prithivMLmods/Canopus-LoRA-Flux-UltraRealism-2.0

Model

Canopus-LoRA-Flux-UltraRealism-2.0

130

37 commits

1 linked in READMEs

updated Nov 23, 2024

See the code

README

Canopus-LoRA-Flux-UltraRealism-2.0

The new versions available: https://huggingface.co/prithivMLmods/Ton618-Epic-Realism-Flux-LoRA
Also Available in Flux LoRA DLC: https://huggingface.co/spaces/prithivMLmods/FLUX-LoRA-DLC

The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.

Model description

prithivMLmods/Canopus-LoRA-Flux-UltraRealism-2.0

Image Processing Parameters

Parameter	Value	Parameter	Value
LR Scheduler	constant	Noise Offset	0.03
Optimizer	AdamW	Multires Noise Discount	0.1
Network Dim	64	Multires Noise Iterations	10
Network Alpha	32	Repeat & Steps	30 & 3.8K+
Epoch	20	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 70 [ Hi-RES ] & More ...............

🚀New Version Available Here🚀

Here's a table summarizing the relevant information about the Flux-Super-Realism-LoRA model on Hugging Face:

Feature	Details
Model Name	`Flux-Super-Realism-LoRA`
Repository	strangerzonehf/Flux-Super-Realism-LoRA
Author	`strangerzonehf`
Description	Super-realism LoRA model designed to produce high-quality, hyper-realistic images using LoRA fine-tuning techniques. This model can generate lifelike textures, lighting, and intricate details.
Model Type	LoRA (Low-Rank Adaptation for Transformers)
Use Cases	- Photorealistic image generation - High-fidelity art - Texture detailing and enhancement
Primary Language	Not applicable (model is image-based)
Base Model	Model used as the foundation for LoRA fine-tuning (may vary per implementation)
License	Refer to Hugging Face model page for specific licensing information.
Tags	super-realism, LoRA, high-fidelity, hyper-realistic
Usage	This model is typically used with tools like Hugging Face's `Diffusers` or other libraries supporting LoRA fine-tuning for enhanced realism in image generation.
Pipeline	Use in `StableDiffusionPipeline` or compatible image generation pipelines.

Image Compare DLC.

Canopus-LoRA-Flux-UltraRealism-2.0

Image	Description
Image 1	Portrait of an attractive woman: Late twenties, light brown hair, wearing a yellow sweater, looking directly at the camera. Standing outdoors near trees. Aspect ratio: 128:85. Style: Raw
Image 2	Headshot of a handsome young man: Dark gray sweater with buttons and shawl collar, brown hair, short beard. Serious expression on a black background, soft studio lighting. Aspect ratio: 85:128. Style: Raw
Image 3	Fashion photo: Model in a white bodysuit and beige trench coat, posing with hands on head in front of a train station at sunset. High resolution, 35mm lens, f/22, natural lighting. Aspect ratio: 85:128. Style: Raw
Image 4	Rustic portrait: Woman with fair skin and natural, wavy hair in soft curls. Wearing a red and navy plaid shirt with a white undershirt, sleeves rolled up. Leaning against a weathered blue door frame with a contemplative expression.

Other Sample

Image	Prompt
	Photography, envision an image steeped in urban nostalgia, a portrait of youthful ennui set against the backdrop of a timeless cityscape. A woman lounges languidly on an old, industrial metal staircase, her pose exuding a sense of introspection and quiet defiance. A plain black t-shirt, snug and slightly worn, subtly contours to her frame. Her black jeans embrace streetwear chic. Classic black and white shoes strike a stark contrast with the rusted steps, while her casual lace-up style hints at a readiness to spring into motion. Her hair is a cascade of dark waves, partly obscured by a black cap, its brim peeking out with a hint of youthful edge. Around her, the weathered brick walls whisper stories of the city's past, the windows reflecting fragmented visions of urban life. There's an air of contemplation as she rests her head on one arm, gazing distantly, perhaps lost in thought or simply enjoying a moment of solitude in the urban maze. Used camera: Sony α9 II with Sony FE 100-400mm f/4.5-5.6 GM OSS lens, emulating a high-contrast, ultra realistic style. --ar 9:16 --style raw --stylize 750

