💡 How to Use This Demo:

  1. Upload an identity (ID) image containing a human face. For multiple faces, only the largest face will be detected. The face should ideally be clear and large enough, without significant occlusions or blur.
  2. Enter the text prompt to describe the generated image and select the model version. Please refer to important usage tips under the Generated Image field.
  3. [Optional] Upload a control image containing a human face. Only five facial keypoints will be extracted to control the generation. If not provided, we use a black control image, indicating no control.
  4. [Optional] Adjust advanced hyperparameters or apply optional LoRAs to meet personal needs. Please refer to important usage tips under the Generated Image field.
  5. Click the "Generate" button to generate an image. Enjoy!
Model Version
0 1
0 1
0 1

❗️ Important Usage Tips:

  • Model Version: aes_stage2 is used by default for better text-image alignment and aesthetics. For higher ID similarity, try sim_stage1.
  • Useful Hyperparameters: Usually, there is NO need to adjust too much. If necessary, try a slightly larger --infusenet_guidance_start (e.g., 0.1) only (especially helpful for sim_stage1). If still not satisfactory, then try a slightly smaller --infusenet_conditioning_scale (e.g., 0.9).
  • Optional LoRAs: realism and anti-blur. To enable them, please check the corresponding boxes. If needed, try realism only first. They are optional and were NOT used in our paper.
  • Gender Prompt: If the generated gender is not preferred, add specific words in the prompt, such as 'a man', 'a woman', etc. We encourage using inclusive and respectful language.
Examples
Identity Image Control Image [Optional] Prompt seed (0 for random) Enable realism LoRA Enable anti-blur LoRA Model Version

Please refer to our GitHub repository to run the InfiniteYou-FLUX gradio demo locally.

📜 Disclaimer and Licenses

The images used in this demo are sourced from consented subjects or generated by the models. These pictures are intended solely to show the capabilities of our research. If you have any concerns, please contact us, and we will promptly remove any inappropriate content.

The use of the released code, model, and demo must strictly adhere to the respective licenses. Our code is released under the Apache License 2.0, and our model is released under the Creative Commons Attribution-NonCommercial 4.0 International Public License for academic research purposes only. Any manual or automatic downloading of the face models from InsightFace, the FLUX.1-dev base model, LoRAs, etc., must follow their original licenses and be used only for academic research purposes.

This research aims to positively impact the field of Generative AI. Any usage of this method must be responsible and comply with local laws. The developers do not assume any responsibility for any potential misuse. We added the "AI Generated" watermark for enhanced safety.

📖 Citation

If you find InfiniteYou useful for your research or applications, please cite our paper:

@article{jiang2025infiniteyou,
  title={{InfiniteYou}: Flexible Photo Recrafting While Preserving Your Identity},
  author={Jiang, Liming and Yan, Qing and Jia, Yumin and Liu, Zichuan and Kang, Hao and Lu, Xin},
  journal={arXiv preprint},
  volume={arXiv:2503.16418},
  year={2025}
}

We also appreciate it if you could give a star ⭐ to our Github repository. Thanks a lot!