Rebuilding AUTOMATIC1111 with Gradio Workflow

Summary

Workflow1111 rebuilds most of AUTOMATIC1111’s stable-diffusion-webui feature set as a single Gradio Workflow canvas. It combines eleven media pipelines and 73 nodes for text-to-image, refinement, image-to-image, prompting, interrogation, detection masks, annotators, upscaling, background removal, PNG metadata, and image-to-video. The implementation uses four operator kinds—Python fn functions, model calls through InferenceClient, Space calls, and Hub dataset rows—with parallel branches for independent work; 32 of 36 operator nodes are fn nodes, and 22 run in-process without network calls. Models can run through Inference Providers, Spaces, or a local GPU, while output nodes automatically become REST endpoints and MCP tools. The result is a browser-accessible, OAuth-enabled workflow that can also be duplicated, rewired, deployed, and called from code.

Takeaways

1. 1

   The text-to-image pipeline adds style presets and cleaned prompts before inference, then writes generation parameters—including prompts, steps, CFG, seed, dimensions, and model—to PNG metadata for later retrieval.

2. 2

   Prompt-matrix variants run through four side-by-side text-to-image nodes because gr.Workflow has no loop operator; equal dependency depth lets all four generations start in parallel.

3. 3

   Workflow1111 exposes nine REST endpoints, and enabling mcp_server=True exposes the output nodes as MCP tools that callers authenticate with their own X-HF-Token header.