# ai-dock/comfyui

ComfyUI docker images for use in GPU cloud and local environments. Includes AI-Dock base for authentication and improved user experience.

Repository: https://github.com/ai-dock/comfyui
Canonical: https://ross.abutalabs.com/products/ai-dock-comfyui
Language: Shell
License: NOASSERTION
License Family: other
Topics: ai, comfyui, docker, stable-diffusion, image-processing, runpod, runpod-serverless, vast, runpod-worker, sdxl
Last push: 2024-11-04T18:23:58+00:00

## Health v2 (maintenance only)
Score: 28/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 79
- inputs: {"age_days": 1107, "days_push": 667, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1061, forks 342 (observed 2026-08-28T04:03:25.871718+00:00)

## What it is
Docker images for running ComfyUI in GPU cloud and local environments, built on the AI-Dock base with authentication and configurable startup. Supports NVIDIA CUDA, AMD ROCm, and CPU platforms with provisioning scripts for model setup.

## Use cases
- run comfyui in a docker container on a gpu cloud
- deploy stable diffusion workflows on runpod serverless
- self-host comfyui with cuda or rocm
- spin up an sdxl or flux image generation environment quickly
- run comfyui locally without installing python dependencies

## When to choose
- you want a preconfigured, cloud-first ComfyUI container for vast.ai, RunPod, or local GPUs
- you need CUDA, ROCm, or CPU variants with environment-variable-driven configuration
- you want automatic provisioning of models via scripts and HF/Civitai tokens

## When to avoid
- you need a lightweight install without Docker
- you want images that bundle models out of the box
- you don't use ComfyUI as your image generation interface

## Facets
- artifact type: infra-config
- maturity: active
- function: container-runtime, image-processing, stable-diffusion, deployment, self-hosted
- domain: artificial-intelligence, image-processing, gpu-computing, cloud-computing
- platform: cloud, self-hosted
- tags: comfyui, docker-images, stable-diffusion, runpod, vast-ai, sdxl, cuda, rocm, serverless-gpu, containers, docker, linux, gpu

## Member repositories
- ai-dock/comfyui (main) score 28

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:25.871718+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:56:49.456990+00:00, confidence not recorded.
  - readme: https://github.com/ai-dock/comfyui (fetched 2026-08-28T04:03:25.871718+00:00, sha db714d98ad34)
- Data as of 2026-08-30T08:39:29.467469+00:00.