What is ComfyUI?
ComfyUI is the most powerful and modular stable diffusion GUI, API, and backend with a graph/nodes interface.
How can I use ComfyUI?
ComfyUI provides a graph/nodes interface to experiment and create complex Stable Diffusion workflows without needing to code anything. It supports various features, including SD1.x, SD2.x, SDXL, Stable Video Diffusion, Stable Cascade, and SD3.
Features of ComfyUI
ComfyUI offers a range of features, including:
- Nodes/graph/flowchart interface to experiment and create complex Stable Diffusion workflows
- Supports SD1.x, SD2.x, SDXL, Stable Video Diffusion, Stable Cascade, and SD3
- Asynchronous Queue system
- Optimizations: Only re-executes the parts of the workflow that change between executions
- Command line option: --lowvram to make it work on GPUs with less than 3GB vram (enabled automatically on GPUs with low vram)
- Works even if you don't have a GPU with: --cpu (slow)
- Can load ckpt, safetensors, and diffusers models/checkpoints
- Standalone VAEs and CLIP models
- Embeddings/Textual inversion
- Loras (regular, locon, and loha)
- Hypernetworks
- Loading full workflows (with seeds) from generated PNG files
- Saving/Loading workflows as Json files
- Nodes interface can be used to create complex workflows like one for Hires fix or much more advanced ones
- Area Composition
- Inpainting with both regular and inpainting models
- ControlNet and T2I-Adapter
- Upscale Models (ESRGAN, ESRGAN variants, SwinIR, Swin2SR, etc...)
- unCLIP Models
- GLIGEN
- Model Merging
- LCM models and Loras
- SDXL Turbo
- Latent previews with TAESD
- Starts up very fast
- Works fully offline: will never download anything
- Config file to set the search paths for models
How can I install ComfyUI?
ComfyUI can be installed on Windows, Linux, and Apple Mac silicon. For Windows, there is a portable standalone build that should work for running on Nvidia GPUs or for running on your CPU only. For Linux and Apple Mac silicon, you can install ComfyUI manually by cloning the repo, installing dependencies, and running the application.
Troubleshooting ComfyUI
If you encounter the "Torch not compiled with CUDA enabled" error, uninstall torch and install it again with the command provided. For AMD GPUs, you may need to install rocm and pytorch with pip. For Intel GPUs, you can install ComfyUI with the support requirements listed in the Installation page. For Apple Mac silicon, you can install ComfyUI with pytorch nightly and follow the manual installation instructions.