Image

Prompt

Photography, envision an image steeped in urban nostalgia, a portrait of youthful ennui set against the backdrop of a timeless cityscape. A woman lounges languidly on an old, industrial metal staircase, her pose exuding a sense of introspection and quiet defiance. A plain black t-shirt, snug and slightly worn, subtly contours to her frame. Her black jeans embrace streetwear chic. Classic black and white shoes strike a stark contrast with the rusted steps, while her casual lace-up style hints at a readiness to spring into motion. Her hair is a cascade of dark waves, partly obscured by a black cap, its brim peeking out with a hint of youthful edge. Around her, the weathered brick walls whisper stories of the city's past, the windows reflecting fragmented visions of urban life. There's an air of contemplation as she rests her head on one arm, gazing distantly, perhaps lost in thought or simply enjoying a moment of solitude in the urban maze. Used camera: Sony α9 II with Sony FE 100-400mm f/4.5-5.6 GM OSS lens, emulating a high-contrast, ultra realistic style. --ar 9:16 --style raw --stylize 750

Trigger words

You should use Ultra realistic to trigger the image generation.

Other Versions

Here’s a table format for the Hugging Face model "prithivMLmods/Canopus-LoRA-Flux-FaceRealism":

Attribute	Details
Model Name	Canopus-LoRA-Flux-FaceRealism
Model ID	`prithivMLmods/Canopus-LoRA-Flux-FaceRealism`
Hugging Face URL	Canopus-LoRA-Flux-FaceRealism
Model Type	LoRA (Low-Rank Adaptation)
Primary Use Case	Face Realism image generation
Supported Framework	Hugging Face Diffusers
Data Type	`bfloat16`, `fp16`, `float32`
Compatible Models	Stable Diffusion, Flux models
Model Author	`prithivMLmods`
LoRA Technique	LoRA for image style transfer with a focus on generating realistic faces
Model Version	Latest
License	Open-Access
Tags	LoRA, Face Realism, Flux, Image Generation

Setting Up

import torch
from pipelines import DiffusionPipeline

base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)

lora_repo = "prithivMLmods/Canopus-LoRA-Flux-UltraRealism-2.0"
trigger_word = "Ultra realistic"  
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)

App File Structure

/project-root/

│ ├── .gitattributes
├── README.md
├── app.py
├── pythonproject.py

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab . . .🤗: https://hf.co/prithivmlmods

diffusers

diffusion

face

flux-dev

hi-res

lora

photorealism

realism

text-to-image

ultra

UltraRealism

Contributors

prithivMLmods

37 commits

Similar repos

prithivMLmods/Canopus-LoRA-Flux-FaceRealism

Model

Canopus-LoRA-Flux-FaceRealism

strangerzonehf/Flux-Super-Realism-LoRA

Model

Model description for super realism engine

272

prithivMLmods/Flux-Realism-FineDetailed

Model

Flux-Realism-FineDetailed - B+ 20

Stranger-Zone/Flux-Super-Realism-LoRA

Realism Adapter for Flux.1 Dev

prithivMLmods/Flux.1-Dev-LoRA-HDR-Realism

Model

Flux.1-Dev-LoRA-HDR-Realism [ Experimental Version ]

strangerzonehf/Flux-Midjourney-Mix2-LoRA

Model

Model description for MJv6 Mix2 LoRA

561

Shakker-Labs/FLUX.1-dev-LoRA-AntiBlur

Model

FLUX.1-dev-LoRA-AntiBlur

238

ECNU-CILab/ArtAug-lora-FLUX.1dev-v1

Model

FLUX Aesthetics Enhancement LoRA

Linked in READMEs

Stranger-Zone/Flux-Super-Realism-LoRA

Realism Adapter for Flux.1 Dev

README badge

prithivMLmods/Canopus-LoRA-Flux-UltraRealism-2.0

Model

Canopus-LoRA-Flux-UltraRealism-2.0

130

37 commits

1 linked in READMEs

updated Nov 23, 2024

See the code

README

Canopus-LoRA-Flux-UltraRealism-2.0

The new versions available: https://huggingface.co/prithivMLmods/Ton618-Epic-Realism-Flux-LoRA
Also Available in Flux LoRA DLC: https://huggingface.co/spaces/prithivMLmods/FLUX-LoRA-DLC

The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.

Model description

prithivMLmods/Canopus-LoRA-Flux-UltraRealism-2.0

Image Processing Parameters

Parameter	Value	Parameter	Value
LR Scheduler	constant	Noise Offset	0.03
Optimizer	AdamW	Multires Noise Discount	0.1
Network Dim	64	Multires Noise Iterations	10
Network Alpha	32	Repeat & Steps	30 & 3.8K+
Epoch	20	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 70 [ Hi-RES ] & More ...............

