Search

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

ComfyUI-Manager is an extension designed to enhance the usability of ComfyUI. It offers management functions to install, remove, disable, and enable various custom nodes of ComfyUI. Furthermore, this extension provides a hub feature and convenience functions to access a wide range of information within ComfyUI.

Making ComfyUI more comfortable!

Deforum ComfyUI Nodes - ai animation node package

CLI for using ComfyUI

Official front-end implementation of ComfyUI

[ARCHIVED] Superseded by https://github.com/Comfy-Org/Comfy-Desktop

ComfyUI template workflows

Enable true multi gpu capability in Comfy UI using XDiT XFuser and FSDP managed by Ray

Prompt Manager for ComfyUI, with integration with llama.cpp for prompt generation. Allowing users to generate and save prompts, as well as extract prompts from images and video with Comfy/A1111 metadata. Lora Stacks are saved along with the prompts. v2.0 pushes this further, giving the user the option of saving complete Recipes.

Fast kernel library for Diffusion inference with multiple compute backends.

Your own personal AIGC Factory. Any picture. Any reel. The Comfy way. ©️

The desktop app for ComfyUI

Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video & audio, authors and runs workflows, and edits your live graph in natural language on ANY LLM (Claude, ChatGPT, Gemini, offline Ollama, or any hosted model). 178 tools, 36 AI skills, 55 installer packs. Local, LAN, VPS, or Comfy Cloud.

Comfy UI workflows from Pixaroma YouTube channel, episode backups.

Vibe coded nodes for LTX2.3

Comfy Cloud product skills: slash commands for generating images, video, audio, and 3D with Comfy Cloud agents. Single source of truth for the installer and MCP server.

Local MCP server for ComfyUI — run your local ComfyUI from AI agents