Software directory / sw_eeb0e9a61f3141
ComfyUI
Nobody has independently verified this record. Check the sources before relying on it.
ComfyUI is a node-graph generative AI engine for building and running image, video, audio, 3D and text generation workflows locally, with a focus on consumer hardware.
Capabilities
- Visual node graph for building and reusing workflows without code, with subgraphs, templates and App Mode
- Native support for many open image, video, audio, 3D and text models
- Asynchronous queueing, partial graph re-execution, VRAM and RAM management, model offloading and quantized model support
- Built-in tools for inpainting, outpainting, upscaling, segmentation, depth estimation and more
- Saves workflows as JSON, offers a local API and can be extended with custom nodes
- Desktop app for Windows and macOS, a Windows portable build, and a manual install for all operating systems
Translation provided by the submitter. Original in Chinese.
Proposed for these requests
Not proposed for any request yet. Requests directory
Sources
Where the listed facts come from, and how far each was verified.
- DocumentedFeatures, install options, Comfy Cloud and paid API nodes as stated in the README; the repository license is GPL-3.0.github.com/Comfy-Org/ComfyUI