Rebuilding AUTOMATIC1111 with Gradio Workflow
huggingface ·
The article describes Workflow1111, a Gradio Workflow project that rebuilds most of AUTOMATIC1111 stable-diffusion-webui's feature set as a single workflow canvas. It is a graph of eleven media pipelines built with seventy-three nodes, covering text-to-image, hi-resolution fix, image-to-image, prompt matrix, VLM interrogate, detection-to-inpaint masks, ControlNet-style annotators, background removal, PNG Info, and image-to-video. The pipelines use four operator kinds: fn for Python functions, model for InferenceClient model calls, space for other Gradio Spaces, and dataset for Hub dataset rows. Users can run the pipelines by signing in with a Hugging Face account or access token, and model calls consume their own quota. Workflow1111 exposes nine output nodes as REST endpoints and can also serve them as MCP tools for AI assistants. The article explains that a fn node can run models locally on a user's own GPU, as in a FastVideo/FastH3 app on ZeroGPU. It also compares gr.Workflow with ComfyUI, noting that nodes can represent hardware or APIs, outputs become typed REST endpoints, and custom nodes are just Python functions.
huggingface