Gradio has released Workflow1111, a project that rebuilds most of AUTOMATIC1111's stable-diffusion-webui feature set using the gr.Workflow framework. The application consists of a single canvas containing eleven media pipelines built from seventy-three nodes, covering text-to-image, image-to-video, and various preprocessing tasks.
- The workflow integrates SOTA models for text-to-image, hi-resolution fix, image-to-image, prompt-matrix grids, VLM interrogation, detection-to-inpaint masks, ControlNet-style annotators, background removal, PNG Info storing, and image-to-video.
- It utilizes four operator kinds: fn (Python functions), model (via InferenceClient), space (other Gradio Spaces), and dataset (Hub rows).
- Users can run pipelines by signing in with a Hugging Face account or providing an access token, using their own quota for model calls.
- The system exposes every output node as a REST endpoint and MCP tool, allowing AI assistants to call generation, detection, and metadata retrieval steps.
- While default runs use remote hardware via Inference Providers, fn nodes can also load local checkpoints to run on the user's own GPU.
This approach allows users to build, share, and modify complex multi-model pipelines in a browser without writing glue code or installing dependencies.