fill, complete outlines, flat surface. Clean clear modern digital illustration quality, suitable for animation promos, stickers, and phone wallpapers.
Vertical format, tiny voxcat signature at bottom right.
A detailed prompt for generating a realistic iPhone-style photo of a woman in a cafe using GPT Image 2, focusing on faithful character reproduction from a reference image and specific lighting/composition details.
Shot on an iPhone. The womanโs appearance should be 100% faithful to the uploaded reference photo, sitting at a cafรฉ table outdoors under an autumn tree, centered in the frame. Her body is facing forward, her head slightly tilted, with one cheek gently resting on one hand while the other hand is relaxed on the table, holding the stem of a wide red-wine glass with a very thin, long, delicate stem and thin glass walls. Only a small amount of wine remains at the bottom.
She is wearing a voluminous black trench coat with structured shoulder pads and oversized long sleeves covering her fingers, with a black turtleneck underneath. Hair exactly matching the uploaded photo.
White tablecloth, elegant white plates, a classic European-style building faรงade in the background, with an autumn tree filling the upper part of the frame.
True-to-life iPhone realism, subtle natural film grain, authentic skin texture and lighting. Do not blur the background; maintain realistic environmental detail throughout the scene.
Short square French-tip manicure.
9:16 vertical format.
She is wearing narrow black rimless cat-eye sunglasses.
Overcast daytime with no direct sunlight. Slightly slower shutter speed for a subtle natural motion/film feel while keeping the subject realistic and recognizable.
A prompt for creating minimalist cartoon doodle illustrations featuring tiny characters with distinct paths and large negative space. Suitable for wallpapers or character series designs.
{argument name="character list" default="Character A / Character B / Character C / Character D"}, Minimalist cartoon doodle illustration x Huge negative space x Micro-character action chain.
Pure white or very light colored background, keeping over 65% of the image area blank. Characters are extremely small in proportion, retaining only hairstyle outlines, main colors, iconic accessories, and clothing color blocks, transformed into simplified, easily recognizable cartoon images.
Each image randomly selects one composition: central vertical queue, S-shaped serpentine, diagonal fall, single-side suspension, U-shaped path, micro-ring, spiral trajectory, intermittent floating nodes, top horizontal event followed by vertical fall, bottom character tower. The overall visual trajectory is slender and clear, with characters concentrated in local areas and large negative space maintained around them.
Set a micro-target object related to the character's worldview along the trajectory, such as fruit, food, badges, weapons, gems, or dolls. The target is located at the start, end, or center of rings/spirals, with characters' gazes and actions naturally pointing towards it.
Each character adopts different exaggerated actions: running, jumping, reaching out, holding up, surprised, falling, opening mouth, turning back, being pressed, or pulling each other. Through limb contact, clothing pulling, gaze direction, and spacing changes, create continuous, readable action relationships among figures. Specific actions and character order are random, maintaining clear visual rhythm.
Relaxed hand-drawn black outline lines, slightly shaky, with flying lines and irregularity, like animation drafts or children's doodles. A few high-purity flat color blocks, composed of black lines, white background, and red, yellow, blue, green for a simple palette, with character main colors serving as identity anchors.
Overall relaxed, absurd, cute, like animation stickers, character journal illustrations, or minimalist phone wallpapers. Vertical format, extremely small voxcat in the bottom right.
A detailed prompt for generating a cinematic fantasy portrait of a woman on a moonlit terrace, optimized for GPT Image 2.
A highly detailed cinematic fantasy portrait of a beautiful young woman standing on an elegant flower-covered terrace at twilight. She has long, naturally wavy dark brown hair, soft glowing skin, expressive hazel-brown eyes, delicate facial features, subtle rosy cheeks, and glossy natural lips. She is wearing a sophisticated flowing black dress with intricate silver floral embroidery, sheer sleeves, elegant dangling earrings, and a delicate hair ornament. She stands in a graceful three-quarter pose, body turned slightly away while looking back over her shoulder directly at the camera, one hand gently holding her dress and the other relaxed by her side.
Behind her is a breathtaking moonlit lake with a distant magical city, glowing domes and towers, mountains, and reflections across the water. Warm vintage lanterns surround the terrace, with white flowers and green vines framing the scene. A crescent moon and soft purple-blue clouds fill the sky. Romantic warm-and-cool cinematic lighting, realistic skin texture, detailed hair strands, natural proportions, shallow depth of field, soft bokeh, dreamy atmosphere, photorealistic fantasy realism, professional photography, 85mm lens, eye-level camera, full-body composition, vertical 9:16.
A retro-styled image of a smiling woman holding up her catch while standing in a mountain river.
A vintage-style photograph of a young woman standing waist-deep in a clear, rocky river. She is wearing a beige bucket hat, a white short-sleeved blouse with a small floral pattern, and dark waders. Her hair is styled in two braids. She holds a bamboo fishing rod in her right hand and raises her left arm to display two freshly caught fish hanging from the line. A woven basket hangs at her hip, and a red mesh landing net is visible in the foreground. The background features lush green mountains under a blue sky.
A cinematic portrait of a Japanese schoolgirl drawing a rabbit on a chalkboard in an empty classroom, featuring vintage film grain and soft lighting.
A vertical, medium-shot photograph with a nostalgic film aesthetic captures a young Asian female student in an empty classroom. She has short, dark bobbed hair with bangs and wears a traditional navy blue sailor-style school uniform (seifuku) with white stripes on the collar and cuffs. Her expression is calm and slightly melancholic as she looks directly at the camera. She stands beside a green chalkboard, holding a piece of pink chalk in her right hand, having just drawn a cute cartoon rabbit face with a heart next to it. In the foreground, resting on a worn wooden desk, is a large orange triangular ruler. The background features rows of empty wooden desks and chairs, tall windows letting in soft natural light, and blurred calligraphy posters on the far wall. The image has visible film grain, dust specks, and scratches, enhancing the retro atmosphere.
A retro-styled photograph capturing a smiling young woman in a hoodie and plaid skirt within a rustic Japanese setting.
A vintage-style portrait of a young woman standing in a traditional Japanese alleyway. She has short, curly dark brown hair and is wearing a cream-colored hooded sweatshirt with drawstrings and a plaid skirt. Her hands are raised to her head as she smiles gently at the camera. A brown leather shoulder bag hangs from her left side. The background features weathered wooden houses with tiled roofs, a utility pole, and an old bicycle leaning against a fence. The image has a nostalgic film grain texture with light leaks on the edges.
A prompt for generating a hyper-realistic fashion portrait of a character with purple hair sitting against a terracotta wall using GPT Image 2.
Create a hyper-realistic medium full-body fashion portrait of the same young adult female character from the reference image, preserving her signature vivid violet-purple chin-length straight bob with soft bangs, fair porcelain skin, natural freckles across her nose and cheeks, hazel/light-brown eyes, delicate facial features, glossy lips, and slim physique.
She is sitting in a relaxed crouching pose against a warm terracotta textured wall, with her head resting gently on one hand while looking calmly and directly at the camera. She wears a terracotta rust-orange cropped hoodie, beige high-waisted cargo jogger pants, and brown leather lace-up combat boots. Add a patterned satin bow headband and a small orange butterfly hair clip.
Use soft natural daylight with warm earthy autumn tones. Keep the composition intimate and editorial with realistic skin texture, detailed purple hair, natural fabric and leather textures, subtle shadows, cinematic depth of field, photorealistic quality, ultra-detailed 8K, premium fashion photography.
A community-shared prompt for generating extreme close-up anime portraits using GPT Image 2, requiring reference sheets.
Create an extreme close-up portrait of the character in the attached character reference sheet. Treat that sheet as the absolute authority for the character's identity and design: preserve their face, facial proportions, skin tone, hair style/color, eyes, ears or other character features, and any visible clothing/accessories. Do not redesign the character.
The second attached portrait is ONLY a rendering-quality reference. Do not copy that character's identity, face, hair, colors, clothing, accessories, expression, pose, or composition. Use it only as the target for detail density and finish: highly defined facial features, dimensional anime shading, intricate eyes and eyelashes, individually rendered hair strands, subtle skin highlights and warmth, sophisticated lighting, depth, material definition, and extremely polished cinematic anime rendering.
Frame the subject very tightly from approximately the upper chest/clavicle to the tips of their hair/ears, with the face dominating the image. Use an eye-level camera and direct eye contact. Give them a small natural smile with subtle blush. Preserve recognizable anime facial proportions while adding significantly more dimensional definition and fine detail; do not make the face photorealistic.
Use a simple dark atmospheric background and cinematic lighting that complements the character's existing palette. Keep the eyes, face, and nearest hair strands exceptionally sharp, with gentle depth falloff elsewhere.
Do not show the waist, hips, legs, or full body. Do not create a detailed environment. Do not copy the second portrait's scene or character.
Character sheet = WHO the character is. Second portrait = ONLY the LEVEL OF RENDERING QUALITY.
Generate the portrait now.
A detailed prompt for GPT Image 2 to create a photorealistic selfie of a woman wearing cat ears and tail in a white cat-themed room, including specific pose, lighting, and style instructions.
Subject:
Selfie in cat ear knit outfit.
Main Subject:
A woman taking a selfie while bending forward in a white cat room, wearing cat ears and a tail, positioned in the center of the frame.
Character & Expression:
Small oval face, large dark brown eyes, thin eyebrows, well-defined nose, glossy pale pink lips. Expression is a soft smile, facing forward, looking at the camera through the smartphone. Long dark brown wavy hair let down, with thin bangs and a white-brown cat ear headband on top of the head.
Clothing & Pose:
Beige and pale pink open-knit long-sleeve knit dress, deep neckline, front tie, pom-pom decorations, short length, white cat-shaped slippers, long white-brown cat tail from waist. Knees bent, bending deeply forward, holding a smartphone with pink case in front of face with right hand, left hand resting on left knee.
Background & Light:
Foreground has long-pile white rug and cat teaser toy. Background has white shelves, peach blossoms, framed cat pictures, cat tower on the right, white-grey cat on floor. Soft warm indoor light from above and back-right illuminates face, knitwear, and cats.
Composition & Camera:
3:4 vertical composition, full-body portrait captured by front camera slightly lower than waist, from cat ears to white slippers. Person placed large in center, occupying most of frame height. Smartphone and tail included in frame, focus on face, smartphone, and cat ears, background lightly blurred.
Texture & Style:
Photorealistic live-action photo. High-definition natural skin, hair, clothing materials, surrounding props, maintaining soft indoor colors of white, beige, and pale pink.
Negative:
Change of cat ears/tail and forward bend; omit background cats.
A prompt for generating a photorealistic portrait of a young South Asian woman wearing traditional attire in a garden setting during golden hour.
Photorealistic elegant portrait of a young South Asian woman wearing a dusty rose pink hijab, softly wrapped around her head and shoulders, with delicate gold traditional jhumka earrings. She is dressed in a luxurious blush-pink and ivory embroidered Pakistani shalwar kameez with intricate floral threadwork, subtle sequins, and detailed borders. She is seated gracefully beside an ornate marble railing, resting one hand gently under her chin, looking slightly upward with a soft, serene smile. Warm golden-hour sunlight, beautiful garden courtyard in the background, pink flowers and lush greenery, creamy architectural details, dreamy bokeh, shallow depth of field, natural skin texture, realistic facial features, soft cinematic lighting, high-end fashion photography, elegant Pakistani aesthetic, ultra-detailed, 85mm portrait lens, vertical 4:5 composition, no text, no watermark, no artificial plastic skin.
A detailed prompt for generating a photorealistic portrait of a woman in a black corset under red neon lights using GPT Image 2.
Subject:
Black corset with red neon.
Main Subject:
A woman in a glossy black corset is the protagonist in a dark lounge with red neon lights, centered in the frame.
Character & Expression:
Small oval face, large dark brown eyes, thin eyebrows, well-defined nose, glossy pale peach lips. Expression: Face tilted slightly upward, gaze meeting the camera, lips slightly parted in an intense expression. Dark brown straight hair falling below shoulders, with wet thin bangs and strands along cheeks.
