ComfyUI and worker-comfyui

The second tool is a serverless API implementation of the first tool, making them ecosystem siblings where one provides infrastructure and an interface, and the other offers a specific deployment and access method for it.

ComfyUI
72
Verified
worker-comfyui
74
Verified
Maintenance 25/25
Adoption 10/25
Maturity 16/25
Community 21/25
Maintenance 23/25
Adoption 10/25
Maturity 16/25
Community 25/25
Stars: 106,230
Forks: 12,230
Downloads:
Commits (30d): 142
Language: Python
License: GPL-3.0
Stars: 671
Forks: 632
Downloads:
Commits (30d): 30
Language: Python
License: AGPL-3.0
No Package No Dependents
No Package No Dependents

About ComfyUI

Comfy-Org/ComfyUI

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Supports diverse generative models across image, video, audio, and 3D modalities with intelligent memory management and GPU offloading for low-VRAM systems. The architecture uses an asynchronous queue system with incremental execution—only re-computing workflow nodes that have changed—and integrates LoRAs, ControlNets, and model merging capabilities. Extensible through custom nodes and external API providers, while maintaining fully offline operation for core functionality.

About worker-comfyui

runpod-workers/worker-comfyui

ComfyUI as a serverless API on RunPod

Exposes ComfyUI workflows through RunPod's serverless API (`/run`, `/runsync`, `/status`) with flexible output handling—images returned as base64 strings by default or uploaded directly to S3 buckets. Pre-built Docker images bundle popular diffusion models (FLUX.1, Stable Diffusion 3/XL) alongside the base ComfyUI installation, eliminating manual model setup. Accepts workflow JSON with optional base64-encoded input images and supports per-request API credentials for external integrations.

Scores updated daily from GitHub, PyPI, and npm data. How scores work