Kandinsky 6.0 Pro
Generate five-second clips with synchronized audio from a text prompt or an input image. Publisher ComfyUI templates run this full Pro checkpoint with a separate gated transformer; managed Pro Distill is a simpler alternative.
What do you want to do?
Choose a task. Get the software, files, settings, and steps to run it.
Open a guide for its software, hardware requirements, and setup steps.
At a glance
- Parameters
- 29B
- Architecture
- Diffusion
- License
- MIT
- Software
- ComfyUI, Diffusers
Will it run on your machine?
Save your machine to see a personalized rating and its reasoning.
Add my hardwareBest for
- Short prompt-to-video clips with synchronized sound.
- Animate an input image with sound.
Tradeoffs
- Full Pro weights are gated behind an access agreement.
- Neither a 5090 fit nor an H200 minimum is a measured complete-pipeline result.
Ways to run it
ComfyUI · publisher Kandinsky 6 nodes · Windows or Linux NVIDIA GPU; check complete pipeline memory
Publisher templates cover text-to-video+audio and image-to-video+audio. Download models manages the default Pro Distill bundle; the gated full-Pro transformer is a separate option.
Official instructionsKandinsky6TI2VAPipeline / Diffusers · Linux NVIDIA GPU; advanced Python alternative
Publisher supplies a full-Pro Python path, but the visual ComfyUI path is simpler for first use.
Official instructionsExplore its uses
Sources and files
Primary sources and files behind this model page.
Keep exploring
MiniMax H3
An open-weight video model with synchronized native audio. ComfyUI provides a local single-GPU template with dynamic offload; the publisher also documents a separate SGLang multi-GPU route.
Wan-Animate-2 · 14B
Animate a character from a driving video, with text control over the camera viewpoint.
Wan2.1
Explore 2 versions of Wan2.1. Compare model sizes, packages, hardware requirements, and available setups.