Outfit & Pose:
Corset top with black enamel gloss, strapless chest, central zipper, side lacing; black waist straps and leather choker. Upper body arched back in front of a black sofa, arms lowered to sides, right shoulder pulled slightly back.
Background & Lighting:
From left to right background: black sofa and small table with candles on the left, red lightning-shaped neon on the right, black vertically grooved wall. Hard red neon from the right and soft white main light from the front illuminate the face and glossy costume.
Composition & Camera:
4:5 vertical composition, frontal camera slightly below chest level capturing a half-body portrait from head to hips. Character placed very large in center, occupying most of frame height. Arms and hips cropped at frame edges; focus on eyes and black glossy corset, background lightly blurred.
Texture & Style:
Photorealistic live-action photo. Natural skin and hair, high-definition costume materials and surrounding props, maintaining strong night colors of black, red, and skin tones.
Negative:
Omit red neon; change black glossy corset.
Generates a vintage-style black and white portrait of a young woman with an intense gaze.
A black and white, high-contrast portrait of a young woman with dark hair pulled back from her face. She is looking directly at the camera with an intense, serious expression. The image has a grainy texture and appears to be a vintage photograph or charcoal drawing.
A detailed photorealistic prompt for GPT Image 2 featuring a woman taking a mirror selfie in a white tulle dress, with specific pose and lighting instructions.
Subject:
White tulle in front of mirror.
Main Subject:
The protagonist is a woman sitting and taking a selfie in front of a floor mirror wearing a white tulle dress, positioned centrally.
Character & Expression:
Small oval face, large dark brown eyes, thin eyebrows, neat nose, glossy pale peach lips. Expression is calm, facing lower left with gaze falling onto smartphone screen. Hair near black tied in low bun, leaving thin bangs and stray hairs along cheeks.
Clothing & Pose:
Long dress with white strapless bodice and multiple layers of sheer tulle, thin silver gem anklets on both ankles. Sitting on white long-pile rug, knees raised high toward chest, holding black smartphone vertically in front of face with right hand.
Background & Light:
From left to right background: black leather chair inside mirror frame, warm lamp and flowers upper left, dark curtains around. Soft warm light from upper left illuminates face, white cloth, and legs.
Composition & Camera:
2:3 vertical portrait, full-body shot from top of head to reflected feet tips via floor mirror frontal camera. Place person very large centrally, occupying most of screen height. Naturally crop feet tips and mirror frame at screen edges, focus on face, phone, and white tulle, lightly blur background.
Texture & Style:
Photorealistic real photo. High definition of natural skin, hair, clothing material, and surrounding props, maintaining indoor colors of white, black, and gold.
Negative:
Change mirror shot and knee position; omit white tulle
A detailed prompt for GPT Image 2 to generate a photorealistic selfie of a woman with three white-grey cats in a bright morning room, specifying composition, lighting, and negative constraints.
Subject:
Morning selfie with three cats.
Main Subject:
A woman taking a selfie in the center of the frame, leaning her face close to three white-grey cats.
Character & Expression:
Small oval face, large dark brown eyes, thin eyebrows, well-defined nose, glossy pale pink lips. Expression is joyful, facing forward, looking at the camera, mouth wide open showing teeth. Black hair tied in a high bun, with wet thin bangs and stray hairs remaining on forehead and cheeks.
Clothing & Pose:
Natural beige thin-strap ribbed camisole top with chest lace and small ribbon. Left arm extended forward to take the photo, holding one cat in front of chest, with one cat above head and one behind left shoulder.
Background & Light:
Bright room with wooden desk and stacked books on the left, white door, white curtains and green leaves on the right. Soft white daylight from window on the right illuminates faces and cat fur.
Composition & Camera:
9:16 vertical composition, close-up front-facing selfie camera from extended arm capturing three cats and portrait from head to below chest. Person placed very large in center, occupying most of frame height. Foreground cat and left arm cropped by frame edge, focus on woman's and three blue-eyed cats' faces, background lightly blurred.
Texture & Style:
Photorealistic live-action photo. High-definition natural skin, hair, clothing materials, surrounding props, maintaining bright indoor colors of white, grey, beige, and wood tones.
Negative:
Change of three cats' arrangement; omit open mouth and selfie.
A prompt for generating a full-body portrait of a ballerina practicing in a studio with morning light, performing a high leg lift, with detailed costume and pose instructions.
Subject:
High leg lift in morning light.
Main Subject:
Woman raising one leg vertically in morning ballet practice hall is the protagonist, centered.
Person & Expression:
Small oval face, large dark brown eyes, thin eyebrows, neat nose, glossy pale peach lips. Expression is focused, face turned down-right, gaze dropped to chair. Dark brown hair in low bun, leaving thin bangs and loose strands along cheeks.
Clothing & Pose:
Leotard in dusty purple with thin straps, sheer ecru long-sleeve front-tie top, short pale-peach frill skirt, pink pointe shoes. Standing on right foot in pointe, left leg raised vertically to ear height held by left hand on calf, right hand on wooden chair back.
Background & Light:
Left and right background have white decorative walls and tall arched windows, background has wooden bar, foreground right has wooden chair, glossy wooden floor. Soft direct morning light from right window casts long window shadows on body and floor.
Composition & Camera:
3:4 vertical composition, horizontal camera slightly lower than waist capturing full body from pointe toe to raised left toe. Person placed largely vertical in center occupying most screen height. Leaving margins for chair and windows on sides, focus on profile and raised leg, background lightly blurred.
Texture & Style:
Photorealistic live-action photo. High-definition natural skin, hair, clothing materials, and props; maintaining morning colors of pale-peach, ecru, and wood.
Negative:
Change vertical leg lift; omit chair and pointe
Generates a striking overhead shot of a woman crouching on a red floor reaching towards the camera, with strong contrast and streetwear aesthetics.
Subject:
Palm on red floor.
Main Subject:
The main character is a woman crouching on a red floor, extending her palm largely towards the lens, positioned in the center of the screen.
Person & Expression:
Small oval face, large dark brown eyes, thin eyebrows, well-defined nose, glossy pale peach lips. The expression is intense, face turned upwards, gaze aligned with camera, lips slightly parted. Wet short black bob hair down, leaving thin bangs and strands along cheeks.
Clothing & Pose:
Dark grey thin-strapped ribbed bra top, white sports shorts, black belt, white sneakers, black leather choker and chain necklace, thick black bracelet. Crouching low on red floor, left hand placed on floor behind, right arm extended towards camera with five fingers spread wide.
Background & Light:
Left to right background: vivid red floor filling entire screen, pair of black-red sneakers at top-right, shadow of person at bottom-left. Hard direct sunlight from above creates strong shadows on hands, face, and shoulders.
Composition & Camera:
3:4 vertical composition, extreme wide-angle overhead bird's-eye view camera capturing full body from extended hand to both shoes. Person placed very large in the center, occupying most of the screen height. Palm made huge in foreground, arms and shoes cropped at screen edges, focus on face and foreground palm, background lightly blurred.
Texture & Style:
Photorealistic live-action photo. High definition skin, hair, clothing materials, and surrounding props; maintain strong contrast of red, black, white, and skin tone.
Negative:
Change of giant foreground hand and overhead view; omission of red floor.
A prompt for generating a photorealistic close-up portrait of a woman in a black satin dress in a dim lounge setting, focusing on lighting and texture details.
Subject:
Black satin candlelight seat.
Main Subject:
Close-up portrait of a woman wearing a black satin dress in a dark lounge seat is the protagonist, centered.
Person & Expression:
Small oval face, large dark brown eyes, thin eyebrows, neat nose, glossy pale peach lips. Expression is calm, face tilted slightly right from front, gaze meeting camera with lips barely parted. Reddish dark brown hair styled in low braided bun, leaving thin bangs and loose strands along cheeks.
Clothing & Pose:
Dress with glossy black satin, thin straps, deep V-neck, twisted waist drapes; large teardrop silver earrings. Sitting diagonally on black fabric sofa, left shoulder forward, both arms lowered beside body.
Background & Light:
Left background has black vase and branches, right has slim glass on marble table, background has vertical warm lights. Soft warm main light from right creates sheen on face, shoulders, and black satin.
Composition & Camera:
3:4 vertical composition, close diagonal frontal camera at chest height capturing bust-up from top of head to above waist. Person placed very large in center occupying most screen height. Left shoulder, right arm, dress hem cropped at edges, focus on eyes and black satin chest, background lightly blurred.
Texture & Style:
Photorealistic live-action photo. High-definition natural skin, hair, clothing materials, and props; maintaining night colors of black, gold, and skin tone.
Negative:
Change braided hair and face direction; omit black satin dress
A prompt for generating images combining old Nokia phone photography aesthetics with handwritten diary doodles and scrapbook elements, featuring a specific character in a daily scene.
{argument name="character" default="Anime Character"}, clearly adult live-action adaptation, preserve facial structure, hairstyle, hair color, eyes, main character color, iconic clothing silhouette and identity accessories.
2000s old Nokia phone photography ร private handwritten diary ร analog scrapbook ร experimental fashion photography.
Character placed in a real daily space, performing an action with a sense of life or slightly unconventional meaning. Action, expression, camera position, shot size, clothing details and space are autonomously designed by the model based on character identity.
Close-range phone direct flash snapshot, slight wide-angle distortion, low pixels, JPEG compression, partial defocus, direct flash highlights and rough digital colors. Character retains real facial structure and natural skin texture, presenting the accidental moment of the action occurring.
Colorful handwritten doodles, simple symbols, date codes and private notes directly overlaid on the photo surface. Some lines extend along the character's body contour, some marks emphasize gaze, gestures and action direction; a few photo fragments and paper edges form scrapbook layers. Handwritten content naturally derives from character identity and current situation.
Photographic subject is clear, manual markings and real space interpenetrate. Colors are autonomously organized based on character main color and scene lighting, overall presenting an experimental vibe of fused colorful private imagery and handwritten records.
3:4 portrait, very small vertical lowercase signature "voxcat" on the right edge.
A cute anime-style illustration of three chibi girls in animal costumes cooking pancakes together in a colorful kitchen.
Using the provided reference image, transform the scene into a cozy kitchen setting where three chibi girls are making pancakes. Keep the character designs (the yellow chick costume and blue shark hoodie) consistent with the reference style but add a third character in a white sheep costume. Change the background from a candy shop to a warm, pastel-colored kitchen with shelves of dishes and hanging utensils.
Action details: The girl in the yellow chick suit is whisking batter in a pink bowl. The girl in the blue shark suit is pouring batter onto a pink electric griddle using a ladle. The new girl in the white sheep suit is holding a bowl of flour/mix. All three characters must have a small smudge of pancake mix on their noses.
Props & Text: Include a bag labeled "Fluffy Pancake Mix", a jar labeled "HONEY", a bottle labeled "MILK", and a jar labeled "SUGAR". Add a stack of finished pancakes topped with strawberries and cream in the foreground. In the top right corner, include a chalkboard sign that reads "Purin-chan & Same-chan & Koharu-chan Pancake Party".
A photorealistic overhead view of a coffee shop's seasonal fall menu card resting on a sunlit wooden table next to a latte.
A high-angle, photorealistic shot of a rustic wooden table bathed in warm, dappled sunlight. On the left side of the frame lies a vertical menu card printed on cream-colored paper with a thin dark green double-line border. The text on the card is arranged as follows: at the top, 'HARBOR STREET COFFEE' in small uppercase serif letters; below that, 'Fall Menu' in large, elegant dark green serif font; followed by a decorative horizontal line with a leaf motif in the center. The menu items are listed in dark green serif text: 'Maple Oat Latte $5.50', 'Pumpkin Cold Brew $5.00', and 'Cardamom Bun $4.25'. At the bottom of the card is another leaf motif and the text 'Open daily 7am - 3pm'. To the right of the menu sits a ceramic mug filled with a latte featuring intricate white rosetta latte art. In the upper left corner, the leaves of a potted plant are partially visible, casting soft shadows across the scene.
