Sakhanda Wire
NVDA $153.73 -1.54% MSFT $506.30 -2.26% GOOGL $280.09 -1.28% META $619.28 -1.14% AMZN $256.62 -0.44%
← Back to the news

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.

Originally published by Hugging Face on

Read the original on Hugging Face ↗

The reporting and the image belong to Hugging Face and are credited and linked above; the text on this page is Sakhanda Wire's own summary.

← Back to the news

More stories

All the latest news