GitHub previewComfyUI
Node workflow engineGPL-3.0 116kBest for: Anyone who expects to try more than one model family this year and wants workflows they can save, share and call over an API.
ComfyUI is where new models land first. Version 0.38.0 (29 September 2026) added Ming-Image and a tiny VAE for Qwen-Image 2.1, and the core team ports memory optimisations across the FLUX and Lumina families in the same release.
Every generation is a graph of nodes, so a workflow saved as JSON or embedded in a PNG reproduces exactly on another machine. The README claims the largest open models run on 4 GB of VRAM with 8 GB of RAM through weight streaming; expect it to be slow at that size.
The official docs list CUDA on NVIDIA, ROCm 7.2 on Linux and ROCm 10.0 on Windows for RDNA 2–4, Arc via torch.xpu, and MPS on Apple Silicon. There is no official Docker image. Optional paid Partner Nodes call closed cloud models; start with --disable-api-nodes to keep everything offline.
Key strengths
- Day-one or early support for most new open image and video models
- Workflows saved as JSON or embedded in output images
- Local HTTP and WebSocket API for automation
- Runs fully offline; paid API nodes can be disabled
- • v0.38.0 changes: Ming-Image, Qwen-Image 2.1 tiny VAE, FLUX optimisations:ComfyUI v0.38.0 release notes
- • NVIDIA, AMD ROCm, Intel XPU and Apple MPS support; no official Docker image:ComfyUI system requirements
- • 4 GB VRAM claim, offline mode and --disable-api-nodes:ComfyUI README