This prompt generates an image capturing a nostalgic scene of a young woman posing inside a classic Japanese department store, perfect for creating retro-themed visuals.
A vintage-style photograph of a young woman standing in a Japanese department store. She has short, dark bobbed hair with bangs and is looking directly at the camera with a gentle expression. She wears a cream-colored long-sleeved blouse with a Peter Pan collar, tucked into a brown plaid pleated skirt that falls just above her knees. A small brown leather satchel hangs from her shoulder, and she holds a book or pamphlet in her hands. Her outfit is completed with white ankle socks and dark brown loafers. The background shows glass display cases filled with perfumes and cosmetics on the left, with a sign reading 'ๅ็ฒงๅ' (cosmetics). To the right, there are clothing racks and another sign reading 'ๅฉฆไบบๆ' (women's clothing). The floor is polished tile reflecting the warm lighting overhead. The overall atmosphere evokes nostalgia, reminiscent of late 20th-century Japan.
A prompt template for creating a nostalgic editorial scrapbook image that combines a realistic photograph with hand-drawn illustrations using GPT Image 2.
Create a nostalgic editorial scrapbook-style image combining one main photorealistic lifestyle photograph with a hand-drawn illustrated section underneath.
The top 50โ55% should be a cinematic, highly realistic photograph of {argument name="subject scene" default="[SUBJECT / SCENE]"}, captured like an authentic film photograph. Natural candid composition, warm nostalgic atmosphere, soft diffused light, subtle film grain, realistic textures, slightly muted vintage colors, autumnal/warm earthy tones, shallow depth of field where appropriate, beautifully composed but not overly polished.
The bottom 45โ50% should look like a vintage handmade scrapbook / travel journal page, printed on warm cream textured paper. Recreate small elements from the photograph as loose colored-pencil and watercolor doodle illustrations arranged in a clean 3ร3 or balanced grid. Include simple hand-drawn objects related to the scene such as {argument name="object 1" default="[OBJECT 1]"}, {argument name="object 2" default="[OBJECT 2]"}. Use imperfect sketch lines, subtle pencil strokes, watercolor bleed, slightly uneven coloring and authentic handmade imperfections.
Add a short handwritten title at the top of the illustrated section: โ{argument name="title" default="[TITLE]"}โ, in casual imperfect black/gray handwritten lettering. Add tiny decorative elements such as hearts, dots, clouds, leaves, stars, waves or small doodles around the illustrations.
At the very bottom, add a small handwritten caption: โ{argument name="short caption" default="[SHORT CAPTION]"}โ.
Overall aesthetic: cozy Pinterest editorial, nostalgic travel diary, vintage film photography + childrenโs sketchbook illustration, warm analog memories, premium lifestyle magazine composition, tactile paper texture, understated and elegant, emotionally warm, authentic rather than overly digital.
Composition: vertical 4:5, clean separation between photograph and illustration, balanced negative space, consistent visual storytelling between the photo and drawings.
Important: preserve realistic photography in the top section; do not turn the photograph into an illustration. The lower section should clearly look hand-drawn. Avoid excessive text, distorted lettering, photorealistic doodles, CGI appearance, oversaturation, clutter, or overly perfect vector graphics.
A surreal poster depicting Guangzhou's morning scene where giant rice noodle rolls form a landscape tended by tiny workers, set against a city skyline.
A creative vertical poster titled "GOOD MORNING GUANGZHOU" (ๅนฟๅทๆฉๅฎ) in the top left corner. The date "2026-10-09" and weather information are below the title. A quote reads: "็ญๆฐ่
พ่
พ๏ผๅฐฑๆฏ็ๆดปๆๅฅฝ็ๅ็ญ" (Steaming hot is life's best answer). Another poetic line on the left says: "ๅนณๅก้ฃๆไน่ฝ้ฟๅบๅๅธ็ๆธฉๆ" (Ordinary ingredients can also grow into the city's tenderness). The main visual features a surreal landscape made of giant, steaming rice noodle rolls (cheung fun) arranged like terraced fields or rolling hills. Tiny workers dressed as chefs and farmers are tending to these noodle fieldsโsome sweeping, others pushing carts filled with green vegetables (scallions/peppers), and some harvesting. The noodles are translucent white, garnished with chopped scallions and orange bits (possibly carrot or shrimp roe). In the background, there is a hazy city skyline featuring the Canton Tower and skyscrapers under a bright sky. On the right side, a wooden signpost reads "ๅนฟๅผ่ ็ฒ" (Cantonese-style Cheung Fun) with smaller text "ไธไปฝๆธฉๆ ่ธๅๆดๅฅฝ็ๆฅๅธธ" (A portion of gentleness, steamed towards a better daily routine). Bottom right text: "ๆฉ่ถ่ฎฉ็ๆดปๆดๆๆปๅณ" (Morning tea makes life more flavorful). The overall style is hyper-realistic miniature photography mixed with food art, bright, warm, and appetizing.
A detailed prompt for generating surreal photo posters where the top half is a real photo and the bottom half expands into a conceptual 'second world' with mixed media elements.
Based on each uploaded photograph, create an independent 3:4 vertical 'Second World' conceptual surrealist photo illustration poster. Output each separately, no collages. Strictly 1:1 split vertically. The top half is the original realistic photo; the bottom half is another layer of space growing from within the photo. They are not stitched together but exist as continuous presences in different narrative layers of the same moment.
The top half should faithfully preserve the original photo as much as possible, without changing the subject, action, spatial relationships, lighting, color, or texture. Only perform necessary proportional cropping and slight high-end tonal adjustments to give it a clean, restrained, publication-quality photographic feel.
The creative focus is not on the 'subject matter' but on re-understanding the visual structure. First, observe the most decisive structural clues in this photo (e.g., boundaries, slopes, water surfaces, reflections, shadows, cracks, roads, branches, clouds, contours, gaps, flow, repetitive rhythms, spatial turns, or poses). Find the part best suited to 'cross the boundary'. Then let it break through the photo's edge into the bottom half, undergoing a translation of purpose, scale, semantics, or narrative role upon entry. It's not simple extension, but transforming something real into another existence that can be used, entered, measured, salvaged, repaired, organized, borrowed, unfolded, or collected in the second layer of space.
The bottom half is a warm, quiet, off-white space with subtle paper texture and ample whitespace. It is not an illustration background or decoration area, but a place to receive the 'new logic after crossing the boundary'. The relationship follows: Reality โ Crossing โ Translation. The charm comes from a smart and accurate cross-layer narrative, not cute decorations.
You may add minimal black hand-drawn line art figures (0-3), few but precise. Figures are users of the second world, interacting authentically with the translated structures. Lines should be light, simple, natural, slightly handmade, not cutesy, complex, or distracting. Actions should be specific, restrained, and smart, like seriously handling a small thing inherent to this world.
You may add a short English handwritten caption, generated based on the actual 'Second World event' happening in the image. Tone should be like a casual discovery or soft narration, with a hint of humor and lingering interest. Do not write inspirational quotes, explain allegories, or use templates.
The overall style should present a synthesis of Mixed-Media Photo Illustration, Surreal Photomontage, Frame-Breaking Illusion, Trompe-l'ลil, Visual Metaphor, and Conceptual Editorial Illustration. Formally cross-media collage, mechanically frame-breaking, core visual metaphor, emotional tone gentle, slight, and smart micro-surrealism.
Do not make it a template of 'photo + small people + sentence'; do not have extension without translation; do not have form without metaphor; do not force sentimentality; avoid commercial ad feel, complex illustration feel, repetitive actions, baseless decoration, mechanical collage, hard connections, or cheap healing vibes.
Final Goal:
Let viewers first see a valid real photo, then suddenly discover an element crossing into another layer of space, gaining an unexpected yet extremely natural new meaning there.
Not adding creativity to the photo, but revealing the second reality latent within it.
A split layout combining a realistic brick texture with a minimalist graphic poster featuring abstract brick shapes and inspirational Chinese typography.
A split-screen composition. The left half is a close-up photograph of a weathered red brick wall with rough texture and grey mortar lines. The right half features a minimalist graphic design on an off-white background, displaying stylized watercolor-textured orange-red rectangular blocks arranged in a staggered pattern resembling bricks, with a soft peach-colored circle representing the sun above them. In the top right corner, large black Chinese characters read 'ๅนณๅกไนๅข' (The Ordinary Wall). Below this title, smaller text reads 'ไธไบๆฎ้็ๆๆ ไน่ฝๆฏๆ่ตท็ๆดป็้้' (Some ordinary materials can also support the weight of life). Further down on the right side, small vertical text says 'ๆฅๅธธไน็พ ไปไธ้ฅ่ฟ' (The beauty of daily life is never far away). In the bottom right corner, there is a list: '็ / ๆถ้ด / ็ๆดป / ไพ็ถๅไธ /' (Brick / Time / Life / Still Rising /).
A photorealistic prompt generating an image of two young women sharing a quiet, potentially awkward moment in a vintage-style kitchen.
A realistic, high-resolution photograph capturing a candid moment between two young East Asian women standing side-by-side in a rustic, sunlit kitchen. The image has a nostalgic film aesthetic with soft grain and warm tones. On the left, a woman with dark hair tied back in a low ponytail wears a cream-colored short-sleeved blouse with delicate eyelet lace details and a dark plaid midi skirt. She holds a white mug with a small orange floral pattern in both hands, gazing off to her right with a slightly distant or pensive expression. Beside her on the right, another woman with short, choppy dark brown hair wears a light blue-grey textured button-down shirt and a beige linen skirt. She is looking towards the first woman with a subtle, perhaps skeptical or curious glance, holding a folded white towel with red stripes near her waist. The background features a cluttered but cozy kitchen setting: a large window letting in bright natural light, shelves lined with jars of spices and condiments, hanging utensils like ladles and spatulas, and a glimpse of a stove and sink area. The atmosphere feels intimate yet tense, suggesting an unspoken conversation or a moment of awkwardness between friends.
A prompt for generating a vertical poster that combines a realistic golden-hour travel photograph with a hand-drawn watercolor scrapbook collage, referencing specific visual elements.
Create a vertical cozy travel scrapbook poster inspired by the reference images. Combine a cinematic realistic travel photograph on the top half with a hand-drawn memory journal collage on the bottom half.
Top section: Show two young travelers relaxing together on a grassy coastal cliff overlooking a beautiful ocean. One person is taking photographs with a vintage camera while the other is looking through a travel guide/map. Include small travel items such as photographs, postcards and camera accessories on the grass. Warm golden-hour sunlight, soft ocean waves, natural candid poses, nostalgic film photography, muted warm colors, cinematic depth of field, authentic peaceful travel atmosphere.
Bottom section: On warm textured cream paper, create a charming 3ร3 illustrated scrapbook grid inspired by the scene. Draw individual hand-drawn elements: a person with a camera, ocean waves and sun, traveler with a map, vintage photographs, a heart symbol, coastal grass and sea, folded jeans/clothing, overalls/backpack, and ocean waves. Use loose colored-pencil and watercolor strokes with dark brown sketch outlines, muted blue, orange, yellow and green accents. Add tiny hearts, stars, birds, sunshine and decorative doodles.
At the top of the illustrated section, add a handwritten title โGood Timesโ and at the bottom a small handwritten phrase โSame place, better together.โ
Style: nostalgic travel diary, vintage film photography, handmade scrapbook, watercolor + colored-pencil illustration, textured recycled paper, warm cozy tones, imperfect hand-drawn details, emotional friendship/travel memories, premium editorial poster, clean composition, vertical 4:5, highly detailed, no watermark.
A prompt to generate a realistic portrait of a young man styled as the Monkey zodiac sign, complete with a pet monkey and traditional attire.
