#123 · Primary category: Image Generation

ComfyUI-PhotoMaker-ZHO

comfyui stable-diffusion

Unofficial implementation of PhotoMaker for ComfyUI

Project last updated:05/22/24

GitHub Stars

814

Forks

40

Contributors

2

License

GPL-3.0

Why we included this project

PhotoMaker's trick is keeping one person's face recognizable while the rest of the image changes, and this ComfyUI port puts that inside the node graph instead of a separate app. You feed it an SDXL base model plus the PhotoMaker adapter, either downloaded from Hugging Face or loaded from local files, and give it one or several reference photos. From there a prompt and the built-in styler shape the output, and LoRA support with adjustable weights plus multi-batch runs make it handy for portrait work where the same character has to show up in different poses and settings. If you already live in ComfyUI, it behaves like a normal set of nodes, so there's no separate pipeline to learn.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category