StoryMaker：让文生图生成一致角色
GitHub - FireRedTeam/StoryMaker: StoryMaker: Towards consistent characters in text-to-image generation · GitHub
FireRedTeam 开源 StoryMaker，目标是让文生图生成保持一致的角色。项目已发布模型权重、技术报告和训练代码，模型可从 HuggingFace 下载，人脸编码器需手动下载到 models/buffalo_l。其工作受 IP-Adapter 和 InstantID 启发，demo 以 YamerMIX 为基础模型。
正文
当前显示原文，中文全文译文尚未就绪。
FireRedTeam; StoryMaker
Repository navigation
NotificationsYou must be signed in to change notification settings; Fork59 (59); Star720 (720)You must be signed in to star a repository
StoryMaker: Towards consistent characters in text-to-image generation
Repository files navigation
README
Visualization of generated images by StoryMaker. First three rows tell a story about a day in the life of a "office worker" and the last two rows tell a story about a movie of "Before Sunrise".
[2024/11/09] 🔥 We release the training code; [2024/09/20] 🔥 We release the technical report; [2024/09/02] 🔥 We release the model weights
You can directly download the model from Huggingface.
If you cannot access to Huggingface, you can use hf-mirror to download models.
For face encoder, you need to manually download via this URL to models/buffalo_l as the default link is invalid. Once you have prepared all models, the folder tree should be like:
Usage
Then, you can customized your own images
Acknowledgements
Our work is highly inspired by IP-Adapter and InstantID. Thanks for their great works!; Thanks Yamer for developing YamerMIX, we use it as base model in our demo
StoryMaker: Towards consistent characters in text-to-image generation