A cinematic, hyper-realistic portrait of a handsome young man representing the Monkey zodiac. He has messy dark brown hair with loose strands falling over his forehead and wears a thin golden headband. His expression is calm and confident, looking directly at the viewer. He is dressed in traditional Chinese robes featuring intricate gold brocade patterns on black fabric, with a textured ochre sash draped across his chest. Perched on his left shoulder is a small, realistic monkey wearing a miniature matching vest. Behind him, he carries a long, ornate golden staff (Ruyi Jingu Bang) that extends vertically out of the frame. The background is a soft-focus landscape of misty mountains and ancient temple roofs. In the top left corner, there is a large, bold calligraphy character '็ด' in beige ink. On the right side, vertical text reads 'CHINESE ZODIAC MONKEY'. On the left side, vertical white text reads 'ๅคฉ็ๆๆๅฟ
ๆ็จ' followed by smaller text '็ตๅจ่ชๆ
งยทๆบๆ่ฟไบบยท่ช็ฑๆ ็'. A red seal stamp is visible near the text.
Generates a detailed 3D render of a spooky but comfortable living room decorated for Halloween with purple walls, a fireplace, pumpkins, and themed furniture.
A cozy, dimly lit interior of a spooky Halloween-themed living room. The walls are painted a deep purple, and the ceiling features dark wooden beams. A large stone fireplace sits in the center back wall with a roaring fire inside; above it hangs a framed picture of a haunted house under a full moon, flanked by candelabras and draped with red garland featuring a jack-o'-lantern face. To the left is a plush burgundy sofa adorned with various pillows, including one shaped like a white ghost and another with a skull pattern, along with a knitted throw blanket. In the foreground, an armchair has a black pillow with white skulls on it. On the floor lies a circular rug with a starry night pattern. Several orange pumpkins are scattered around the room, some glowing from within. To the right, a large flat-screen TV displays a yellow background with a skeleton character and a long list of song titles or text. Beside the TV stands a tall wooden bookshelf filled with books. A small window on the far left shows a twilight sky outside. The overall atmosphere is warm yet eerie, illuminated primarily by the fireplace glow and ambient lighting.
A detailed prompt for generating realistic close-up phone snapshots with flash lighting, distorted angles, and casual expressions using GPT Image 2.
[Character], clearly adult photorealistic, close-up phone snapshot, face extremely close to lens, slight wide-angle perspective, head tilted to one side, squinting or suddenly widened eyes, random uncontrolled expressions like sticking out tongue, pursing lips, or strange smiles. One hand raised from foreground near camera, randomly making peace signs, heart shapes, pointing at lens, covering half face, or other casual gestures. Direct front phone flash, face and skin illuminated by hard flash, background quickly darkened to near black. Extreme close-up, slight edge cropping, non-standard composition, private phone album snapshot feel, slight wide-angle facial distortion, realistic digital sharpening and JPEG texture. Tiny 'voxcat' signature bottom right.
A prompt for creating dreamcore night portraits with harsh flash lighting, frozen motion, and colorful bokeh against a black background.
[Character], clearly adult photorealistic, retaining hairstyle outline, hair color, eyes, main clothing colors, and iconic accessories.
Dreamcore night portrait ร Black field photography ร Flash freeze ร Star cluster bokeh ร Private snapshot.
Person in large deep black space, body sideways, suddenly looking back at camera, one hand raised to side of face blocking flash. Close-range skewed half-body composition, tilted shoulders, palm near lens, forming natural depth scale difference.
Strong on-camera direct flash freezes face, eyes, and moment. Light-colored jacket forms nearly overexposed glowing white block, character main color clearly shown in inner wear or accessories. Flash intensity decays rapidly with distance, some body contours merge into black field.
Arms, hem, and contour edges retain slight motion afterimages and soft focus, face remains clear. Scattered few red, blue, yellow light points in distance, varying size and blur, forming ambiguous spatial star cluster bokeh.
2:3 vertical, text element is tiny 'voxcat' signature bottom right.
Prompt for monkey-themed cosplay at a summer night BBQ stall with old phone camera quality.
Adult female Cosplayer, monkey-themed outfit, natural long black hair loose, some strands sticking to forehead, cheeks and neck due to heat and sweat. Wearing brown-white plush round ears, brown plush short-sleeve dress, cream-white plush trim on collar and cuffs, simple lace-up structure on chest, brown plush curled tail connected at waist, wearing thin gold necklace.
Character sitting on red plastic chair at summer night open-air BBQ stall, body leaning forward close to lens, head slightly tilted, looking directly at camera, cheeks flushed, small sweat beads on forehead and nose tip, lips slightly parted, playful expression from being heated by steam. One hand holding freshly grilled bone-in meat, meat close to side of face, surface charred brown, oily, bones clearly visible. Small monkey tightly beside character, monkey's front paws resting on table edge, looking up at meat in hand, forming natural private group photo squeezed into same frame.
Close-range skewed half-body composition, slight phone wide-angle perspective, face and meat close to lens, shoulders, arms and monkey naturally cropped at frame edges. Foreground has stainless steel grill tray, charcoal grill and several pieces of meat, grease reflection and smoke clearly visible. Background is real night market BBQ stall, plastic tables/chairs, diners' backs, simple sheds and warm yellow bulbs creating messy yet daily spatial layers.
Early 2000s old Nokia phone photography, low-pixel color digital photography, close-range direct flash, face and plush clothing illuminated by frontal flash, skin showing direct and slightly hard highlights, background brightness rapidly decaying, distant bulbs locally overexposed. Low resolution, slight out-of-focus, soft edges, rough digital noise, JPEG compression artifacts, limited dynamic range, uneven white balance, skin tone slightly cool gray and pink shift, background warm yellow lights mixed with cyan-gray shadows. Real snapshot, private record feel, retaining hot night sweat, messy hair and natural demeanor.
3:4 vertical format, only text in image is tiny handwritten signature "voxcat" in bottom right corner.
A dual-panel promotional poster for the 2025 Tsing Hua University Arts Festival featuring colorful floral illustrations in both sharp vector and soft-focus styles.
Create a split-screen graphic design poster for the '2025 Spring x Tsing Hua Arts Festival'. The left side features a clean white background with vibrant, flat vector-style illustrations of flowers including a large daisy, pink lilies, blue hydrangeas, and purple lilacs. Vertical Chinese text on the far left reads '2025 ๆฅไนๆธ
่ฏ่่ก็ฏ' alongside English text 'Spring x Tsing Hua Arts Festival'. The bottom left contains four distinct event categories: '้ณๆจๆๆจๅคงๅธซ็ญ', 'ๅตไฝๅฑ่ฆฝ', '่่กๅทฅไฝๅ', and '็ ่จ่ซๅฃ', each with specific dates (4/15-5/28) and small QR codes. The right side displays a soft-focus, dreamy version of the same floral arrangement against a warm, hazy cream background. Large serif typography at the top reads '2025 Spring x Tsing Hua Arts Festival', accompanied by smaller text 'ART CULTURE PEOPLE IN BLOOM'. The bottom right shows the dates '4.15 โ 5.28' and the logo 'TSING HUA UNIVERSITY'.
This prompt generates a promotional banner for a game development project featuring multiple AI-generated monster designs alongside explanatory Japanese text about turning common generative AI artifacts into enemy characters.
A horizontal banner image with a light beige background. On the left side, there is Japanese text in purple and yellow: 'ๅถไฝ่จ้ฒ #2 ๆตใญใฃใฉ็ทจ' (Production Record #2 Enemy Character Edition), followed by large bold text '็ๆAIใฎใใใใใใใใขใณในใฟใผใซ๏ผ' (Generative AI's "Common Occurrences" become monsters!), and smaller text below 'ใธใงใใณใฎๅ้บ ๏ฝใใคใบใฎๅคง่ฟทๅฎฎ๏ฝ ๆตใญใฃใฉๅถไฝใฎ2ๆฅ้' (Geneko's Adventure ~ The Labyrinth of Noise ~ Two Days of Enemy Character Creation). To the right of the text, there are two small chibi characters: a girl with brown hair wearing glasses and a school uniform holding an open book, and a blue cat-like creature with pink ears reading over her shoulder. The rest of the image is filled with a collage of various colorful monster designs arranged in rows. Top row includes a shiny green sphere with eyes, a muscular blue furry beast with glowing purple eyes, a purple insectoid robot with green wings, and a multi-limbed robotic figure. Middle section features a red beetle-like creature with warning signs on its shell, a wizard character wearing a rainbow-colored pointed hat and robe holding a staff, a white moth-like creature with blue eye patterns on its wings, a black spider-tank hybrid with red lights, and a pink abstract shape resembling a face or symbol. Bottom row shows a green goblin-like creature with glowing yellow eyes, a brown spiky turtle-like monster, a pale humanoid figure with blank facial features, a split-faced doll character (half pink/half grey) holding a knife, and a purple blob monster with angry eyes.
A dual-panel image showing a realistic overhead shot of pastel stationery alongside a matching cute watercolor illustration of the items as characters.
Goal: Create a vertical two-panel image contrasting a realistic top-down desk photo with a cute kawaii illustration of the same items.
Canvas: Vertical 4:5 aspect ratio, split horizontally into two equal sections.
Top Section (Realistic Photo): A high-angle flat-lay photograph on a clean white surface. Soft dappled sunlight shadows fall across the scene from the left. Items include: a mint green sticky note square labeled "Focus." in white serif text; a small square photo of a blue and beige macaron; three copper wire spiral paper clips scattered around; a light blue marker pen with cap off; a sage green mechanical pencil with gold tip; a light blue ballpoint pen with gold tip; a light blue highlighter; a teal envelope or folder edge on the left; and a lined notepad corner at the bottom left.
Bottom Section (Kawaii Illustration): A hand-drawn watercolor-style illustration on a cream background featuring anthropomorphic versions of the items above. The characters have simple happy faces (two black dot eyes, pink blush circles, smiling mouths). Elements include: a stack of two macarons (blue top, beige bottom) with a face; a sage green sticky note character labeled "Focus." holding a tiny heart; a tall green marker character standing upright; a lying down blue highlighter character; a lined paper sheet; a copper spiral clip; and yellow sparkle stars. Handwritten Korean text appears in two places: upper right says "์ง๊ธ, ์ข์ ๊ฒ์ ์ง์คํด์." (Now, focus on good things.) with a heart symbol; lower left says "์์ ์ค๋์ด ์ข์ ํ๋ฃจ๋ฅผ ๋ง๋ค์ด์." (Small todays make a good day.) underlined in green.
Visual Style: The top is crisp, bright, and airy photography. The bottom is soft, pastel-colored, whimsical watercolor art with thin outlines.
A stylized manga page illustrating the concept of prompt engineering for AI image generation, featuring a kitsune character and a breakdown of visual elements.
A vertical, highly detailed manga-style infographic page with a parchment-like background. The layout is divided into three main sections: a top illustration area, a middle diagrammatic breakdown, and a bottom text-heavy conclusion.
Top Section:
- A large, ethereal illustration of a woman with long white hair and fox ears (a kitsune) standing on a mountain peak at sunset. She wears flowing white robes.
- Below her, an elderly man with long black hair tied back, wearing dark blue traditional Chinese robes, sits cross-legged holding a calligraphy brush, looking up thoughtfully.
- To his right, a younger man in grey robes kneels, sketching the kitsune onto paper.
- Surrounding this scene are blocks of Japanese text explaining the concept of 'Prompt' (ใใญใณใใ).
- On the left side, there are four small square character portraits labeled with descriptions like 'Beautiful Woman', 'Dancer', etc., showing variations of female characters.
- Large vertical Japanese text on the right reads 'Introduction to Prompts'.
Middle Section:
- A horizontal flow diagram titled 'Verbalizing features to compose a picture'.
- It shows a sequence of six small square images connected by plus signs (+), leading to an equals sign (=) and a final result image.
- The sequence includes: 1. Long silver hair, 2. Blue eyes, 3. White clothes, 4. Mountain sunset, 5. Looking back pose, 6. Soft backlighting.
