The classic browser UI for Stable Diffusion: text-to-image, inpainting, upscaling and thousands of community extensions.
All repositories
Voice, video, multimodalComfy-Org
ComfyUI
Growing fastest
A node-based builder for diffusion pipelines: wire up image, video and audio generation visually. Runs locally and exposes API endpoints.
Who it is for
People who need precise control over image and video generation rather than a single button.
How to start
- Download the desktop app from comfy.org/download (Windows and macOS), the easiest way in.
- Or follow the Manual Install section of the README, which supports all OSes and GPU types.
- Open the ready-made templates at comfy.org/workflows and run one as is.
Steps are taken from the README. Check the current version in the repository before running them.
Stars over the last 30 days
+4,694Sep 6 — Oct 5
Author's description
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
More in «Voice, video, multimodal»
OpenAI's reference speech-recognition model: transcribes audio in dozens of languages, translates speech and detects the language.
Few-shot voice cloning: about a minute of recorded speech is enough to fine-tune a text-to-speech model. Ships a web UI for data prep and training.
Whisper rewritten in C/C++: runs fast on a plain CPU and on Macs with no Python or heavy dependencies. Easy to embed in apps.
A speech-synthesis model tuned for natural conversational dialogue: handles pauses, laughter and intonation. Good for voice assistants and dialogue voice-over.
Instant voice cloning: takes a short sample, transfers the timbre to any text and lets you control style, emotion and language. MIT-licensed and free for commercial use.