ComfyUI reference implementation for a/PhotoMaker models. NOTE: PhotoMaker V2 is supported.
ComfyUI implementation for PhotoMaker.
PhotoMaker implementation that follows the ComfyUI way of doing things. The code is memory efficient, fast, and shouldn't break with Comfy updates.
<div align="center"> <img width="1261" alt="example workflow" src="https://github.com/user-attachments/assets/0b05d24f-ec3a-4be7-9e93-9169c66c65f5"> </div>insightface
.custom_nodes
by running the following commands in a terminal:
cd ComfyUI/custom_nodes
git clone https://github.com/shiimizu/ComfyUI-PhotoMaker-Plus.git
photomaker
folder in your models
folder such as ComfyUI/models/photomaker
.Plus
versionCLIPImageProcessor
like in the original code.PhotoMakerStyles
and PrepImagesForClipVisionFromPath
2024-09-01
PhotoMakerLoraLoaderPlus
node was added. Use that to load the LoRA.2024-07-26
PhotoMakerLoaderPlus
and PhotoMakerInsightFaceLoader
nodes.2024-01-24
PhotoMakerEncode
node is also now PhotoMakerEncodePlus
.2024-01-21
ref_images_path
input. Added a PrepImagesForClipVisionFromPath
node.2024-01-18
@article{li2023photomaker,
title={PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding},
author={Li, Zhen and Cao, Mingdeng and Wang, Xintao and Qi, Zhongang and Cheng, Ming-Ming and Shan, Ying},
booktitle={arXiv preprint arxiv:2312.04461},
year={2023}
}