ArchestackGitHub ↗ (opens in a new tab)

11st of 8 in Image and video

ComfyUI

Node-graph engine for diffusion image, video, audio and 3D models

Documentation ↗ (opens in a new tab)Website ↗ (opens in a new tab)Repository on GitHub ↗ (opens in a new tab)
Stars
136.8k
License
GPL-3.0
Last commit
Oct 2026
Last release
Oct 2026

Overview

Builds generation pipelines as a visual node graph and runs them locally for image (SD 1.5, SDXL, SD3.5, Flux.1 and Flux.2, Qwen Image), video (Wan 2.x, LTX-Video, HunyuanVideo), audio (ACE-Step, Stable Audio) and 3D (Hunyuan3D) models, with a local API and an App Mode that exposes a workflow as a simple UI. Runs on NVIDIA, AMD, Intel, Apple Silicon and Ascend. For professionals who want control over every parameter.

Who it is for: Visual professionals running diffusion models locally

Strengths

  • Asynchronous weight streaming runs large models on 4 GB VRAM plus 8 GB RAM
  • Workflows saved as JSON and recoverable from generated media metadata
  • Runs fully offline; --offline disables the paid API nodes
  • Loads checkpoints, separate diffusion models, VAEs, text encoders, LoRAs, ControlNets

Weaknesses

  • Commits outside stable tags can break many custom nodes; stable releases roughly biweekly
  • GPL-3.0 license constrains embedding in proprietary products
  • NVIDIA 20-series and newer require PyTorch built with CUDA 13.0 or above
  • Paid partner and API nodes stay on unless --offline or --disable-partner-nodes is set

What it needs

  • RAM ≥ 8 GB
  • GPU optional
  • Models: Stable Diffusion 1.5, SDXL, SD3.5, Flux.1 and Flux.2, Qwen Image and Qwen Image Edit, Wan 2.1/2.2, LTX-Video 2

Also in Image and video

See all 8
Also in Image and video
RankProjectScore
2MoneyPrinterTurboGenerates short videos from a topic with script, footage, voice and subtitles129.5k stars, MIT69 out of 100
3InvokeAICanvas-first web UI for Stable Diffusion and Flux image generation28.5k stars, Apache-2.062 out of 100
#4AI ToolkitFine-tuning suite for image, video and audio diffusion models, with GUI and CLI12.3k stars, MIT54 out of 100
#5Kohya's GUIGradio GUI and CLI for Kohya diffusion training scripts12.6k stars, Apache-2.052 out of 100
#6Pixelle-VideoTopic-to-short-video pipeline built on ComfyUI workflows and TTS28.8k stars, Apache-2.051 out of 100