Kandinsky: Open Video and Audio Generation Models
ComfyUI Wiki
Kandinsky 6.0 is Kandinsky Lab's open family of diffusion models that generate 5-second video with synchronized 44 kHz audio, in Pro and Lite sizes.
K
Kandinsky
Video GenerationAudio-VideoText-to-VideoImage-to-VideoComfyUIKandinsky is Kandinsky Lab's open family of diffusion models for video generation. Kandinsky 6.0 generates 5-second clips with synchronized 44 kHz audio in text-to-audio-video and image-to-audio-video modes, ships as a 29B Pro line and a 3B Lite line, and pairs with a separate super-resolution model for Full HD output. A first-party ComfyUI extension provides ready-to-run workflows.
Models
| Model | Type | Description | License | Released |
|---|---|---|---|---|
| Kandinsky 6.0 | Video + Audio | 29B Pro and 3B Lite diffusion models with synchronized 44 kHz audio and a Full HD super-resolution pipeline | MIT | 2026-10 |
Select a model above for curated weight downloads, tutorials, and related information.
Comments
Sign in with GitHub to join the discussion.