FLUX 3 Klein 4-step LoRA

by muinezco.huggingface.muinez/flux3-klein-4step-demo

How the score works

  • Remote endpoint
  • 4 tools

Tools

  • flux3_klein_4step_demo__check_login_status
  • flux3_klein_4step_demo__load_initial
  • flux3_klein_4step_demo_endpoint
  • flux3_klein_4step_demo_infer Generate or edit images with FLUX 3 Image Klein, the 5.6B open weights image model from Black Forest Labs. Text-to-image, editing with up to 10 reference images, and layout control with bounding boxes, through one model. Use the 4-step LoRA mode for 4-step generation without guidance, or base mode for 50-step generation with classifier-free guidance. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: tuple: the generated PIL Image, the seed used, and the prompt the model saw.

As the server's own listing gives them. We never call a tool.