kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s-Diffusers

Habr | Project Page | Technical Report | 🤗 Video Lite / Video Pro / Image Lite | 🤗 Diffusers | ComfyUI

Kandinsky 5.0 I2V Pro Diffusers

Kandinsky 5.0 Pro line-up of large high quality video generation models (19B parameters). It offers high qualty generation in HD and more generation formats like I2V.

⚠️ Warning! all Pro models should be infered with pipeline.enable_model_cpu_offload()

import torch
from diffusers import Kandinsky5I2VPipeline
from diffusers.utils import export_to_video, load_image

pipe = Kandinsky5I2VPipeline.from_pretrained(
    "kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s-Diffusers",
    torch_dtype=torch.bfloat16,
)

pipe = pipe.to("cuda:0")
pipe.transformer.set_attention_backend("flex")
pipe.enable_model_cpu_offload()
pipe.transformer.compile(mode="max-autotune-no-cudagraphs", dynamic=True)

image = load_image(
    "https://img.freepik.com/free-photo/pug-dog-isolated-white-background_2829-11416.jpg?semt=ais_hybrid&w=740&q=80"
)

height = 640
width = 640
image = image.resize((width, height))

prompt = "A pug smiles happily holding a sign that says KANDINSKY"

negative_prompt = "Static, 2D cartoon, cartoon, 2d animation, paintings, images, worst quality, low quality, ugly, deformed, walking backwards"


output = pipe(
    image=image,
    prompt=prompt,
    negative_prompt=negative_prompt,
    height=height,
    width=width,
    num_frames=121,
    num_inference_steps=50,
    guidance_scale=5.0,
    num_videos_per_prompt=1,
    generator=torch.Generator(43)
)

Authors

Core Contributors:

• Video: Alexey Letunovskiy, Maria Kovaleva, Lev Novitskiy, Denis Koposov, Dmitrii Mikhailov, Anastasiia Kargapoltseva, Anna Dmitrienko, Anastasia Maltseva
• Image & Editing: Nikolai Vaulin, Nikita Kiselev, Alexander Varlamov
• Pre-training Data: Ivan Kirillov, Andrey Shutkin, Nikolai Vaulin, Ilya Vasiliev
• Post-training Data: Julia Agafonova, Anna Averchenkova, Olga Kim
• Research Consolidation & Paper: Viacheslav Vasilev, Vladimir Polovnikov

Contributors: Yury Kolabushin, Kirill Chernyshev, Alexander Belykh, Mikhail Mamaev, Anastasia Aliaskina, Kormilitsyn Semen, Tatiana Nikulina, Olga Vdovchenko, Polina Mikhailova, Polina Gavrilova, Nikita Osterov, Bulat Akhmatov

Track Leaders: Vladimir Arkhipkin, Vladimir Korviakov, Nikolai Gerasimenko, Denis Parkhomenko

Project Supervisor: Denis Dimitrov

Citation

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

Acknowledgements

We gratefully acknowledge the open-source projects and research that made Kandinsky 5.0 possible:

• PyTorch — for model training and inference.
• FlashAttention 3 — for efficient attention and faster inference.
• Qwen2.5-VL — for providing high-quality text embeddings.
• CLIP — for robust text–image alignment.
• HunyuanVideo — for video latent encoding and decoding.
• MagCache — for accelerated inference.
• ComfyUI — for integration into node-based workflows.

We deeply appreciate the contributions of these communities and researchers to the open-source ecosystem.