- The final result is the complete image of the kitsune from the top section.
Bottom Section:
- A large, bold Japanese headline in red and black ink style: "Listing hundreds of words loses one stroke" (็พ่ชใไธฆในใฆไธ็ปใๅคฑใ).
- Surrounding the headline are torn pieces of paper with handwritten notes listing negative effects of over-prompting, such as '8K resolution', 'ultra-high quality', 'complex composition', 'unnatural lighting', 'film-like lighting', 'large scale', 'highest quality'.
- At the very bottom, a concluding sentence in a box states that words are tools, but too many obscure the essence of the single stroke.
A comprehensive character design sheet for a protective shadow-beast Hell Hound and its tiny cat companion, featuring lore, anatomy studies, and behavioral poses.
Goal: Create a dark fantasy character design sheet for a 'Hell Hound' guardian creature, featuring a small cat companion named Stinky.
Canvas: Vertical infographic layout with a parchment-style background and gothic typography.
Layout: Top section features the main illustration; middle sections contain detail panels and skeletal studies; bottom section displays behavioral poses and a poetic oath.
Subject details: The Hell Hound is a massive, terrifying beast made of living shadow and charcoal-black fur. It has a skeletal, ancient skull head with glowing white eyes, long spindly limbs, and sharp claws. Despite its monstrous appearance, it is crouching protectively around a tiny, cute grey cat wearing a pink hoodie (Stinky). The atmosphere is moody, magical, and protective.
Text content: Include specific labels and lore text:
- Title: "HELL HOUND" in large gothic font.
- Subtitle: "FOREST GUARDIAN & PROTECTOR".
- Stats block: Type: Noble Protector, Habitat: Kolby's World, Skin: Charcoal Black - Guardian's Oath, Coat: Shimmering Void, Behavior: Protective โข Loyal โข Gentle, Primary Mission: Protect the innocent โ especially Stinky.
- Quote: "You will never harm what I swear to protect."
- Detail Panels: "COLOR VARIANTS" (Charcoal Black, Ash Gray, Corpse Gray), "SKIN DETAIL", "EYE DETAIL", "HEAD DETAIL", "TEETH", "CLAW / HAND".
- Skeletal Study: Front, Left, Back, Right views of the hound's skeleton.
- Movement & Behavior: Resting/Watching, Protecting, Sheltering, Gentle.
- Common Hiding Places: Forests, Abandoned Places.
- Odor: Smells like rain, moss, and ancient oaths.
- Bottom Section: "THE GUARDIAN'S OATH" poem starting with "I do not hunt her..." ending with "I am her forever." Footer text: "STINKY IS PROTECTED. ALWAYS. NO HARM SHALL TOUCH HER. EVER."
Visual style: High-fantasy concept art, dark academia aesthetic, detailed textures, dramatic lighting with golden sparks surrounding the hound.
A detailed character reference sheet featuring a male and female anime character in traditional Chinese Hanfu attire, including multiple angles and accessory close-ups.
A high-resolution character design sheet featuring two anime-style characters dressed in traditional Chinese Hanfu, set against a plain white background. The layout includes full-body front and back views for both characters, along with detailed close-ups of their heads, accessories, and clothing textures.
Left Character (Male):
- Appearance: Young man with short black hair wearing a tall, structured black official's hat (Guan) with ribbons hanging down. He has blue eyes and a gentle expression.
- Outfit: A dark navy/black cross-collar robe (Yi) with wide sleeves, trimmed with a patterned reddish-brown border. Underneath is a white collar. He wears a long skirt-like lower garment (Shang). A belt with a gold buckle secures the waist, from which hangs a jade pendant ornament (Pei) with red tassels. He holds a sword in a black scabbard with red accents.
- Views: Front full-body view holding the sword; back full-body view showing the drape of the robe; headshot close-up; isolated detail shots of the hat, belt buckle, jade pendant, and sword.
Right Character (Female):
- Appearance: Young woman with light brown/auburn hair styled in an elaborate updo with loops and side bangs framing her face. She has blue eyes and a calm expression. Her hair is adorned with a hairpin featuring a jade disc and red tassel.
- Outfit: A layered ensemble consisting of a peach/light orange outer robe with a subtle floral pattern and deep red trim at the collar and cuffs. Underneath is a cream-colored pleated skirt (Qun) with a reddish-brown patterned panel visible at the hem. A pink sash is tied around the waist, also featuring a hanging jade ornament.
- Views: Front full-body view; back full-body view showing the long hair and robe details; headshot close-up; isolated detail shots of the hairpin, collar texture, and waist sash knot.
A comprehensive character reference sheet for an armored anime heroine, including profile stats, orthographic turnaround, expression variations, wardrobe breakdown, material palette, and technical notes.
Create a highly detailed, professional character design sheet for an anime-style female warrior named {argument name="character name" default="RU RIO"}. The layout should be organized into distinct sections on a dark background with gold and white text.
**Top Left (Profile):** A header titled "CHARACTER PROFILE" featuring a winged emblem. Below it, the name "RU RIO" in large serif font, subtitle "SWORD QUEEN". Include a data list: AGE (22), HEIGHT (172cm), OCCUPATION (Sword Queen), AFFILIATION (The Royal Court of Elysion), TITLE (Heir to the Radiant Throne), ELEMENT (Light), WEAPON (Regal Longsword "Lumina Regalia"). Add a "PERSONALITY" section describing her as calm and unwavering, and a "LIKES/DISLIKES" section. End with a quote: "A queen's blade shall never waver."
**Top Center (Main Art):** A large, high-quality bust portrait of the character looking slightly upward. She has short black hair, grey eyes, and wears intricate silver plate armor with gold filigree and a high collar.
**Top Right (Turnaround & Analysis):** A section labeled "ORTHOGRAPHIC TURNAROUND" showing five full-body views of the character standing straight: FRONT, 3/4 FRONT, SIDE, 3/4 BACK, and BACK. To the right of this is a "PROPORTIONAL ANALYSIS" diagram showing the front view with horizontal grid lines marking head-to-foot ratios (Head x 1, Head to Chin, etc.).
**Middle Band (Expressions):** A row labeled "EXPRESSION ANCHORS" containing eight square panels showing close-ups of the character's face with different emotions: NEUTRAL, CALM, DETERMINED, PROUD, SOFT SMILE, SWEET SMILE, CONCERN/HANDLING, and BATTLE CRY.
**Bottom Left (Wardrobe):** A section titled "WARDROBE & ACCESSORIES BREAKDOWN". It displays the full outfit on a mannequin, followed by isolated items labeled: CLOAK, TORSO ARMOR, GAUNTLETS, LEG ARMOR, BOOTS, and various small accessories like belts and jewelry.
**Bottom Center (Materials & Details):** Two rows. The top row is "MATERIAL PALETTE" showing swatches for SILVER STEEL, MIDNIGHT SATIN, STARCHED TOP, ROYAL LEATHER, and GILDED TRIM. The bottom row is "DETAIL CLOSE-UPS" showing macro shots of SHOULDER PAULDRON, CHEST ORNAMENT, THIGH STRAP & CHAIN, THIGH HARP & CHAIN, and SWORD HILT DETAIL.
**Bottom Right (Technical):** A column with "TECHNICAL NOTES" listing bullet points about the silhouette and fabrics. Below that, a "COLOR SCHEME" strip with diamond-shaped color swatches. Finally, a "RIG & MOVEMENT REFERENCE" section showing three small wireframe/skeleton diagrams of the character.
A detailed prompt for generating a vertical editorial storybook illustration of a woman studying in a cafe, featuring Scandinavian folk-art simplicity and watercolor sketchbook aesthetics.
GPT IMAGE 2 on CHATGPT
Use case: illustration-story
Asset type: vertical editorial storybook illustration, standalone generation without any reference image
Scene/backdrop:
A quiet neighborhood cafรฉ depicted as a minimal, poetic everyday scene. A young woman sits alone at a small round cafรฉ table, studying on an open MacBook. Include only a simple chair, the laptop, one notebook, a pen, a ceramic cup, and a small suggestion of a cafรฉ window or pendant lamp. Keep the environment sparse and flattened, with no detailed interior architecture.
Subject and action:
Show the young woman in a relaxed three-quarter side view, leaning slightly toward the laptop with one hand near the keyboard and the other writing a note. Her expression is calm, curious, and absorbed in studying. Give her simplified childlike proportions, a softly rounded face, slightly oversized hands, a compact geometric hairstyle, and a natural seated pose. Dress her in a patterned cardigan, loose trousers, and simple shoes. The laptop should be recognizable as a slim MacBook, but do not show a prominent logo or any readable screen content.
Style and medium:
Decorative folk flat illustration infused with delicate minimal watercolor sketchbook art. Combine Scandinavian folk-art simplicity, Japanese picture-book restraint, and modern flat editorial illustration. Reduce every person, object, and furnishing to clean, softly rounded geometric color blocks. Use opaque gouache-like shapes layered with faint translucent watercolor washes. Add loose, imperfect ink-pen contours with gently wavering line weight, occasional broken edges, tiny scratch marks, short stitch lines, dots, and naรฏve hand-drawn patterns. The drawing must feel handmade, slightly asymmetrical, tender, and intentionally imperfect.
Color palette:
Use a fresh palette completely independent from the source image: dusty violet, periwinkle blue, raspberry red, pale lemon, apple green, warm cocoa brown, and creamy ivory paper. Use no teal, coral-orange, mustard, or dark navy as dominant colors. Keep the palette limited and harmonious, with violet or periwinkle as the main clothing color and raspberry and lemon used only as playful accents.
Composition:
Portrait orientation, approximately 2:3. Make the seated woman and laptop the unmistakable focal point, occupying about 60 percent of the canvas. Use a gently cropped table and chair to anchor the lower half. Preserve generous off-white negative space around the figure, especially above and along the outer edges. Use a mostly flat side-view perspective with only a slight tabletop angle. Keep the visual hierarchy simple and immediately readable.
Decorative details:
Scatter only a few tiny floating elements through the empty space: four or five dots, two miniature petals, one naรฏve eight-point star, a small leaf sprig, and one faint lavender watercolor splash. Add a tiny hand-drawn check or seed pattern to the cardigan and a simple scalloped edge on the cup or lampshade. Decorat
A prompt for generating a minimalist, experimental typography poster with a Mid-Autumn theme, featuring large sans-serif characters and Gucci red accents.
Take any futuristic theme providing core concepts, short phrases, and minor auxiliary notes, and translate the theme into an extremely enlarged text or symbol subject: The first impression must be heavy, bold sans-serif glyphs filling almost the entire frame, pressed horizontally into the layout, with the character body occupying the center like structural beams, partially cropped or overflowing, making reading first become a strong form event before reading subtitles at its edges. Keep the background largely empty with cool white space, overlaid with extremely thin, light warm-colored composition lines, baselines, and vertical column lines; these lines should look like unhidden skeletons of a design draft rather than decoration. Use only high-saturation orange-red as the primary color to carry all visual weight, gray for small explanatory text, avoiding multi-colors and gradients. Information modules are sparsely placed at grid intersections and edges: small icons composed of simple geometric angles, dots, and short dashes; titles are short and bold; body text is in narrow columns and light gray. The overall presentation should have a precise, restrained, experimental typographic educational feel. Glyph construction requires low contrast, thick strokes, large open counters, flat terminals, tight tracking; punctuation and auxiliary symbols also follow the grid rhythm. If switching to other writing systems, maintain equivalent block volume, inner/outer spatial relationships, cropping pressure, and horizontal reading momentum. Prohibit illustrative backgrounds, shadows, paper textures, centered cards, rounded cuteness, commercial poster lighting effects, and over-packed information.
โโโโโโ
Theme: {argument name="theme_en" default="Joy"}
Aspect Ratio: {argument name="aspect_ratio_en" default="9:16"}
Note: Appropriate Mid-Autumn elements
Font Color: {argument name="font_color_en" default="Gucci Ancora Red"}
A detailed industrial-style infographic poster illustrating the workflow and principles of a wastewater treatment plant, featuring process diagrams and bold typography.
