NICESONY/SW-University-Generative-AI-Experience-Contest

"Implementation of a Generative AI Model for Converting Government-Issued Disaster Alerts (Text Information) into Image Information"

stars

commits

Python

primary language

Oct 24, 2024

updated

README

SW-University-Generative-AI-Experience-Contest

SW-Centered University Generative AI Experience Contest

문제점 제시

생성형 AI를 이용한 해결방안

결과물 출력 로직

Chat gpt 4 API 사용해서 입력 text에 대해서 해당 장소와 특징 추출 -> Bing APi를 이용해서 해당 장소 검색 후 -> 이미지 저장 -> 이미지에 있는 text 정보 추출을 위한 ocr -> 이미지를 바탕으로 생성형 모델(stable-video-duffusion pretrained model, AnimateDiff, i2vgen)영상생성

파일명 : 입력 프롭포트 (해당입력 프롭포트를 영어로 변환 후 chat gpt 4 API를 이용해서 입력)

결과물(1)

funny video of a grandma with a perm__84

결과물(2)

a little girl with long hair in a yellow hat__79

결과물(3)

dong-yeong as an old man with glasses, white hair, and a cane__31

Contributors

NICESONY

31 commits

Similar repos

NICESONY/2024_kongju_Generative_Competition

2024_kongju_Generative_Competition

same org

kairess/Chat2Image-Creator

Generate a image through chat using ChatGPT API and StableDiffusion. 챗봇을 사용하여 채팅으로 상상하게하고 그림으로 그리기.

VITA-Group/4DGen

"4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency", Yuyang Yin*, Dejia Xu*,…

254

zeinhasan/Vision-Language-Model-Image-to-Text-Generation

Vision Language Model - Image to Text Generation

langgptai/Awesome-Multimodal-Prompts

Prompts of GPT-4V & DALL-E3 to full utilize the multi-modal ability. GPT4V Prompts, DALL-E3…

288

misshimichka/CV-T-Bank-Sirius-ML-2024

Решение отборочного этапа на программу от Т-Банка и Университета Сириус

Pushkar1853/Cover-Generator

Application of OpenAI tools such as Whisper, DALL-E, and ChatGPT to generate album covers from audio

kekwdaway-cyber/ai-image-to-video

Languages

Python

39.6%

HTML

29.9%

CSS

21.3%

JavaScript

9.2%

NICESONY/SW-University-Generative-AI-Experience-Contest

"Implementation of a Generative AI Model for Converting Government-Issued Disaster Alerts (Text Information) into Image Information"

stars

commits

Python

primary language

Oct 24, 2024

updated

README

SW-University-Generative-AI-Experience-Contest

SW-Centered University Generative AI Experience Contest

문제점 제시

생성형 AI를 이용한 해결방안

결과물 출력 로직

Chat gpt 4 API 사용해서 입력 text에 대해서 해당 장소와 특징 추출 -> Bing APi를 이용해서 해당 장소 검색 후 -> 이미지 저장 -> 이미지에 있는 text 정보 추출을 위한 ocr -> 이미지를 바탕으로 생성형 모델(stable-video-duffusion pretrained model, AnimateDiff, i2vgen)영상생성

파일명 : 입력 프롭포트 (해당입력 프롭포트를 영어로 변환 후 chat gpt 4 API를 이용해서 입력)

결과물(1)

funny video of a grandma with a perm__84

결과물(2)

a little girl with long hair in a yellow hat__79

결과물(3)

dong-yeong as an old man with glasses, white hair, and a cane__31

Similar repos

NICESONY/2024_kongju_Generative_Competition

2024_kongju_Generative_Competition

same org

kairess/Chat2Image-Creator

Generate a image through chat using ChatGPT API and StableDiffusion. 챗봇을 사용하여 채팅으로 상상하게하고 그림으로 그리기.

VITA-Group/4DGen

"4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency", Yuyang Yin*, Dejia Xu*,…

254

zeinhasan/Vision-Language-Model-Image-to-Text-Generation

Vision Language Model - Image to Text Generation

langgptai/Awesome-Multimodal-Prompts

Prompts of GPT-4V & DALL-E3 to full utilize the multi-modal ability. GPT4V Prompts, DALL-E3…

288

misshimichka/CV-T-Bank-Sirius-ML-2024

Решение отборочного этапа на программу от Т-Банка и Университета Сириус

Pushkar1853/Cover-Generator

Application of OpenAI tools such as Whisper, DALL-E, and ChatGPT to generate album covers from audio

kekwdaway-cyber/ai-image-to-video

Contributors

NICESONY

31 commits

Languages

Python

39.6%

HTML

29.9%

CSS

21.3%

JavaScript

9.2%