News: Now you can try our ReplaceAnything v1.0 on HuggingFace space ( in English ) . Enjoy it and have fun!
News: Now you can try our ReplaceAnything v1.0 on ModelScope 魔搭 ( in Chinese ) . Enjoy it and have fun!
Feel free to share your interesting results with us. If you have any questions or suggestions, don’t hesitate to leave a message in issues.
To Do Lists:
- Paper release
- Code release
- Replace Anything
- Replace Anything Blog
Note: Please don’t forget to give us a star if you like this project. Thanks! 😜
Abstract:
Recently, Artificial Intelligence Graphic Computing (AIGC) techniques have garnered substantial attention. These techniques exhibit formidable capabilities in fields such as image editing and image generation. We’ve identified a notable but challenging demand for generating new content while stringently maintaining the identity of user-specified objects. To tackle this demand, we have proposed the ‘ReplaceAnything’ framework. This framework finds utility across numerous scenarios like human replacement, clothing replacement, and background replacement, among other applications. We also furnish several use-case examples pertaining to this framework.
Clothing replacement (masked region is strictly retained):
Background replacement for ID photo and family photo (masked region is strictly retained):
Human replacement (masked region is strictly retained):
Background replacement (masked region is strictly retained):
