jaidaken
f09734b0ee
Includes 30 custom nodes committed directly, 7 Civitai-exclusive loras stored via Git LFS, and a setup script that installs all dependencies and downloads HuggingFace-hosted models on vast.ai. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
4.1 KiB
PuLID-Flux for ComfyUI
PuLID-Flux ComfyUI implementation (Alpha version)
🆕 Version Updates
- V0.1.0: Working node with weight, start_at, end_at support (attn_mask not working)
Notes
This project was heavily inspired by cubiq/PuLID_ComfyUI. It is just a prototype that uses some convenient model hacks for the encoder section. I wanted to test the model’s quality before reimplementing it in a more formal manner. For better results I recommend the 16bit or 8bit GGUF model version of Flux1-dev (the 8e5m2 returns blurry backgrounds).
In the examples directory you'll find some basic workflows.
Supported Flux models:
32bit/16bit (~22GB VRAM): model, encoder
8bit gguf (~12GB VRAM): model, encoder
8 bit FP8 e5m2 (~12GB VRAM): model, encoder
8 bit FP8 e4m3fn (~12GB VRAM): model, encoder
Clip and VAE (for all models): clip, vae
For GGUF models you will need to install ComfyUI-GGUF
Installation
- Install this repo into
ComfyUI/custom_nodes
git clone https://github.com/balazik/ComfyUI-PuLID-Flux.git
-
Install all the packages listed in the
requirements.txtfile into the Python environment where you run ComfyUI. I prefer not to use automatic installation scripts, as I dislike when scripts install software without my knowledge. 😉 -
You need one of the mentioned
Flux.1-devmodels. Download the model intoComfyUI/models/unet, clip and encoder intoComfyUI/models/clip, VAE intoComfyUI/models/vae. -
PuLID Flux pre-trained model goes in
ComfyUI/models/pulid/. -
The EVA CLIP is EVA02-CLIP-L-14-336, should be downloaded automatically (will be located in the huggingface directory). If for some reason the auto-download fails (and you get face_analysis.py, init assert 'detection' in self.models exception), download this EVA-CLIP model manually, put the file to your
ComfyUI/models/clipand restart ComfyUI. -
facexlibdependency needs to be installed, the models are downloaded at first use. -
Finally you need InsightFace with AntelopeV2, the unzipped models should be placed in
ComfyUI/models/insightface/models/antelopev2.
Known issues
- ApplyPulidFlux doesn't work on HW with CUDA compute < v8.0, (when Flux FP8 it needs bfloat16).
- When the ApplyPulidFlux node is disconnected after first run, the Flux model is still influenced by the node.
- ApplyPulidFlux attn_mask is not working (in progress).
Credits
ComfyUI/ComfyUI - A powerful and modular stable diffusion GUI.
PuLID for Flux - tuning-free ID customization solution for FLUX.1-dev
cubiq PuLID_ComfyUI - PuLID ComfyUI native implementation (Thanks for the awesome work what you do Matteo 😉 ).