Apps · Desktop app

ComfyUI

by Comfy Org · GPL-3.0 · 142,909 GitHub stars

Node-based image and video generation with day-one support for most open models, GGUF nodes and offloading.

macOSWindowsLinux

Get ComfyUI

At a glance

Best for
The default for image and video models on Windows and Linux, and for the newest video models on any OS.
Inference engine
  • PyTorch (ComfyUI)
  • GGUF via ComfyUI-GGUF
GPU support
  • NVIDIA CUDA
  • AMD ROCm
  • Intel oneAPI / SYCL
  • Apple Metal
  • CPU only
Opens
  • Safetensors (original weights)
  • GGUF
Features
  • Chat window
  • Node workflows
  • Offloads to RAM on small GPUs
  • HTTP API
Platforms
Windows portable build and desktop app, macOS (Apple silicon, MPS), Linux. NVIDIA, AMD (ROCm), Intel (XPU) and Apple GPUs.

Sources: github.com · github.com

Install

macOS

Download from comfy.org

Windows

Download from comfy.org

Linux

git clone https://github.com/comfyanonymous/ComfyUI

77 models on this site run in ComfyUI

Model Made by Type Size Opens it as Quality tier
FLUX.2 [dev] Black Forest Labs Image 32.2B Original or GGUF 92
Qwen-Image 2512 Alibaba Image 20.4B Original or GGUF 90
Qwen-Image Alibaba Image 20.4B Built-in support 88
Qwen-Image-Edit 2511 Alibaba Image 20.4B Original or GGUF 86
FLUX.2 [klein] 9B Black Forest Labs Image 9.1B Original or GGUF 84
HiDream-I1 Full HiDream.ai Image 17.1B Original or GGUF 84
Z-Image Turbo Alibaba (Tongyi) Image 6.2B Original or GGUF 84
FLUX.1 Kontext [dev] Black Forest Labs Image 11.9B Original or GGUF 82
FLUX.1 Krea [dev] Black Forest Labs Image 11.9B Original or GGUF 82
Z-Image Alibaba (Tongyi) Image 6.2B Original or GGUF 82
FLUX.1 [dev] Black Forest Labs Image 11.9B Original or GGUF 80
HiDream-I1 Dev HiDream.ai Image 17.1B Original or GGUF 80
Chroma1-HD Lodestone Rock Image 8.9B Built-in support 78
FLUX.2 [klein] 4B Black Forest Labs Image 3.9B Original or GGUF 78
FLUX.1 Fill [dev] Black Forest Labs Image 11.9B Built-in support 76
HiDream-I1 Fast HiDream.ai Image 17.1B Original or GGUF 76
CogView4 6B Zhipu AI Image 6.4B Built-in support 70
FLUX.1 [schnell] Black Forest Labs Image 11.9B Original or GGUF 70
OmniGen2 BAAI (VectorSpaceLab) Image 4.0B Built-in support 66
Stable Diffusion 3.5 Large Stability AI Image 8.1B Original or GGUF 66
Juggernaut XL v9 RunDiffusion Image 2.6B Built-in support 62
Lumina-Image 2.0 Shanghai AI Lab Image 2.6B Built-in support 62
RealVisXL V5.0 SG161222 Image 2.6B Built-in support 62
Stable Diffusion 3.5 Large Turbo Stability AI Image 8.1B Original or GGUF 62
Animagine XL 4.0 Cagliostro Lab Image 2.6B Built-in support 60
Illustrious XL v0.1 OnomaAI Image 2.6B Built-in support 60
Kolors Kuaishou Image 2.6B Built-in support 60
Playground v2.5 Playground AI Image 2.6B Built-in support 60
AuraFlow v0.3 fal Image 6.9B Original or GGUF 58
DreamShaper XL v2 Turbo Lykon Image 2.6B Built-in support 58
Pony Diffusion V6 XL PurpleSmartAI Image 2.6B Built-in support 58
