PuLID (NeurIPS 2024)
📖 PuLID: Pure and Lightning ID Customization via Contrastive Alignment
Zinan Guo*, Yanze Wu*✝, Zhuowei Chen, Lang Chen, Peng Zhang, Qian He
(*Equal Contribution, ✝Corresponding Author)
ByteDance Inc
🔥🔥 We are excited to share DreamO, a unified image customization framework that supports ID, IP, Try-On, and style tasks. Check it out and see what it can do! 🔥🔥
🚩 Updates
- 2024.10.31: 🔥 We are happy to release our latest models, PuLID-v1.1 and PuLID-FLUX-v0.9.1. See more in Model Zoo and pulid v1.1 model. We also update a new revision for the arXiv paper, which includes more results, details, and analysis, please check it out.
- 2024.09.26: 🎉 PuLID accepted by NeurIPS 2024
- 2024.09.12: We're thrilled to announce the release of the PuLID-FLUX-v0.9.0 model. Enjoy exploring its capabilities! 😊 Learn more about this model
- 2024.05.23: share the preview of our upcoming v1.1 model, please stay tuned
- 2024.05.01: release v1 codes&models, also the 🤗HuggingFace Demo
- 2024.04.25: release arXiv paper.
PuLID for FLUX
Please check the doc and demo of PuLID-FLUX here.
updates
Below results are generated with PuLID-FLUX.
Examples
Images generated with our PuLID
Applications
pulid_demo.mp4
🏰 Model Zoo
| Version | Base Model | Description |
|---|---|---|
| PuLID-v1 | SDXL | Paper model. |
| PuLID-v1.1 | SDXL | Compared to PuLID-v1, better compatibility, editability, facial naturalness, and similarity. |
| PuLID-FLUX-v0.9.0 | FLUX | Our first version for PuLID-FLUX, better prompt-following and image quality (since FLUX is more powerful than SDXL). But ID fidelity is not high enough for some male inputs |
| PuLID-FLUX-v0.9.1 | FLUX | Compared to PuLID-FLUX-v0.9.0, better ID fidelity. From the quantitative metric of ID similarity, the improvement is about 5 percentage points. Meanwhile, the editability remains similar as before. |
🔧 Dependencies and Installation
- Python >= 3.9 (Recommend to use Anaconda or Miniconda)
- PyTorch >= 2.0 if you don't need flux-dev-fp8, otherwise PyTorch >= 2.4.1
# clone PuLID repo git clone https://github.com/ToTheBeginning/PuLID.git cd PuLID # create conda env conda create --name pulid python=3.10 # activate env conda activate pulid # Install dependent packages # 1. if you don't need flux-fp8, e.g., you are using xl or flux-bf16, install the following requirements.txt pip install -r requirements.txt # 2. if you need flux-fp8 (to put flux on consumer-grade gpu), install the following requirements_fp8.txt pip install -r requirements_fp8.txt
⚡ Quick Inference
Local Gradio Demo
# for v1 version python app.py # for v1.1 version python app_v1.1.py --base BASE_MODEL Usage: -base: can be RunDiffusion/Juggernaut-XL-v9 or Lykon/dreamshaper-xl-lightning
Online HuggingFace Demo
Thanks for the GPU grant from HuggingFace team, you can try PuLID HF demo in
- https://huggingface.co/spaces/yanze/PuLID for SDXL
- https://huggingface.co/spaces/yanze/PuLID-FLUX for FLUX
📎 Related Resources
Following are some third-party implementations of PuLID we have found in the Internet. We appreciate the efforts of the respective developers for making PuLID accessible to a wider audience. If there are any PuLID based resources and applications that we have not mentioned here, please let us know, and we will include them in this list.
Online Demo
- Colab: https://github.com/camenduru/PuLID-jupyter provided by camenduru
- Replicate (PuLID): https://replicate.com/zsxkib/pulid provided by zsxkib
- Replicate (PuLID-FLUX): https://replicate.com/zsxkib/flux-pulid provided by zsxkib
ComfyUI
- https://github.com/cubiq/PuLID_ComfyUI provided by cubiq, native ComfyUI implementation
- https://github.com/ZHO-ZHO-ZHO/ComfyUI-PuLID-ZHO provided by ZHO, diffusers-based implementation
WebUI
- SD.Next Implementation provided by vladmandic
- Mikubill/sd-webui-controlnet#2838 provided by huchenlei
Other Applications
- PuLID-FLUX multi-person generation with Regional-Prompting-FLUX, provided by Anthony
Disclaimer
This project strives to impact the domain of AI-driven image generation positively. Users are granted the freedom to create images using this tool, but they are expected to comply with local laws and utilize it responsibly. The developers do not assume any responsibility for potential misuse by users.
Citation
If PuLID is helpful, please help to ⭐ the repo.
If you find this project useful for your research, please consider citing our paper:
@InProceedings{guo2024pulid, title={PuLID: Pure and Lightning ID Customization via Contrastive Alignment}, author={Guo, Zinan and Wu, Yanze and Chen, Zhuowei and Chen, Lang and Zhang, Peng and He, Qian}, booktitle={Advances in Neural Information Processing Systems}, year={2024} }
Acknowledgement
We would like to acknowledge our core team members, Pengze Zhang and Songtao Zhao, for their significant contributions to the continued development and maintenance of the PuLID model. Although they were not listed as authors on the first version of this paper, their efforts played a crucial role in enhancing the model.
📧 Contact
If you have any comments or questions, please open a new issue or feel free to contact Yanze Wu and Zinan Guo.