Kandinsky 5.0: A family of diffusion models for Video & Image generation

Project Updates

• 🔥 Source: 2025/09/29: We have open-sourced Kandinsky 5.0 T2V Lite a lite (2B parameters) version of Kandinsky 5.0 Video text-to-video generation model. Released checkpoints: kandinsky5lite_t2v_pretrain_5s, kandinsky5lite_t2v_pretrain_10s, kandinsky5lite_t2v_sft_5s, kandinsky5lite_t2v_sft_10s, kandinsky5lite_t2v_nocfg_5s, kandinsky5lite_t2v_nocfg_10s, kandinsky5lite_t2v_distilled16steps_5s, kandinsky5lite_t2v_distilled16steps_10s contains weight from pretrain, supervised finetuning, cfg distillation and diffusion distillation into 16 steps. 5s checkpoints are capable of generating videos up to 5 seconds long. 10s checkpoints is faster models checkpoints trained with NABLA algorithm and capable to generate videos up to 10 seconds long.

Kandinsky 5.0 T2V Lite

• SFT model — delivers the highest generation quality;
• CFG-distilled — runs 2× faster;
• Diffusion-distilled — enables low-latency generation with minimal quality loss (6× faster);
• Pretrain model — designed for fine-tuning by researchers and enthusiasts.

Pipeline

• Qwen2.5-VL and CLIP provides text embeddings.
• HunyuanVideo 3D VAE encodes/decodes video into a latent space.
• DiT is the main generative module using cross-attention to condition on text.

Model Zoo

Examples:

Kandinsky 5.0 T2V Lite SFT

Kandinsky 5.0 T2V Lite Distill

Results:

Side-by-Side evaluation

Distill Side-by-Side evaluation

VBench results

Quickstart

Installation

Model Download

Run Kandinsky 5.0 T2V Lite SFT 5s

Run Kandinsky 5.0 T2V Lite SFT 10s

Run Kandinsky 5.0 T2V Lite pretrain 5s

Run Kandinsky 5.0 T2V Lite pretrain 10s

Run Kandinsky 5.0 T2V Lite no-CFG 5s

Run Kandinsky 5.0 T2V Lite no-CFG 10s

Run Kandinsky 5.0 T2V Lite distill 5s

Run Kandinsky 5.0 T2V Lite distill 10s

Inference

Distributed Inference

NUMBER_OF_NODES=1
NUMBER_OF_DEVICES_PER_NODE=1 / 2 / 4
python -m torch.distributed.launch --nnodes $NUMBER_OF_NODES --nproc-per-node $NUMBER_OF_DEVICES_PER_NODE test.py

Optimized Inference

Offloading

Magcache

ComfyUI

Beta testing

📑 Todo List

• Kandinsky 5.0 Lite Text-to-Video
  • Multi-GPU Inference code of the 2B models
  • Checkpoints 2B models
    • pretrain
    • sft
    • rl
    • cfg distil
    • distil 16 steps
    • autoregressive generation
  • ComfyUI integration
  • Diffusers integration
  • Caching acceleration support
• Kandinsky 5.0 Lite Image-to-Video
  • Multi-GPU Inference code of the 2B model
  • Checkpoints of the 2B model
  • ComfyUI integration
  • Diffusers integration
• Kandinsky 5.0 Pro Text-to-Video
  • Multi-GPU Inference code of the models
  • Checkpoints of the model
  • ComfyUI integration
  • Diffusers integration
• Kandinsky 5.0 Pro Image-to-Video
  • Multi-GPU Inference code of the model
  • Checkpoints of the model
  • ComfyUI integration
  • Diffusers integration
• Technical report

Authors

Citation

@misc{kandinsky2025,
    author = {Alexey Letunovskiy, Maria Kovaleva, Ivan Kirillov, Lev Novitskiy, Denis Koposov,
              Dmitrii Mikhailov, Anna Averchenkova, Andrey Shutkin, Julia Agafonova, Olga Kim,
              Anastasiia Kargapoltseva, Nikita Kiselev, Vladimir Arkhipkin, Vladimir Korviakov,
              Nikolai Gerasimenko, Denis Parkhomenko, Anna Dmitrienko, Anastasia Maltseva,
              Kirill Chernyshev, Ilia Vasiliev, Viacheslav Vasilev, Vladimir Polovnikov,
              Yury Kolabushin, Alexander Belykh, Mikhail Mamaev, Anastasia Aliaskina,
              Tatiana Nikulina, Polina Gavrilova, Denis Dimitrov},
    title = {Kandinsky 5.0: A family of diffusion models for Video & Image generation},
    howpublished = {\url{https://github.com/ai-forever/Kandinsky-5}},
    year = 2025
}

@misc{mikhailov2025nablanablaneighborhoodadaptiveblocklevel,
      title={$\nabla$NABLA: Neighborhood Adaptive Block-Level Attention}, 
      author={Dmitrii Mikhailov and Aleksey Letunovskiy and Maria Kovaleva and Vladimir Arkhipkin
              and Vladimir Korviakov and Vladimir Polovnikov and Viacheslav Vasilev
              and Evelina Sidorova and Denis Dimitrov},
      year={2025},
      eprint={2507.13546},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2507.13546}, 
}