Kandinsky 6.0 Video Open-Sources Audio-Video Generation Under MIT License

Kandinsky Lab open-sourced Kandinsky 6.0 Video, a text/image-to-audio-video foundation model under MIT license, offering six variants including Lite (3B) and Pro (29B), with day-0 support in Hugging Face Diffusers and vLLM.

2026-10-06 ~ 2026-10-06 · 4 related posts

• Kandinsky 6.0 Video: Open-Source Synchronized Audio-Video Models Under MIT — kandinskylab · 2026-10-06
• Kandinsky 6.0 Video open-sourced under MIT, vLLM adds day-0 inference support — vllm_project · 2026-10-06
• MIT releases open-weight Kandinsky video+audio model in 6 variants with Diffusers day-0 support — RisingSayak · 2026-10-06

1 near-duplicate retellings: RisingSayak