Stable Diffusion 3.5 Medium Stability AI Image 2.5B Original or GGUF 58
Animagine XL 3.1 Cagliostro Lab Image 2.6B Built-in support 56
Stable Diffusion XL 1.0 Stability AI Image 2.6B Built-in support 55
SDXL-Lightning (4-step) ByteDance Image 2.6B Built-in support 54
Hunyuan-DiT v1.2 Tencent Image 1.5B Built-in support 52
Stable Cascade Stability AI Image 5.2B Built-in support 52
Stable Diffusion 3 Medium Stability AI Image 2.0B Built-in support 52
PixArt-Σ XL 1024 PixArt Image 0.6B Built-in support 50
Kandinsky 3 Sber AI Image 3.0B Built-in support 48
Realistic Vision V5.1 SG161222 Image 0.9B Built-in support 42
DreamShaper 8 Lykon Image 0.9B Built-in support 40
SDXL Turbo Stability AI Image 2.6B Built-in support 40
Stable Diffusion 1.5 Stability AI / Runway Image 0.9B Built-in support 35
LCM DreamShaper v7 Tsinghua (LCM) Image 0.9B Built-in support 30
SD Turbo Stability AI Image 0.9B Built-in support 28
LTX-2.3 Lightricks Video 18.9B Original or GGUF 86
Wan 2.2 I2V A14B Alibaba Video 14.0B Original or GGUF 86
Wan 2.2 T2V A14B Alibaba Video 14.0B Original or GGUF 86
HunyuanVideo 1.5 (8.3B) Tencent Video 8.3B Built-in support 84
LTX-2 (19B, video + audio) Lightricks Video 18.9B Original or GGUF 82
SkyReels V2 T2V 14B 720P Skywork Video 14.0B Built-in support 78
Wan 2.1 I2V 14B 720P Alibaba Video 14.0B Original or GGUF 78
Wan 2.1 T2V 14B Alibaba Video 14.0B Original or GGUF 78
Wan 2.1 VACE 14B Alibaba Video 17.3B Original or GGUF 78
Wan 2.2 Animate 14B Alibaba Video 17.3B Original or GGUF 78
Wan 2.2 S2V 14B (speech to video) Alibaba Video 16.3B Original or GGUF 76
FramePack I2V (HunyuanVideo 13B) lllyasviel Video 12.9B Built-in support 74
SkyReels V2 T2V 14B 540P Skywork Video 14.0B Built-in support 74
Wan 2.1 I2V 14B 480P Alibaba Video 14.0B Original or GGUF 74
HunyuanVideo 13B Tencent Video 13.0B Original or GGUF 72
HunyuanVideo I2V 13B Tencent Video 13.0B Original or GGUF 72
Cosmos-Predict2 14B Video2World NVIDIA Video 14.0B Built-in support 70
Wan 2.2 TI2V 5B Alibaba Video 5.0B Original or GGUF 70
LTX-Video 13B 0.9.8 (distilled) Lightricks Video 13.0B Built-in support 68
Mochi 1 Preview (10B) Genmo Video 10.0B Built-in support 62
CogVideoX 1.5 5B Zhipu AI Video 5.6B Built-in support 60
Cosmos 1.0 Diffusion 7B Text2World NVIDIA Video 7.0B Built-in support 60
Cosmos-Predict2 2B Video2World NVIDIA Video 2.0B Built-in support 58
CogVideoX 5B Zhipu AI Video 5.0B Built-in support 55
CogVideoX 5B I2V Zhipu AI Video 5.6B Built-in support 55
Wan 2.1 T2V 1.3B Alibaba Video 1.3B Built-in support 55
Wan 2.1 VACE 1.3B Alibaba Video 2.2B Built-in support 55
SkyReels V2 Diffusion Forcing 1.3B Skywork Video 1.4B Built-in support 52
LTX-Video 2B Lightricks Video 1.9B Original or GGUF 50
CogVideoX 2B Zhipu AI Video 1.7B Built-in support 45
AnimateDiff v3 (SD 1.5) Shanghai AI Lab Video 1.3B Built-in support 35

Alternatives

Draw Things Unsloth Desktop DiffusionBee JoyFusion

Which app should I use?

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.