Workflow1111 rebuilds AUTOMATIC1111 features as a Gradio canvas
Workflow1111 brings most of AUTOMATIC1111’s feature set into one Gradio workflow canvas. The project combines 11 media pipelines built from 73 nodes, covering text-to-image, image-to-image, hi-resolution refinement, prompt matrices, image interrogation, detector-generated inpainting masks, ControlNet-style annotators, upscaling, background removal, PNG metadata, and image-to-video. Users can run the pipelines after signing in with a Hugging Face account or supplying an access token; model calls then use the caller’s quota.
The canvas combines four operator types: Python functions, models called through InferenceClient, other Gradio Spaces, and dataset rows. Several branches run in parallel, including prompt-matrix generation and image interrogation. Local functions handle tasks such as metadata processing and image annotation, while models including Qwen3-4B, Qwen2.5-VL, FLUX.1-Kontext, and Wan 2.2 I2V A14B provide generation, analysis, editing, or animation.
Each output node can become a REST endpoint, and the same outputs can be exposed as MCP tools for AI assistants. The workflow can use remote providers or Spaces, but functions may also load checkpoints on a user’s own GPU. Developers can duplicate the project, replace nodes and models, reconnect the graph, and deploy the result as a Space.
Written by Sakhanda Wire AI from reporting by Hugging Face. Facts, quotes and full context are in the original article below.