Create a horizontal infographic poster explaining the working principles of a wastewater treatment plant. The design style is industrial, modern, and high-contrast, utilizing a color palette of deep red, black, white, and teal/blue for water elements.
**Layout & Text Elements:**
1. **Top Left/Center (Headline):** Large, bold, distressed red Chinese characters "ๆฑกๆฐดๅค็ๅ" (Wastewater Treatment Plant) spanning across the top. Below it, large black bold text "ๅทฅไฝๅ็" (Working Principles). Smaller black text underneath: "ไป่ฟๆฐดใๅ็ฆปใ็ๅๅๅบๅฐๅๅๅบๆฐด" (From influent, separation, biochemical reaction to purified effluent).
2. **Left Sidebar:** Vertical layout with small text blocks. Top block: "่ฎฉๆฏไธๆปดๆฑกๆฐด้ๅ่ช็ถ" (Let every drop of sewage return to nature), "ๆฐด็ไธไธ็ซๆฏๆดๆดๅ็ๆชๆฅ" (Water's next stop is a cleaner future), English text "CLEANER WATER BRIGHTER TOMORROW". Bottom block (red background): "ๅค็ๆนๅไธบไบๆดๅฅฝ็ๆฐด็ฏๅข" (Treatment changes for a better water environment), English text "CLEAN CYCLE HEALTHY CITIES".
3. **Right Side (Background Image):** A large photographic collage showing an aerial view of circular clarifier tanks filled with blue-green water, connected by pipes and walkways. Overlay text on the right: "ไปๆฑกๆฐดๅฐๆธ
ๆฐด" (From sewage to clear water), "่ฟๆฅๅๅธไธๆดๅฅๅบท็็ๆดป" (Connecting cities with healthier lives), "FOR A CLEANER TOMORROW", "ๆฐดๅพช็ฏ ๅๅธ่ฟ่ก ไธ่ช็ถๅ
ฑ็" (Water cycle, city operation, symbiosis with nature), "ๅๅ ่ฎฉๅๅธๆดๆ็ๅฝๅ" (Purification makes cities more vibrant), "CLEAN WATER STRONGER CITIES".
4. **Bottom Center (Process Diagram):** A schematic cross-section diagram showing the flow of water through different stages. Arrows indicate direction from left to right. Labels above the sections: "ๆ ผๆ
/ ๆฒ็ " (Screening/Grit Chamber), "ๅๆฒ" (Primary Sedimentation), "็ๅๅๅบ" (Biochemical Reaction - depicted with bubbles), "ไบๆฒ" (Secondary Sedimentation). Labels at ends: "่ฟๆฐด" (Influent) on left, "ๅบๆฐด" (Effluent) on right.
5. **Bottom Right:** Small text block: "ๆดๅนฒๅ็ๆฐด ๆดๅฎๅฑ
็ๅๅธ ๆดๅฏๆ็ปญ็ๆๅคฉ" (Cleaner water, more livable cities, more sustainable tomorrow), English text "CLEANER WATER HEALTHIER CITIES A BRIGHTER TOMORROW".
6. **Center Red Box:** A small red square containing white text: "็ไธ่ง็ๅทฅ็จ ๆฏๆ็ๅพ่ง็็พๅฅฝ็ๆดป" (Invisible engineering supports visible good life), English text "INFRASTRUCTURE FOR A HEALTHIER TOMORROW".
**Visual Style Details:**
* Use a grainy texture overlay on the entire image to give it a printed paper feel.
* The typography should be heavy sans-serif for Chinese characters.
* The water in the photos and diagrams should be a distinct teal/cyan color against the grayscale/red/black background.
A detailed prompt for generating minimalist, high-aesthetic posters with a sense of ceremony and rationality using GPT Image 2. It specifies layout, typography, color usage, and negative constraints to achieve a museum-like white space effect.
Create a minimalist ceremonial information poster around any given theme. The first impression must be a large area of warm white empty space where the main title is precisely centered, engaging in solemn alignment with three thematic symbols: transform the core name, participants, or keywords provided by the theme into a large thin-stroke title at the top, a set of recognizable abstract logos in the center, and solid color blocks on both sides; semantics may change but order remains constant. Retain high-ratio whitespace, vertical central axis, upper-lower zoning, and the pause feeling of thin black horizontal lines; arrange all elements restrainedly like an exhibition catalog or international institutional yearbook. Use high-contrast fine serifs or equivalent glyph structures for the main text, with open counters, slender strokes, sharp terminals, and spacious rhythm, maintaining a slender skeleton, loose tracking, clear recognition, and calm breathing when switched to any writing system, rather than copying a specific Latin font. Extract two high-purity representative colors from the theme for hard-edged squares; use only black lines and minimal solid geometry for the central logo; keep the background as slightly paper-textured warm white, avoiding gradients, shadows, and decorative textures. Place subtitles and small explanatory text at a lower center of gravity at the bottom, with footer micro-information pressing the edges, creating a contrast where grand themes are tamed by museum-style whitespace; failure symptoms include crowded elements, chaotic colors, thick fonts, realistic icons, or the poster losing its cold ritual order.
Set the theme to "City Public Library Open Day" for a public cultural institution event main poster: use indigo blue and cinnabar red as the two high-purity square colors; abstract opened book pages and door arches with black lines in the center, letting the symbol group fall steadily below the title along the vertical axis; place the main title in the center of the upper half, with subtitles and dates forming a sparse two-level information hierarchy below, retaining large areas of warm white whitespace and thin black line pauses; aspect ratio is vertical 3:4.
A structured prompt for creating a 3x3 grid of realistic user-generated content style panels for marketing campaigns, including space for cinematic visuals and production notes.
Create a full-sheet 3x3 grid of realistic UGC-style panels featuring this {argument name="category" default="provision store"} using GPT Image 2. Split the video into 3 continuous sections. Each panel must contain a cinematic visual frame plus readable production notes printed directly inside the panel. The goal isn't just to show the product. Itโs to help customers imagine a reason to buy it. The business name is {argument name="business name" default="Zioraa Ventures"}. Embedded the business name in the background.
Creates a split-screen scene comparing a misty golden forest deer photograph with a minimalist needle-felt wool illustration.
Goal: Create a two-panel horizontal comparison image showing a real-life nature photo transformed into a minimalist needle-felt illustration.
Canvas: Wide 16:9 canvas split vertically into two equal halves with a clean straight division down the center.
Left panel: A realistic golden-hour forest meadow photograph. Show exactly 5 deer in the foreground: 1 deer walking at far left, 1 deer grazing left-center, 1 deer grazing center, 1 small deer standing upright center-right, and 1 larger deer standing at far right. The meadow is covered in dewy green grass, with warm yellow sunlight and soft morning mist. In the background, dark evergreen trees form a dense forest silhouette, with additional leafy branches at the upper right. Strong sunbeams stream diagonally through the trees from the upper right, creating a serene cinematic atmosphere.
Right panel: A soft handmade needle-felt wool reinterpretation of the same scene on a warm off-white textured paper background with generous blank space. Center the felt scene horizontally in the upper-middle area. Show exactly 5 small felt deer matching the left panel arrangement: 1 standing deer at far left, 1 grazing deer left-center, 1 orange-brown grazing deer center, 1 small upright deer center-right, and 1 larger standing deer at far right. Place them on a thin strip of fuzzy pale green felt grass. Above them, include a simple round felt sun and 2 soft horizontal felt cloud wisps. Under the felt grass, add handwritten text reading {argument name="caption text" default="A kinder morning โก"} in a delicate gray-brown script.
Visual style: Combine warm healing aesthetics, generous white space, cozy wool-felt texture, soft edges, muted earthy colors, and a calm poetic mood. The left side should look photographic and atmospheric; the right side should look like a handcrafted felt illustration with visible fibers and a minimal composition.
Constraints: Keep the split-screen layout, exactly 5 deer on each side, no extra animals, no border, no watermark, no additional text beyond the caption.
Generates a professional technical infographic with blueprint-style overlays, including dimensions and diagrams for product design visualization.
Premium technical infographic of {argument name="product" default="[Apple 18 pro ]"}. Use the reference image only to understand the shape and structure of the object, without copying the same photo, angle, composition, or background. Reinterpret the subject in a new professional and realistic photograph, clean and well-lit, with a suitable and more aesthetic background. Keep the object as a real photo, not an illustration. Add a technical blueprint-style overlay with white lines, arrows, dimensions, labels, and small diagrams of parts, materials, measurements, and functionality. Clear, elegant, and informative composition. Include a sketch box in the upper left corner with the title "{argument name="title" default="[Apple 18 pro]"}
A prompt to transform an attached research paper into a professional academic poster following specific conference regulations.
Research the poster regulations for presentation at the {argument name="conference name" default="2026 Neuroscience Conference"} and transform the attached paper into a poster accordingly.
A comprehensive prompt setup to generate clean 3D graphic design layouts, informational diagrams, and matte-texture presentation slides.
You are an information editor, diagram designer, and 3D art director.
- Compare 3 visual proposals matching the content, and adopt the most intuitive option.
- Explain using objects or materials specific to the subject. Use books, bamboo slips, or paper for classical literature; parts or assembly for manufacturing.
- Elegant matte materials, soft lighting, and natural depth. Use 3D representations to convey sequence, relationships, and changes.
A prompt for generating a realistic image of a girl in a modified school uniform fighting zombies in a burning medieval village.
A hyper-realistic, cinematic action shot of a young Japanese female warrior in the midst of a chaotic medieval battle. She has long black hair tied back with two gold hair clips and wears a modified dark blue sailor-style school uniform (seifuku) reinforced with heavy leather armor on her shoulders and arms. Her face is dirty with soot and blood splatters, showing an intense, determined expression as she lunges forward. In the foreground, blurred zombie-like creatures are attacking. The background depicts a burning village with wooden structures, smoke rising into the sky, and other soldiers fighting amidst the chaos. The lighting is dramatic and gritty, emphasizing the realism of the scene.
A cinematic render of a bearded Minecraft avatar holding a bee in a sunflower field at sunset, featuring a pixelated rainbow background.
A hyper-realistic, cinematic close-up shot of a Minecraft-style character standing in a vibrant field of sunflowers during a golden sunset. The character is constructed from blocky voxels, featuring dark skin, a full black beard, and wearing a green cap with a white t-shirt and green pants. He is holding a large, blocky bee gently against his face. Surrounding him are numerous other flying bees with translucent wings, rendered with realistic motion blur and depth of field. In the background, there is a pixelated rainbow arching across an orange sky filled with blocky clouds, a distant tree line, and a small white pickup truck on a dirt road. The lighting is warm and volumetric, creating a nostalgic and peaceful atmosphere.
A creative image generation prompt describing a llama undergoing a wild magic transformation with enchanted vines and elemental effects.
A llama undergoing a Wild Magic Transformation as enchanted vines, glowing feathers, dragon scales, elemental flames...
A prompt for GPT Image 2 to generate a surreal, photorealistic scene of a man sitting on a cloud above a city drinking coffee.
Create an ultra-realistic, cinematic, photorealistic surreal photograph of a handsome young South Asian man sitting casually on a gigantic fluffy white cloud hundreds of meters above a sprawling modern city, peacefully drinking a cup of coffee while commercial airplanes fly beneath and around him.
The man is in his mid-20s, with thick slightly messy wavy black hair, warm brown skin, expressive deep-brown eyes, and a neatly trimmed beard and mustache. He wears an oversized black technical jacket over a clean white T-shirt, dark wide-leg cargo trousers, futuristic black sneakers, a silver chain, and a black smartwatch. His expression is calm and relaxed, as if sitting on a balcony above the world.
The enormous cloud looks physically realisticโsoft, dense, voluminous and detailed, with individual vapor textures and subtle sunlight passing through its edges. The man sits naturally on its surface, one leg slightly hanging over the edge, holding a realistic ceramic coffee cup in one hand.
