OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Image & Video AI

Comfyui

ComfyUI is a Python-based, open-source application with a visual node graph, backend and API for building and running diffusion-model workflows. It supports media generation and processing, including images, video, audio and 3D-related workflows.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Comfyui — OpenViST project profile in Image & Video AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use ComfyUI when a media task benefits from a configurable, reusable node graph, or when a workflow needs to be exposed through an API or simplified with App Mode.

Who it is for

  • Visual creators who want to control models, parameters and generation steps.
  • Developers integrating reusable AI workflows into applications or production pipelines.
  • People who want to assemble and save node-based generation workflows.

Documented uses

  • Connect generation and processing steps into a visual workflow.
  • Generate or edit media with supported diffusion models and workflow templates.
  • Save and reuse workflows, or integrate them through the API.
  • Use tools such as inpainting, compositing, upscaling, frame interpolation and depth estimation.
Before you choose

Requirements & limits

The project documents desktop software for Windows and macOS, manual installation for Windows, Linux and macOS, and an official paid cloud version. Core functionality can run offline; optional paid API nodes can be disabled.

  • Local installation choice depends on operating system and available hardware; the project lists support for NVIDIA, AMD, Intel, Apple Silicon and Ascend GPU types for manual installation.
  • ComfyUI is a workflow application and backend, not a diffusion model; users work with supported models and their associated components.
  • The API supports integration into applications and production pipelines, while the node graph is the visual authoring interface.
  • Optional partner/API nodes provide access to some closed-source models; the core can also run offline.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Run ComfyUI from an existing installation

Start ComfyUI using its documented Python entry point.

Before you start

  • An existing ComfyUI installation.
  • Python and dependencies configured for that installation.

Steps

  1. From the ComfyUI directory, run the command below.

    Documented command
    python main.py

  2. Use the running ComfyUI interface to work with node-graph workflows.

Expected outcome

ComfyUI starts using its documented entry point and provides its node-graph interface.

Guide limitations

  • The source documents the launch command but not installation steps, model setup, or a generation workflow.
  • The source does not specify hardware requirements for this procedure.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
Comfy-Org/ComfyUI · Official homepage title · retained in its source language
How we review sourcesSuggest a correction