PhotoMaker V2: Improved ID Fidelity and Better Controllability than PhotoMaker V1

Official 🤗 Gradio demo for PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding.
How to use PhotoMaker V2 can be found in 🎬 this video 🎬.

For previous version of PhotoMaker, you could use our original gradio demos PhotoMaker and PhotoMaker-Style.
❗️❗️❗️[Important] Personalization steps:
1️⃣ Upload images of someone you want to customize. One image is ok, but more is better. Although we do not perform face detection, the face in the uploaded image should occupy the majority of the image.
2️⃣ Enter a text prompt, making sure to follow the class word you want to customize with the trigger word: img, such as: man img or woman img or girl img.
3️⃣ Choose your preferred style template.
4️⃣ (Optional: but new feature) Select the ‘Enable Drawing Doodle...’ option and draw on the canvas
5️⃣ Click the Submit button to start customizing.

Style template
Output aspect ratio

After enabling this option, PhotoMaker will generate content based on your doodle on the canvas, driven by the T2I-Adapter (Quality may be decreased)

20 100
15 50
1 4
0.1 10
0 2147483647
Examples
Drag (Select) 1 or more photos of your face Prompt Style template Negative Prompt

If PhotoMaker V2 is helpful, please help to ⭐ the Github Repo. Thanks!

📝 Citation
If our work is useful for your research, please consider citing:

@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={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2024}
}

📋 License
Apache-2.0 LICENSE. Please refer to the LICENSE file for details.

📧 Contact
If you have any questions, please feel free to reach me out at zhenli1031@gmail.com.