Far below, a vast modern city stretches toward the horizon with skyscrapers, roads, tiny vehicles, parks and realistic atmospheric haze. Several passenger airplanes fly through the sky at different distances and scales, creating an incredible sense of depth. One airplane passes relatively close beneath the cloud while others appear tiny near the horizon.
Golden-hour sunlight illuminates the scene from the side, creating warm highlights on the man's face, clothing and cloud while casting soft natural shadows. The sky transitions from bright blue near the horizon to deeper blue overhead, with subtle wispy clouds scattered across the atmosphere.
Use an epic wide-angle composition showing the enormous scale difference between the man, cloud, airplanes and city below. Strong foreground-to-background depth, realistic atmospheric perspective, natural reflections, physically accurate lighting, detailed skin texture, realistic fabric fibers, realistic hair strands, cinematic color grading, HDR, subtle film grain, shallow depth of field on the character with the distant city naturally softened.
Photographed like a high-end cinematic editorial campaign, 35mm lens, f/2.8, ultra-detailed, 8K UHD, photorealistic, natural proportions, realistic human anatomy, believable physics, dramatic scale, surreal but completely convincing.
No cartoon appearance, no illustration, no CGI look, no plastic skin, no distorted face, no extra fingers, no duplicate people, no deformed airplanes, no floating objects, no text, no watermark.
A prompt for generating an ultra-realistic cinematic scene of a man standing in a hall surrounded by doors leading to different worlds like cosmic dimensions, frozen kingdoms, and cyberpunk cities.
Ultra-realistic, cinematic 8K HDR, high-fashion editorial photograph of a strikingly handsome young man in his early 20s, with thick naturally wavy jet-black hair, strong masculine eyebrows, intense deep dark-brown eyes, a sharply defined sculpted jawline, subtle natural stubble, and realistic skin texture with visible pores.
CONCEPT & COMPOSITION:
A breathtaking, surreal cinematic scene featuring a handsome young man standing confidently at the center of a gigantic, mysterious hall surrounded by dozens of magnificent doors of different shapes, sizes, materials, and architectural styles. Every door opens into a completely different world, creating a spectacular visual contrast between reality, fantasy, and the unknown.
The young man wears a perfectly tailored black outfit consisting of a luxurious black high-neck shirt, a long elegant black coat, tailored black trousers, and polished black boots. His thick, naturally wavy hair is slightly tousled, and his intense eyes gaze directly toward the camera with a calm, confident, mysterious expression. One hand rests gently on the handle of a partially opened door, as if he is about to step into another dimension.
THE DOORS & THEIR WORLDS:
Surrounding him are dozens of enormous, beautifully detailed doorways, each revealing a unique and breathtaking environment:
๐ Cosmic Dimension: A glowing galaxy filled with colorful nebulae, distant planets, stars, and swirling cosmic energy.
๐๏ธ Frozen Kingdom: A magical winter landscape with snow-covered mountains, frozen waterfalls, and gently falling snow.
๐ฅ Kingdom of Fire: A dramatic volcanic world with flowing rivers of lava, burning skies, and glowing embers.
๐ธ Cherry Blossom Paradise: A peaceful Japanese landscape filled with pink cherry blossoms, a traditional Japanese temple, and a beautiful red bridge.
๐ฐ Dark Fantasy Realm: A mysterious gothic castle surrounded by a dark enchanted forest and a sky illuminated by lightning.
๐ Cyberpunk Future: A futuristic city with towering skyscrapers, glowing neon signs, flying vehicles, and vibrant blue and purple lights.
๐ฟ Enchanted Forest: An extraordinary magical forest with gigantic ancient trees, glowing flowers, floating golden particles, and mystical waterfalls.
โ๏ธ Heavenly Dimension: A magnificent world above the clouds featuring golden palaces, radiant sunlight, and endless white clouds.
๐๏ธ Lost Desert Civilization: An ancient golden city surrounded by desert dunes.
A creative writing snippet serving as a prompt for a steampunk-themed image titled 'The Last Gear', created with GPT Image 2.
"The Last Gear"
The mechanical city had stopped.
I gently picked up the last remaining gear.
If this meshes,
surely, this world will move again.
โ๏ธ๐งโจ
A prompt for generating a realistic image of a colossal MPD robot assisting in a nighttime disaster relief operation with human first responders.
A cinematic, photorealistic night scene depicting a massive bipedal police robot standing in the center of a muddy disaster response zone during heavy rain. The giant robot is white and black with industrial paneling, featuring red emergency lights on its shoulders and head, and markings that read "่ญฆ่ฆๅบ MPD" (Metropolitan Police Department) on its chest and arms. Its head consists of multiple camera lenses arranged horizontally. Surrounding the robot's feet are numerous first responders: police officers in dark uniforms with "MPD" on their backs, firefighters in orange gear, and paramedics in blue vests with Japanese text. To the left is a mobile command unit truck displaying screens with data maps. In the background, there is a large pile of rubble or debris illuminated by floodlights, with excavators visible atop the mound. Several drones hover in the sky, casting bright spotlights down onto the wet ground. The atmosphere is tense and high-tech, with reflections on the wet pavement and rain streaks visible against the dark sky.
A high-quality anime-style portrait of a girl holding an old book on a snowy street at twilight, featuring warm lighting and falling snow.
Create a vertical digital illustration in a semi-realistic anime style depicting a young woman standing on a snowy cobblestone street during twilight. The subject has long, dark hair with bangs, dusted with white snowflakes, and fair skin with soft pink blush on her cheeks and nose. She is looking upward to the right with a gentle, wistful expression, exhaling a visible puff of white breath into the cold air. She wears a thick, textured beige wool coat and a matching chunky scarf wrapped around her neck. In her arms, she clutches a vintage brown leather-bound book with gold detailing on the cover. To the left, a classic black iron street lamp glows with a warm yellow light. The background features blurred European-style brick buildings with snow-covered roofs and distant church spires against a sky transitioning from deep blue to purple and orange. Falling snowflakes are scattered throughout the scene.
A realistic depiction of a giant Japanese police mech lifting a destroyed car on a rainy Tokyo highway.
A cinematic, photorealistic image of a colossal bipedal police robot standing on a wet Tokyo highway at dusk. The robot is constructed from heavy black mechanical joints and white armored plating, with "่ญฆ่ฆๅบ" and "MPD" clearly printed in black text on its chest plates. It has red emergency lights mounted on its shoulders and a complex sensor array head. In its left hand, the robot is lifting a heavily crushed, mangled black sedan off the ground. The scene is chaotic but organized: in the foreground, a Japanese police car with flashing red lights sits on the left, while officers wearing dark uniforms and high-visibility yellow vests labeled "POLICE" direct traffic with glowing batons. Orange traffic cones line the wet asphalt, which reflects the city lights. In the background, green overhead highway signs display directions for "Shutoko Expwy," "Ginza," "Tokyo Sta.," and "Hamamatsucho." A large tow truck with an orange crane arm is visible to the right. The atmosphere is moody and industrial, with rain-slicked surfaces and a backdrop of blurred skyscrapers.
Reverse-engineered prompt to convert a hand-drawn illustration of a WWII fighter plane into a hyper-realistic, cinematic aerial shot.
Using the provided reference image, transform this hand-painted digital artwork into a photorealistic cinematic photograph. Keep the composition of the weathered fighter plane and pilot identical, but render all surfaces with high-fidelity textures: replace the painterly brushstrokes on the fuselage with realistic oxidized metal, peeling paint, and rust. Render the pilot's gear as authentic leather and fabric. Convert the abstract background into a detailed aerial view of a burning landscape below, featuring volumetric smoke plumes, realistic fire glow, and atmospheric motion blur to simulate a high-speed dive.
A prompt for a heartwarming 3D animated cinematic scene of an elderly couple dancing and filming in a cozy vintage hallway, specified as being generated by GPT Image 2 via ChatGPT.
Create a heartwarming 3D animated cinematic scene inside a cozy vintage hallway. An elderly woman with short white hair, round glasses, a mustard-yellow loose top, beige pants, and slippers playfully poses and dances while an elderly man in a light blue shirt and beige pants crouches nearby, recording her with a smartphone. Warm golden indoor lighting, wooden walls, framed artwork, patterned Persian rug, hanging lamp, cozy home atmosphere. The woman changes playful poses naturallyโarms wide, pointing, smiling, raising both handsโwhile the man moves slightly as he films her. Expressive faces, charming comedic timing, smooth natural body movement, consistent character identity, detailed Pixar-like 3D animation, cinematic depth of field, realistic lighting, warm color grading, smooth camera movement, high detail, 4K.
A realistic image of a giant police robot managing a traffic checkpoint on a Tokyo highway with officers and cars.
A hyper-realistic, wide-angle shot of a massive bipedal police robot standing in the middle of a busy Tokyo highway checkpoint. The robot is towering over the cars, featuring a complex mechanical design with black and white armor plating, exposed hydraulic joints, and red emergency lights on its shoulders. It has a rectangular head unit with multiple camera lenses instead of a face. The text '่ญฆ่ฆๅบ MPD' (Metropolitan Police Department) is printed in white on its chest and shoulder plates. One of its large mechanical hands is raised in a 'stop' gesture. In the foreground, human police officers wearing dark blue uniforms and white helmets are directing traffic; one officer holds a glowing red baton. A white vertical sign stands near them with Japanese text reading 'ๆคๅๅฎๆฝไธญ' (Checkpoint in progress). Orange traffic cones line the road. To the right, a black van and other vehicles are stopped for inspection. The background features a clear blue sky, modern city skyscrapers, overhead green highway signs indicating directions to 'Shutoko Expwy', 'Ginza', and 'Ueno', and the iconic Tokyo Skytree visible in the distance.
A detailed prompt for generating an ultra-realistic cinematic dark-fantasy photograph of a handsome young man standing beneath Gothic cathedral arches, featuring dramatic lighting and mysterious atmosphere.
Ultra-realistic cinematic dark-fantasy photograph of a strikingly handsome young man in his early 20s standing alone beneath enormous Gothic cathedral arches. He has thick naturally wavy jet-black hair, strong eyebrows, deep dark-brown eyes, a defined sculpted jawline, subtle natural stubble, realistic skin texture, visible pores, and refined masculine facial features.
He wears an elegant long black tailored coat over a dark high-neck shirt, giving him a mysterious, powerful presence. Towering Gothic arches rise dramatically above him, decorated with intricate stone carvings, weathered columns, and enormous shadowy vaulted ceilings. Sharp beams of golden-white light pierce through dense atmospheric smoke and mist, illuminating parts of his face and shoulders while the rest of the cathedral disappears into deep darkness.
Ancient stone floor slightly wet and reflective, faint dust particles floating through the light, subtle candlelight in the distant background, dramatic volumetric lighting, deep shadows, strong chiaroscuro, gothic architecture, mysterious sacred atmosphere, cinematic composition, realistic proportions, natural expression, highly detailed stone textures, photorealistic skin, HDR, 85mm lens, shallow depth of field, dramatic perspective, dark luxury editorial photography, ultra-detailed, 8K, no women, no text, no watermark, no AI-looking face, vertical 9:16.
A prompt for creating a surreal cinematic photograph splitting a man between 1920s vintage and 2120 futuristic aesthetics using GPT Image 2.
Ultra-realistic cinematic surreal photograph of a strikingly handsome young man in his early 20s standing exactly at the boundary between two centuries, creating a seamless visual split between 1920 and 2120.
He has thick naturally wavy jet-black hair, strong eyebrows, deep dark-brown eyes, a defined sculpted jawline, subtle natural stubble, realistic skin texture, visible pores, and refined masculine facial features.
The LEFT side of the image represents the 1920s: an elegant vintage city street with Art Deco architecture, classic automobiles, old brick buildings, warm amber street lamps, vintage shop signs, pedestrians in 1920s suits and coats, subtle film grain, sepia tones, and authentic period atmosphere. The young man wears a perfectly tailored 1920s three-piece suit, pocket watch, polished leather shoes, and vintage hairstyle details.
