Gradio adds gr.Workflow, turning a typed node graph into both a UI and one REST endpoint per output

Hugging Face Blog·medium signalXBlueskyLinkedInCopy link

Hugging Face published a guide on 2026-08-25 for gr.Workflow, a built-in Gradio primitive where you describe a pipeline as a graph of typed nodes and Gradio makes the pipeline itself the interface. It supports sequential chains such as generate then background-remove then edit, parallel fan-out from one input, and mixing Hugging Face Inference Providers, existing Spaces, and plain Python functions as nodes. The minimal form is gr.Workflow(bind=[your_function]).launch(), GPU nodes use the @spaces.GPU decorator with ZeroGPU, and deploying to Spaces auto-generates named REST endpoints per output callable from gradio_client or curl. No version number is given in the post.