OSS TanbouOverview
ComfyUI is an AI creation engine for assembling image, video, audio, 3D, and text generation as reusable node graphs. It exposes detailed control over models and parameters, then runs completed workflows through an interface or local API.
Based on official documentation; not hands-on tested · Content checked:
Turn generation pipelines into graphs and re-run only changed work
Nodes assemble image, video, audio, 3D, and text processing into templates, reusable subgraphs, App Mode interfaces, and local API workflows. The engine also provides partial graph re-execution, asynchronous queueing, model offloading, and VRAM and RAM management.
Sources: [1]
For visible, repeatable control over models and generation settings
It fits creators and development teams that combine models, VAEs, LoRAs, ControlNets, upscalers, and other processing while saving, sharing, and reproducing complex pipelines. Core operation can remain offline because it downloads nothing unless requested.
Sources: [1]
Check GPU setup, model locations, and custom-node compatibility
Installation and PyTorch requirements differ across NVIDIA, AMD, Intel, Apple Silicon, and other hardware. Model files must be placed in type-specific directories. Commits outside stable tags may break custom nodes, so verify extension provenance and supported versions and back up workflows before upgrades.
Sources: [1]
Official sources
- [1]ComfyUI README(2026-09-13)
Supplemental curator note
Selected for transferring an anonymous founder's discovery equity into an organization through redirects, then expanding it with a distinctive name and multilingual documentation.
Growth trends
Last 30 days
132,801 Stars
Trend data is still being collected.
Built with
- Python
Categories and tags
Categories
Tags
GitHub Topics
- stable-diffusion
- pytorch
- ai
- python
- comfy
- comfyui
GitHub dataView detailed GitHub data
- Stars
- 132,801
- Forks
- 15,686
- Watchers
- 809
- Open issues
- 4,225
- Contributors
- 338
- Primary language
- Python
- License
- GPL-3.0
- Repository last updated
- Sep 13, 2026
Explore next
- n8n204,119 Stars
A fair-code platform combining a visual canvas and code for service integrations, workflows, and AI agents.
TypeScript - Ollama180,764 Stars
A runtime for downloading and running open models on a computer or server through a CLI and local API.
Go - Transformers165,220 Stars
A Python framework for inference and training with pretrained text, vision, audio, and multimodal models.
Python - AUTOMATIC1111 Stable Diffusion WebUI164,915 Stars
A Gradio UI for Stable Diffusion image generation, editing, model selection, extensions, and APIs.
Python - Dify155,555 Stars
A visual LLM application platform combining AI workflows, RAG, agents, model management, and observability.
TypeScript
Report incorrect information
Tell us if any listing information is incorrect or outdated.