#126 · Primary category: Image Generation
ComfyUI-PuLID-Flux
PuLID-Flux ComfyUI implementation
Project last updated:10/03/24
GitHub Stars
721
Forks
59
Contributors
3
License
Apache-2.0
Why we included this project
ComfyUI users who want to keep a person's face consistent across a batch of generations can wire the PuLID-Flux identity model into their existing graphs with this custom node. It exposes controls for the influence weight and for when that influence starts and ends during sampling, so you can tune how strongly the reference face drives the output. The README is upfront about the alpha status and the prototype-quality encoder hacks, which is useful when you're weighing whether to build a production pipeline on it. It also spells out which Flux.1-dev model variants work best, including 16-bit and 8-bit GGUF options for lower VRAM setups, and flags the extra ComfyUI-GGUF dependency you'll need. For artists and developers already comfortable with ComfyUI, this is a straightforward way to test face-consistent generation without leaving the tool you know.
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.