Metraipolis › archive › dc_0429dbe2ef53
Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation — arXiv:2610.05608
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.05608
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:27:03.985Z
- SHA-256 of the archived text
4b3d3d923c8c51b738118a15163832c8aa275ceb57ad879210fc01dd4449650b- Stable URL of this page
https://metraipolis.com/documento/dc_0429dbe2ef53
How to cite
Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation — arXiv:2610.05608 — arXiv, https://arxiv.org/abs/2610.05608 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0429dbe2ef53 (Metraipolis archive dc_0429dbe2ef53, sha256 4b3d3d923c8c51b738118a15163832c8aa275ceb57ad879210fc01dd4449650b)
BibTeX
@misc{dc0429dbe2ef53,
title = {Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation — arXiv:2610.05608},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.05608},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0429dbe2ef53; sha256 4b3d3d923c8c51b738118a15163832c8aa275ceb57ad879210fc01dd4449650b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05608. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 (I2AV) modes; a built-in super-resolution model raises the output resolution to Full-HD (1920$\times$1080). Building on the video generation capabilities of Kandinsky 5.0, Kandinsky 6.0 Video employs a dual-stream CrossDiT architecture that connects a pretrained video stream and a newly trained audio stream through bidirectional cross-attention for temporal and semantic alignment. Our continuous pretraining strategy first trains the audio stream from scratch on large-scale audio corpora and then trains both streams jointly on paired audio-video data while preserving unimodal fidelity; pretraining is followed by supervised fine-tuning, reinforcement-learning-based post-training, and distillation. In side-by-side human evaluation, Kandinsky 6.0 Video Pro clearly outperforms its predecessor, Kandinsky 5.0 Video Pro, and remains competitive with leading audio-video generation models, particularly in speech quality. To accelerate open research and deployment in multimedia generation, we release the code, model checkpoints, and diffusers integration under the MIT license. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multimedia (cs.MM). Pagina del lavoro: https://arxiv.org/abs/2610.05608 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T05:24:06.054Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).