🚀New Version Available Here🚀

Here's a table summarizing the relevant information about the Flux-Super-Realism-LoRA model on Hugging Face:

Feature	Details
Model Name	`Flux-Super-Realism-LoRA`
Repository	strangerzonehf/Flux-Super-Realism-LoRA
Author	`strangerzonehf`
Description	Super-realism LoRA model designed to produce high-quality, hyper-realistic images using LoRA fine-tuning techniques. This model can generate lifelike textures, lighting, and intricate details.
Model Type	LoRA (Low-Rank Adaptation for Transformers)
Use Cases	- Photorealistic image generation - High-fidelity art - Texture detailing and enhancement
Primary Language	Not applicable (model is image-based)
Base Model	Model used as the foundation for LoRA fine-tuning (may vary per implementation)
License	Refer to Hugging Face model page for specific licensing information.
Tags	super-realism, LoRA, high-fidelity, hyper-realistic
Usage	This model is typically used with tools like Hugging Face's `Diffusers` or other libraries supporting LoRA fine-tuning for enhanced realism in image generation.
Pipeline	Use in `StableDiffusionPipeline` or compatible image generation pipelines.

Image Compare DLC.

Canopus-LoRA-Flux-UltraRealism-2.0

Image	Description
Image 1	Portrait of an attractive woman: Late twenties, light brown hair, wearing a yellow sweater, looking directly at the camera. Standing outdoors near trees. Aspect ratio: 128:85. Style: Raw
Image 2	Headshot of a handsome young man: Dark gray sweater with buttons and shawl collar, brown hair, short beard. Serious expression on a black background, soft studio lighting. Aspect ratio: 85:128. Style: Raw
Image 3	Fashion photo: Model in a white bodysuit and beige trench coat, posing with hands on head in front of a train station at sunset. High resolution, 35mm lens, f/22, natural lighting. Aspect ratio: 85:128. Style: Raw
Image 4	Rustic portrait: Woman with fair skin and natural, wavy hair in soft curls. Wearing a red and navy plaid shirt with a white undershirt, sleeves rolled up. Leaning against a weathered blue door frame with a contemplative expression.

Other Sample

Image	Prompt
	Photography, envision an image steeped in urban nostalgia, a portrait of youthful ennui set against the backdrop of a timeless cityscape. A woman lounges languidly on an old, industrial metal staircase, her pose exuding a sense of introspection and quiet defiance. A plain black t-shirt, snug and slightly worn, subtly contours to her frame. Her black jeans embrace streetwear chic. Classic black and white shoes strike a stark contrast with the rusted steps, while her casual lace-up style hints at a readiness to spring into motion. Her hair is a cascade of dark waves, partly obscured by a black cap, its brim peeking out with a hint of youthful edge. Around her, the weathered brick walls whisper stories of the city's past, the windows reflecting fragmented visions of urban life. There's an air of contemplation as she rests her head on one arm, gazing distantly, perhaps lost in thought or simply enjoying a moment of solitude in the urban maze. Used camera: Sony α9 II with Sony FE 100-400mm f/4.5-5.6 GM OSS lens, emulating a high-contrast, ultra realistic style. --ar 9:16 --style raw --stylize 750

Image

Prompt

Trigger words

You should use Ultra realistic to trigger the image generation.

Other Versions

Here’s a table format for the Hugging Face model "prithivMLmods/Canopus-LoRA-Flux-FaceRealism":

Attribute	Details
Model Name	Canopus-LoRA-Flux-FaceRealism
Model ID	`prithivMLmods/Canopus-LoRA-Flux-FaceRealism`
Hugging Face URL	Canopus-LoRA-Flux-FaceRealism
Model Type	LoRA (Low-Rank Adaptation)
Primary Use Case	Face Realism image generation
Supported Framework	Hugging Face Diffusers
Data Type	`bfloat16`, `fp16`, `float32`
Compatible Models	Stable Diffusion, Flux models
Model Author	`prithivMLmods`
LoRA Technique	LoRA for image style transfer with a focus on generating realistic faces
Model Version	Latest
License	Open-Access
Tags	LoRA, Face Realism, Flux, Image Generation

Setting Up

import torch
from pipelines import DiffusionPipeline

base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)

lora_repo = "prithivMLmods/Canopus-LoRA-Flux-UltraRealism-2.0"
trigger_word = "Ultra realistic"  
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)