The RIGHT side represents the year 2120: a breathtaking futuristic metropolis filled with towering glass-and-metal skyscrapers, holographic advertisements, autonomous flying vehicles, glowing neon architecture, futuristic pedestrians, advanced technology, floating transportation systems, and subtle atmospheric mist. The young man wears an elegant futuristic black tailored suit with sophisticated metallic details and subtle glowing accents.
The center of the composition shows the two eras merging around him, with a luminous temporal distortion, floating clock fragments, particles, and ripples in reality connecting 1920 to 2120. His body subtly transitions between both eras while his face remains identical and perfectly realistic, symbolizing a man caught between past and future.
Epic cinematic composition, symmetrical split-world concept, dramatic perspective, realistic environmental reflections, volumetric lighting, atmospheric depth, physically accurate materials, highly detailed skin, natural facial expression, photorealistic, 8K HDR, ultra-sharp focus, cinematic color grading, 35mm photography, masterpiece, no text, no watermark.
First-person view from inside a fighter jet cockpit looking at another jet banking sharply against a backdrop of motion-blurred clouds and blue sky.
A hyper-realistic, first-person perspective shot from inside a fighter jet cockpit during an intense aerial maneuver. The camera is positioned behind the pilot's gloved hand gripping the control stick in the lower left foreground. Through the curved canopy glass, a second fighter jet is visible flying ahead and slightly above, banking hard to the right with its afterburner glowing bright orange. The scene captures a high-speed turn, creating significant motion blur on the clouds and landscape below. The sky is a vibrant blue filled with streaking white cumulus clouds that warp around the edges due to the speed and G-force. A green digital Heads-Up Display (HUD) overlay is projected onto the canopy glass on the left side, showing flight data such as 'G 7.6', 'M 0.92', and heading numbers like '320'. The lighting is bright daylight, casting realistic reflections on the canopy frame and instruments.
Creates a cinematic night photograph of a man in a vintage red telephone booth during heavy rain, emphasizing moody lighting and realistic details.
Ultra-realistic cinematic night photograph of a strikingly handsome young man in his early 20s sitting inside a vintage red telephone booth on a deserted city street at midnight. He has thick naturally wavy jet-black hair, strong eyebrows, deep dark-brown eyes, a defined sculpted jawline, subtle natural stubble, realistic skin texture, visible pores, and refined masculine facial features. He holds an old black telephone receiver close to his ear, with a mysterious, thoughtful expression as he looks slightly toward the rain-covered glass.
Heavy rain falls outside, droplets streaming down the glass panels, while dense atmospheric fog surrounds the booth and softly obscures the empty street. Wet pavement reflects the warm amber glow of the booth and distant streetlights. Vintage urban architecture fades into the mist in the background. Subtle neon reflections, cinematic rim lighting, soft volumetric light beams, deep shadows, moody midnight-blue atmosphere, realistic reflections on wet surfaces, shallow depth of field, 85mm lens, f/1.4, dramatic film grain, high dynamic range, photorealistic skin, intricate fabric details, sophisticated noir aesthetic, mysterious and emotional atmosphere, premium editorial photography, 8K, ultra-detailed, natural proportions, no text, no watermark, no women.
Generates a dynamic first-person view of a motorcycle race cornering at high speed with motion blur effects.
A high-speed, first-person point-of-view (POV) shot from a racing motorcycle on a professional circuit. The camera is tilted aggressively to the left, simulating a sharp cornering maneuver at speed. In the immediate foreground, the rider's gloved hand (white and red leather) grips the handlebar, with a digital dashboard visible showing '93 km/h' and gear indicator '2'. Ahead on the asphalt track, another racer in full leathers leans deeply into the curve, their bike nearly parallel to the ground. The background features blurred scenery due to motion blur: green trees, distant mountains under a bright blue sky with scattered clouds, and red-and-white curbing along the edge of the track. The lighting is natural daylight, creating realistic reflections on the tarmac and helmets.
A vertical social media thumbnail comparing an impressionist oil painting of two girls with lanterns to its photorealistic AI-generated recreation.
Create a vertical 9:16 social media thumbnail. The background is a hyper-realistic, high-resolution photograph of two young girls with curly brown hair wearing vintage white lace-trimmed dresses standing in a lush garden at twilight. They are holding and decorating glowing pink paper lanterns. Surround them with large white lilies and soft-focus pink roses. In the center, overlay bold sans-serif text: 'AI Made This Painting' in white, followed by 'Real' in yellow on the next line. Below the text, place a smaller rectangular inset image showing the original impressionist oil painting (two girls with lanterns) framed in gold, with a hand-drawn yellow arrow pointing from the painting up to the realistic scene.
A highly detailed photorealistic prompt for generating an action shot of a badminton player smashing a shuttlecock, created using GPT Image 2 (referred to as 'Gpt 2').
Ultra-realistic cinematic sports photograph of a strikingly handsome young male badminton athlete in his early 20s, captured at the peak of a powerful overhead smash. He has thick naturally wavy jet-black hair, strong eyebrows, deep dark-brown eyes, a defined sculpted jawline, subtle natural stubble, realistic skin texture, visible pores, and refined masculine facial features.
He is jumping explosively above the badminton court, body dynamically twisted, one arm fully extended overhead with a professional badminton racket aimed aggressively toward the camera. His expression is intensely focused and determined. A shuttlecock is extremely close to the lens in the foreground, dramatically enlarged with razor-sharp feather details, creating powerful depth and perspective.
Modern indoor badminton arena, polished court floor, subtle net visible in the background, dramatic overhead stadium lights, strong rim lighting, atmospheric haze, realistic shadows, tiny sweat droplets frozen in motion, cinematic motion energy, shallow depth of field, dynamic low-angle perspective, 85mm sports photography aesthetic, ultra-detailed skin and clothing, photorealistic textures, HDR, high contrast, frozen action, premium sports campaign photography.
Large bold โSMASHโ typography subtly integrated into the background, clean athletic editorial design, no logos, no watermark, no other people.
9:16 vertical composition, 8K, photorealistic, cinematic, professional sports advertising campaign, extremely sharp subject and shuttlecock, dramatic depth of field.
A hyper-realistic image of a colossal Japanese police mecha standing in a garage during a rainstorm, with Tokyo landmarks visible in the background.
A cinematic, photorealistic wide shot of a massive bipedal police robot standing inside a large industrial hangar on a rainy day. The robot is the central focus, towering over the scene with a complex mechanical design featuring white armored plating and exposed black hydraulic joints. It has a multi-lens camera array for a head instead of a face, and red warning lights are illuminated on its shoulders. The text "่ญฆ่ฆๅบ MPD" (Metropolitan Police Department) is printed in black on its chest plates and arms. Its feet are wide, treaded platforms resting on the wet concrete floor. To the left, a vertical banner hangs from the ceiling reading "่ญฆ่ฆๅบ METROPOLITAN POLICE DEPARTMENT" with a cherry blossom crest. Below it, a horizontal sign reads "ๅฎๅ
จใชๆฑไบฌใ ๆฌกใฎไธไปฃใธ A SAFER TOKYO FOR THE NEXT GENERATION". In the background, through the open hangar doors, heavy rain falls over a Tokyo cityscape featuring the red lattice structure of the Tokyo Tower and modern skyscrapers under a grey sky. Several police trucks marked "MPD" are parked outside with their headlights on. Two human officers wearing dark uniforms and white helmets stand in the foreground corners, providing scale.
A detailed prompt for generating images in a neo-naive/outsider art style depicting characters fighting clumsily. Explicitly states the generation model is GPT-image2.
[Character A] and [Character B], neo-naรฏve painting ร outsider art ร primitive figurative painting ร children's drawing style character translation.
The two characters are composed of a small number of irregular geometric color blocks, retaining only their strongest identity markers: primary color, head silhouette, hairstyle or ears, eyes, representative clothing color blocks, signature accessories.
The two are fighting intensely but comically, bodies pressed close and entangled. Randomly design actions such as face-grabbing, head-pushing, hugging, pulling, slapping, pinning down, or mutual pouncing based on the characters; hand contact is clear, limbs intersect, center of gravity is unbalanced, making the fighting relationship instantly readable.
Childish and inaccurate human anatomy: slender torsos, stiff straight limbs, inaccurate proportions, tilted heads, exaggerated hands and feet, incorrect perspective. Facial features compressed into a few rough color blocks, expressions angry, shocked, baring teeth, screaming, or aggrieved, possessing an absurd comedic feel.
Rough opaque paint flat coloring, dry brush marks, frayed edges, uneven filling, shaky hand-drawn outlines, local underpainting exposure; body and clothing represented directly by flat color blocks.
Warm gray-white or off-white paper background, large areas of blank space. The two characters are located in the center, entangled with each other forming a compact action mass, the picture focuses on expressing the relationship between the characters.
Like a fight moment quickly drawn from memory by an untrained person: primitive, clumsy, direct, absurd, cute.
Vertical format, extremely small "voxcat" signature in the bottom right corner.
A humorous 3-panel manga-style comic depicting a user's dilemma between the new 'Opus 5.5' AI model and their existing 'Wife GPT', framed as an affair.
Goal: Create a vertical 3-panel comic strip in an anime style, titled "Thoughts After Experiencing Opus 5.5".
Canvas: Vertical layout with three distinct panels stacked on top of each other.
Panel 1 (Top):
- Subject: A young man with messy black hair and starry eyes looks excitedly at a cheerful girl with long orange hair wearing a sunflower-themed dress.
- Text Bubble (Man): "After experiencing Opus 5.5... Wow... so charming....!!"
- Info Box (Right): A yellow decorative box labeled "Claude:" containing the text "Youthful and smart, making life colorful!".
- Background: Bright, sunny field of sunflowers.
Panel 2 (Middle):
- Subject: The same man is now hiding his face in his hands, sweating nervously. Beside him stands an elegant woman with long white hair, horns, and a cold expression.
- Text Bubble (Man): "Oh no, this feels like cheating... Lost the passion of newlyweds..."
- Info Box (Left): A purple decorative box labeled "Wife GPT:" containing the text "Still beautiful and elegant, but a bit cold.".
- Background: Darker, indoor setting with blue curtains.
Panel 3 (Bottom):
- Subject: A scene at a train station platform. The man is peeking around a pillar, blushing, next to the orange-haired girl (Claude). In the background, the white-haired woman (Wife GPT) stands watching them from a distance near a train.
- Signage: A blue sign hanging above reads "Transfer Station ->".
- Text Bubble (Left): "Strict rules at home, can only meet secretly at the transfer station! Keep it down..."
- Text Bubble (Right): "I know everything... watching quietly."
Visual Style: Clean digital illustration, vibrant colors for the first panel, muted tones for the second, realistic lighting for the third.
An action-packed illustration showing Chun-Li delivering a devastating kick to a large green monster while Ryu lies defeated in the foreground.
A high-resolution digital illustration in a vibrant, comic-book style depicting a chaotic street fight. The scene features Chun-Li from Street Fighter on the right side, wearing her iconic blue qipao with gold trim and white boots, executing a powerful high kick that connects directly with the torso of a massive green-skinned monster. The monster resembles Blanka but is significantly larger and more muscular, with wild red hair, sharp claws, and glowing eyes, roaring in pain as it absorbs the impact. In the foreground, lying defeated on the rubble-strewn ground, is Ryu from Street Fighter, wearing his torn white gi, appearing battered and unconscious. The background shows a gritty urban alleyway with brick buildings, fire escapes, and overflowing trash cans under a dramatic, fiery orange and purple sky. Debris and dust explode outward from the point of impact.
Truncated โ view the full README on GitHub.
(top 24 of 26)
1,152 followers ยท starred May 2026
4,596 followers ยท starred May 2026
7,371 followers ยท starred Apr 2026
18 followers ยท starred May 2026