AI Rank
EN
← 开源
balazik

ComfyUI-PuLID-Flux

PuLID-Flux ComfyUI implementation

ApplicationsContent creationPython
在 GitHub 打开
增长势头
+124 小时新增 Star+0.1%
725
Star
60
Fork
+2
本周
2
贡献者
创建于 2024-10-01 · 更新于 2026-10-16 · 今日第 6375 名
主要开发者
BadisGbalazik

balazik/ComfyUI-PuLID-Flux 排名第 6,375，有 725 个星标。

同类别比较

balazik/ComfyUI-PuLID-Flux 排名第 6,375，此处有 8 个同类条目；EvilBT/ComfyUI_SLK_joy_caption_two 排名第 6,374。

同类别比较
名称排名指标
nateherkai/token-dashboard6,366
语言:
Python
星标数:
729
分叉数:
197
简介:
See where Claude Code is burning tokens - turn raw JSONL transcripts into local cost analytics, hotspot views, and session-level usage insight.
bkingfilm/lapian-notes6,368
语言:
TypeScript
星标数:
728
分叉数:
74
简介:
AI 辅助的电影拉片工具：AI 拆出剧情泳道时间轴、结构树、情绪曲线，边播边写拉片笔记，免费开源全本地 | AI-assisted film breakdown notebook: story-lane timeline, structure tree, emotion curve. Free, open source, fully local.
ShayneP/local-voice-ai6,372
语言:
Python
星标数:
726
分叉数:
217
简介:
Local voice AI powered by llama-cpp, Kokoro, Nemotron STT, and LiveKit.
EvilBT/ComfyUI_SLK_joy_caption_two6,374
语言:
Python
星标数:
725
分叉数:
45
简介:
ComfyUI Node
sylearn/AIUsage6,377
语言:
Swift
星标数:
725
分叉数:
55
AITabby/codexsplit6,379
语言:
TypeScript
星标数:
723
分叉数:
57
简介:
CodexSplit - local Codex Desktop control center, provider gateway, and model routing workspace
codefuse-ai/Test-Agent6,381
语言:
Python
星标数:
723
分叉数:
92
简介:
Agent that empowers software testing with LLMs; industrial-first in China
homanp/infinite-monitor6,383
语言:
TypeScript
星标数:
722
分叉数:
96
简介:
Monitor anything in real time
关键参数与规格
关键参数与规格
参数值
语言Python
类别Applications
子类别Content creation
关键词Image production
星标数725
分叉数60
贡献者2
创建日期2024-10-01
更新日期2026-10-16
1 天星标数1
7 天星标数2
排名6,375
上次排名6,553
排名变化178
7 天星标排名8,567
上次 7 天星标排名10,880
7 天星标排名变化2,313
总星标排名14,456
上次总星标排名14,448
总星标排名变化-8
README 摘录

PuLID-Flux for ComfyUI PuLID-Flux ComfyUI implementation (Alpha version) :new: Version Updates V0. 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 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 or model version of Flux1-dev

(the 8e5m2 returns blurry backgrounds). In the 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 Install all the packages listed in the file 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. :wink: You need one of the mentioned models. Download the model into , clip and encoder into , VAE into . 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. models exception**), download this EVA-CLIP model manually

, put the file to your and restart ComfyUI. dependency needs to be installed, the models are downloaded at first use. Finally you need InsightFace with AntelopeV2, the unzipped models should be placed in . Known issues ApplyPulidFlux doesn't work on HW with CUDA compute < v8. 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 :wink: ).

常见问题

记录了多少星标和分叉？

balazik/ComfyUI-PuLID-Flux 有 725 个星标和 60 个分叉。

仓库排名是多少？

balazik/ComfyUI-PuLID-Flux 排名第 6,375。

记录的语言和类别是什么？

balazik/ComfyUI-PuLID-Flux 有 725 个星标，语言为 Python，类别为 Applications。

哪个仓库排名最接近？

balazik/ComfyUI-PuLID-Flux 与 EvilBT/ComfyUI_SLK_joy_caption_two 比较，后者排名第 6,374，有 725 个星标。

README

PuLID-Flux for ComfyUI

PuLID-Flux ComfyUI implementation (Alpha version)

:new: 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.txt file 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. :wink:

  • You need one of the mentioned Flux.1-dev models. Download the model into ComfyUI/models/unet, clip and encoder into ComfyUI/models/clip, VAE into ComfyUI/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.

  • facexlib dependency 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 :wink: ).

排名相邻
同类项目