"Sber" released Kandinsky 6.0 Video neural network
"Sber" presented the Kandinsky 6.0 Video neural network, which can create video clips with synchronized speech, music, and ambient sounds.
As the developers reported, the new model allows generating videos up to five seconds long in SD, HD, and Full HD (1920 × 1080 pixels) quality. The sound is formed with a sampling frequency of 44 kHz, while the characters' lip movements are synchronized with their speech. If desired, a video can be created without an audio track.
The request is formed using a text description or based on an uploaded first frame. The lineup includes two versions: Lite with 3 billion parameters and Pro with 30 billion parameters. According to the company, the model on average exceeded the previous version in 71% of cases in all criteria for transmitting movement and physics.
The tool is integrated into the "GigaChat" service and is also available on Hugging Face. The source code and model weights are open under the free MIT license, which allows developers to use it for free in their own products.
What it means
The model is available to users in "GigaChat", and third-party developers can integrate it for free under the MIT license through the Hugging Face repository.
Sources
- Hi-Tech Mail: Сбер представил Kandinsky 6.0 Video: генерирует видео с синхронным звуком в Full HD media outlet
- iXBT.com: «ГигаЧат» Сбера научился создавать видео с синхронным звуком media outlet
- 3DNews: «Сбер» выпустил Kandinsky 6.0 Video — ИИ-модель для генерации видео с синхронным звуком media outlet
- Хабр: «Сбер» выпустил модель Kandinsky 6.0 Video для генерации видео с речью и музыкой media outlet
This article was prepared with the help of AI and translated from the Russian original. Spotted an error — let us know.
Published 7 October 2026, 14:32 · No updates · Russian original
Comments on this story live under its post in our Telegram channel. Comment on Telegram