kandinskylab/kandinsky-6
Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
Kandinsky 6.0: A family of diffusion models for Video + Audio generation We present Kandinsky 6.0 Video, a family of foundation diffusion models for synchronized text-to-audio-video generation, comprising Kandinsky 6.0 Video Lite (3B parameters) and Kandinsky 6.0 Video Pro (29B parameters). Both models generate 5-second video clips with synchronized 44 kHz audio, including lip-sync, in text-to-audio-video (T2AV) and image-to-audio-video (TI2AV) modes. A plug-in super-resolution model raises the output resolution to Full HD (1920×1080). An NVIDIA GPU and Python 3.13 or 3.14. The first run downloads Kandinsky-6.0-Pro-distill-5s into $KANDINSKYHOME/weights. When $KANDINSKYHOME is unset, that directory is /.cache/kandinsky. The clip is written to $KANDINSKYHOME/outputs/generate/generations/output.mp4, with the expanded prompt in expandedprompt.txt next to launch.json, logs/, and profiles/. The generate command downloads the checkpoint named in the config if it is not already on disk. Other catalog names are pro, pro-pretrain, lite, lite-distill, and lite-pretrain. You need uv and just. just setup reads the…
Read the full README ↗ · Preview checked 2026-10-08T13:41:14.837Z
Inside the original README — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: MIT. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation
Repository facts
- Owner
- kandinskylab
- Primary language
- Python
- Stars
- 214
- Forks
- 12
- Open issues + pull requests
- 2
- License
- MIT
- Archived
- No
- Default branch
- main
- Created
- 2026-10-05T09:06:41.000Z
- Last push
- 2026-10-08T09:04:36.000Z
Topics and intended use
No topics were included in the latest source metadata.
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-10-08T12:06:17.489Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related repositories
EbookFoundation/free-programming-books
donnemartin/system-design-primer