Skip to main content

ComfyUV Deployment Guide

Overview

This guide explains how to deploy the Docker image:

sandichhuu/comfyuv on Docker Hub

⚛️ ComfyUI - UV precompiled byte code.

An optimized, production-ready ComfyUI Docker image built with uv for ultra-fast Python package management. It comes pre-configured with modern performance optimizations like Triton, SageAttention.

Important Note:

⚠️ ThisImportant imageNote
is🌵 I only supporthave nvidiaRTX RTX20xx20, 30 series (sm75),SM75 RTX30xx& (sm86)SM86). So newer series untested.
✅🌵 CompatibleIf withyou higherfacing GPUany RTX40xx,issue, 50xx,please ...,send butthe noterror optimized.log to:
     💮 LinkedIn
     💮 Facebook
     💮 Whatsapp

🌵 Compatible GPU List
✅ SM75 : RTX 2060, 2070, 2080, 2080 Ti, and their Super/Laptop variants.
✅ SM86 : RTX 3050, 3060, 3070, 3080, 3090, A2, A10, A16, A40, A2000, A4000, A5000, A6000 and their Super/Laptop variants.
✅ Newer : Runnable, but notslower.
fastest.✅ SM86 : RTX 40 Series.
✅ SM86 : RTX 30 Series.
✅ SM75 : RTX 20 Series.
⛔ Unsupported : GTX10xxGTX 10 Series and older series,older, AMD or Intel GPU.

⚠️ Unsupport xformers.
      Because cu132 have no pre-build for this package & have no reason to use the slowest method.
✅ You can use sage-attention or triton instead.

⚠️ No longer support flash-attn (because the compile time is super slow).
✅ You can do it your self with this command:

MAX_JOBS=10 NVCC_THREADS=1 uv pip install flash-attn --no-build-isolation

🌸 Why use this Docker image for ComfyUI?

  • ✅ Custom Nodes Compatibility: Python 3.13.13, widely compatible with extensions.
✅ Blazing Fast Execution: Leverages uv for ultra-fast package management and bytecode compilation. Built on CUDA 13.2, delivering superior performance compared to older versions like CUDA 12.8 or 13.0. ✅ Precompiled Ecosystem: Comes out-of-the-box with precompiled essential packages and popular custom nodes, saving you significant setup and compile time. ✅ Privacy-Focused (No Analytics): Completely stripped of telemetry and analytics tracking. Your data and workflows remain entirely private. ✅ Optimized for cloud: You can public the website without configuration. Use caddy or nginx for authentication.

Preinstalled

PRE-INSTALLED

    sage-attnattention and custom nodes:

    🌸 Quick Start (Docker Compose)

    Install Docker, Nvidia Driver (refer Studio version), CUDA Toolkit (version 13.2).
    Next, copy docker-compose.yml content below and put to empty folder.
    Then, open Terminal/CMD/Windows PowerShell and navigate to directory contain docker-compose.yml file.
    Finally, run this command docker compose up -d to start the container. Go to http://localhost:8188 and enjoy.

    Requirements

    ⬇️ Docker
    ⬇️ nvidia-driver
    ⬇️ cuda-toolkit (CUDA 13.2)

    docker-compose.yml

    services:
  comfyuv:
    image: sandichhuu/comfyuv:sm86cu132
    container_name: comfyuv
    ipc: host
    port:
      - 8188:8188
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    volumes:
      - ./input:/comfy/input
      - ./output:/comfy/output
      - ./workflows:/comfy/user/default/workflows
      - ./models:/comfy/models
      - ./workflows:/comfy/user/default/workflows
      
      - comfyuv:/comfy
      - uv_cache:/root/.cache/uv
    command: >
      --enable-triton-backend
#     --use-flash-attention unsupport becase it take long times to compile.
#     --lowvram
      --use-sage-attention
      --disable-pinned-memory
      --fast fp8_matrix_mult autotune
      --front-end-version Comfy-Org/ComfyUI_frontend@latest

volumes:
  comfyuv:
  uv_cache:

    Files🌸 Setup Structure

    comfyuv/
├── docker-compose.yml
├── config.ini
├── input/
├── models/
├── workflows/
└── output/

    🌸 Why have no all-in-one image ?

    All GPU support int4, int8, fp16, fp32.
    But each GPU series has different physics structure due to different kernels and different attention optimization.

    For example RTX4090 support fp8 native, RTX5090 support fp8 & nvfp4 native.
    RTX40xx fastest with FlashAttention3, RTX50xx with FlashAttention4.
    If I compile everything on one image, the file size come super heavy.
    And the compile time is slow as hell.

    I have to put a lot of effort to build this image.
    If the compilation failed, I have to wait several hours to fix and recompile.

    So, All-In-One image is impossible.

    Back to top