#97 · Primary category: Image Generation
PuLID_ComfyUI
PuLID native implementation for ComfyUI
Project last updated:04/14/25
GitHub Stars
910
Forks
65
Contributors
7
License
Apache-2.0
Why we included this project
PuLID transfers a face's likeness from a reference photo into generated images, and this project wraps it as a native ComfyUI node set. The standard node and an advanced variant expose a fidelity slider, projection options, and a method parameter, so you can push resemblance closer to the reference or give the checkpoint more stylistic freedom. Worth flagging before you build on it: the code is beta and the repo has moved to maintenance-only mode, and output quality depends a lot on feeding it a clean, sharp reference image, with some experimenting around samplers and CFG. Within those limits it tracks the official Gradio demo closely, and anyone already running IPAdapter workflows can drop it in alongside them.
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
stable-diffusion-webui
Stable Diffusion web UI
ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
upscayl
🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.
InvokeAI
InvokeAI is a leading open-source creative engine for Stable Diffusion, offering an industry-leading web UI for generating and editing visual media.