InfiniteYou-FLUX + OmniControl LoRA

Identity Preservation + Object Control (Unified)

💡 How to Use InfiniteYou + OmniControl:

  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. [Optional] Upload an object image for OmniControl. This enables object control in addition to identity preservation. The object will be integrated into the scene.
  3. Enter the text prompt to describe the generated image and select the model version. Use "this item", "the object", or "it" to refer to the uploaded object.
  4. [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.
  5. [Optional] Adjust advanced hyperparameters or apply optional LoRAs to meet personal needs. Please refer to important usage tips under the Generated Image field.
  6. Click the "Generate" button to generate an image. Enjoy!
Model Version
0 1
0 1
0 1
0 1
0 1
0 1
0 2

❗️ 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.
  • OmniControl: Upload an object image and set OmniControl weight > 0 to enable object control. Use "this item", "the object", or "it" in your prompt to refer to the object.
  • 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, Indo Realism, Add Details, and OmniControl. 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.