Forwarded From Garyの梦呓 (Gary です)

https://github.com/Vision-CAIR/MiniGPT-4
MiniGPT-4，最新发布的类 GPT-4 多模态LLM，基于Vicuna

MiniGPT-4 能提供类似 GPT-4 的图像理解与对话能力，如详细的图像描述生成、从手写草稿创建网站等。还能根据图像创作故事和诗歌，为图像中显示的问题提供解决方案，教用户如何根据食物照片做饭等。#AI #MiniGPT4
From

----------------------
GitHub
GitHub - Vision-CAIR/MiniGPT-4: MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models

MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models - GitHub - Vision-CAIR/MiniGPT-4: MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Langu...

----------------------

via MJJ出征 - Telegram Channel
 
 
Back to Top