[
    {
        "id": "osp-16002",
        "type": "article-journal",
        "title": "Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation",
        "author": [
            {
                "family": "Kandinsky",
                "given": "Team"
            },
            {
                "family": "Agafonova",
                "given": "Julia"
            },
            {
                "family": "Akhmatov",
                "given": "Bulat"
            },
            {
                "family": "Aksyutin",
                "given": "Mikhail"
            },
            {
                "family": "Alekseenko",
                "given": "Grigorii"
            },
            {
                "family": "Aliaskina",
                "given": "Anastasia"
            },
            {
                "family": "Androsova",
                "given": "Olga"
            },
            {
                "family": "Arkhipkin",
                "given": "Vladimir"
            },
            {
                "family": "Averchenkova",
                "given": "Anna"
            },
            {
                "family": "Belykh",
                "given": "Alexander"
            },
            {
                "family": "Bocharova",
                "given": "Serafima"
            },
            {
                "family": "Bogakovskaya",
                "given": "Sofiya"
            },
            {
                "family": "Bukashkin",
                "given": "Anton"
            },
            {
                "family": "Bulygin",
                "given": "Mark"
            },
            {
                "family": "Buzygin",
                "given": "Kirill"
            },
            {
                "family": "Cheremnykh",
                "given": "Irina"
            },
            {
                "family": "Chernyshev",
                "given": "Kirill"
            },
            {
                "family": "Chernyshov",
                "given": "Mikhail"
            },
            {
                "family": "Chernyy",
                "given": "Vladimir"
            },
            {
                "family": "Chikovani",
                "given": "David"
            },
            {
                "family": "Daniltsev",
                "given": "Georgy"
            },
            {
                "family": "Dimitrov",
                "given": "Denis"
            },
            {
                "family": "Dmitrienko",
                "given": "Anna"
            },
            {
                "family": "Dokholyan",
                "given": "Vladimir"
            },
            {
                "family": "Emelyanov",
                "given": "Sergey"
            },
            {
                "family": "Ermilov",
                "given": "Dmitry"
            },
            {
                "family": "Fedorov",
                "given": "Georgii"
            },
            {
                "family": "Gavrilova",
                "given": "Polina"
            },
            {
                "family": "Gerasimenko",
                "given": "Nikolai"
            },
            {
                "family": "Gordeev",
                "given": "Aleksandr"
            },
            {
                "family": "Inozemtsev",
                "given": "Andrey"
            },
            {
                "family": "Ivaniuta",
                "given": "Andrei"
            },
            {
                "family": "Ivanov",
                "given": "Alexander"
            },
            {
                "family": "Karaev",
                "given": "Mikhail"
            },
            {
                "family": "Kargapoltseva",
                "given": "Anastasiia"
            },
            {
                "family": "Kirillov",
                "given": "Ivan"
            },
            {
                "family": "Kiselev",
                "given": "Nikita"
            },
            {
                "family": "Kobenko",
                "given": "Valeria"
            },
            {
                "family": "Kolabushin",
                "given": "Yury"
            },
            {
                "family": "Koposov",
                "given": "Denis"
            },
            {
                "family": "Korobov",
                "given": "Anatoly"
            },
            {
                "family": "Korviakov",
                "given": "Vladimir"
            },
            {
                "family": "Kozlov",
                "given": "Kirill"
            },
            {
                "family": "Krzhivokolskiy",
                "given": "Denis"
            },
            {
                "family": "Kuklev",
                "given": "Konstantin"
            },
            {
                "family": "Kunitsyn",
                "given": "Alexander"
            },
            {
                "family": "Kuzin",
                "given": "Sergey"
            },
            {
                "family": "Lakhtionov",
                "given": "Vladislav"
            },
            {
                "family": "Letunovskiy",
                "given": "Alexey"
            },
            {
                "family": "Litvinov",
                "given": "Maxim"
            },
            {
                "family": "Lyulkov",
                "given": "Alexander"
            },
            {
                "family": "Makarov",
                "given": "Georgy"
            },
            {
                "family": "Malakhov",
                "given": "Kirill"
            },
            {
                "family": "Malykh",
                "given": "Egor"
            },
            {
                "family": "Mamaev",
                "given": "Mikhail"
            },
            {
                "family": "Mikhailov",
                "given": "Dmitrii"
            },
            {
                "family": "Mikhailova",
                "given": "Polina"
            },
            {
                "family": "Mikheev",
                "given": "Ivan"
            },
            {
                "family": "Muromtseva",
                "given": "Elizaveta"
            },
            {
                "family": "Nazarkin",
                "given": "Nikolai"
            },
            {
                "family": "Nikulina",
                "given": "Tatiana"
            },
            {
                "family": "Novitskiy",
                "given": "Lev"
            },
            {
                "family": "Onuchin",
                "given": "Stanislav"
            },
            {
                "family": "Osterov",
                "given": "Nikita"
            },
            {
                "family": "Parkhomenko",
                "given": "Denis"
            },
            {
                "family": "Parpara",
                "given": "Anatoliy"
            },
            {
                "family": "Polovnikov",
                "given": "Vladimir"
            },
            {
                "family": "Reznikov",
                "given": "Konstantin"
            },
            {
                "family": "Saginbaev",
                "given": "Azat"
            },
            {
                "family": "Samsonov",
                "given": "Nikita"
            },
            {
                "family": "Sentsov",
                "given": "Alexander"
            },
            {
                "family": "Shaimov",
                "given": "Nikita"
            },
            {
                "family": "Sherstyuk",
                "given": "Artem"
            },
            {
                "family": "Shutkin",
                "given": "Andrey"
            },
            {
                "family": "Silvestrov",
                "given": "Egor"
            },
            {
                "family": "Suleimanov",
                "given": "Bulat"
            },
            {
                "family": "Suprunov",
                "given": "Matvey"
            },
            {
                "family": "Taranov",
                "given": "Sergey"
            },
            {
                "family": "Tolstykh",
                "given": "Irina"
            },
            {
                "family": "Trofimuk",
                "given": "Tatiana"
            },
            {
                "family": "Trushkin",
                "given": "Ilya"
            },
            {
                "family": "Tsybina",
                "given": "Aleksandra"
            },
            {
                "family": "Varlashina",
                "given": "Olga"
            },
            {
                "family": "Vasilev",
                "given": "Viacheslav"
            },
            {
                "family": "Vasiliev",
                "given": "Ilya"
            },
            {
                "family": "Vilisov",
                "given": "Eugeny"
            },
            {
                "family": "Yakubson",
                "given": "Sergey"
            },
            {
                "family": "Zakharov",
                "given": "Konstantin"
            }
        ],
        "URL": "https://omanscience.com/en/articles/kandinsky-6-0-video-foundation-models-for-synchronized-video-and-audio-generation",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "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."
    }
]