#52 · Primary category: Image Generation

worker-comfyui

ai comfyui docker pod runpod sdxl serverless stable-diffusion worker

ComfyUI as a serverless API on Runpod

Project last updated:08/27/26

GitHub Stars

734

Forks

696

Contributors

18

License

AGPL-3.0

Why we included this project

ComfyUI users who want to turn their workflows into a callable API without babysitting a GPU instance will get the most out of this worker. It wraps ComfyUI in Docker images built for RunPod's serverless endpoints, so you send a workflow JSON over HTTP and receive generated images back as base64 strings or S3 URLs. The prebuilt images ship with FLUX.1 schnell and dev, SDXL, and SD3 checkpoints, so you skip most of the environment setup. It also covers the production details that tend to trip people up, like feeding input images into a workflow, choosing between synchronous and asynchronous endpoints, and configuring S3 uploads. If you already run on RunPod, this is the shortest route from a working ComfyUI graph to a metered, pay-per-use image API.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category