MichalGeyer/plug-and-play
A diffusion model implementation for text-guided image-to-image translation using plug-and-play feature manipulation.
Not currently ranked — collecting fresh signals.
star history
This repository implements the Plug-and-Play Diffusion Features method from CVPR 2023, enabling text-driven image-to-image translation by extracting and re-injecting intermediate features from a pretrained diffusion model. The approach allows users to control image synthesis by manipulating spatial features while preserving the generative model’s overall structure. It builds on Stable Diffusion v1.4 and includes feature extraction pipelines and inference code for image translation tasks.
Frequently asked
- What is MichalGeyer/plug-and-play?
- A diffusion model implementation for text-guided image-to-image translation using plug-and-play feature manipulation.
- Is plug-and-play open source?
- Yes — MichalGeyer/plug-and-play is an open-source project tracked on heatdrop.
- What language is plug-and-play written in?
- MichalGeyer/plug-and-play is primarily written in Python.
- How popular is plug-and-play?
- MichalGeyer/plug-and-play has 1k stars on GitHub.
- Where can I find plug-and-play?
- MichalGeyer/plug-and-play is on GitHub at https://github.com/MichalGeyer/plug-and-play.