In this repository, we provide a family of diffusion models to generate a video or an image given a textual prompt and/or image.
https://github.com/user-attachments/assets/b06f56de-1b05-4def-a611-1a3159ed71b0
Kandinsky 5.0 Video Pro is a line-up of 19B models that generates high-quality HD videos from English and Russian prompts with controllable camera motion.
We provide several Text-to-Video model variants, each optimized for different use cases:
SFT model — delivers the highest generation quality;
Pretrain model — designed for fine-tuning by researchers and enthusiasts.
All models are available in two versions: for generating 5-second and 10-second videos.
Additionally, we provide Image-to-Video model capable to generate video given input image and text prompt.
| Model | config | video duration | NFE | Checkpoint | Latency* |
|---|---|---|---|---|---|
| Kandinsky 5.0 T2V Pro SFT 5s HD | configs/k5_pro_t2v_5s_sft_hd.yaml | 5s | 100 | 🤗 HF | 1241 |
| Kandinsky 5.0 T2V Pro SFT 10s HD | configs/k5_pro_t2v_10s_sft_hd.yaml | 10s | 100 | 🤗 HF | - |
| Kandinsky 5.0 T2V Pro SFT 5s SD | configs/k5_pro_t2v_5s_sft_sd.yaml | 5s | 100 | 🤗 HF | 560 |
| Kandinsky 5.0 T2V Pro SFT 10s SD | configs/k5_pro_t2v_10s_sft_sd.yaml | 10s | 100 | 🤗 HF | 1158 |
| Kandinsky 5.0 T2V Pro pretrain 5s HD | - | 5s | 100 | 🤗 HF | 1241 |
| Kandinsky 5.0 T2V Pro pretrain 10s HD | - | 10s | 100 | 🤗 HF | - |
| Kandinsky 5.0 T2V Pro pretrain 5s SD | - | 5s | 100 | 🤗 HF | 560 |
| Kandinsky 5.0 T2V Pro pretrain 10s SD | - | 10s | 100 | 🤗 HF | 1158 |
| Kandinsky 5.0 I2V Pro HD 5s | configs/k5_pro_i2v_5s_sft_hd.yaml | 5s | 100 | 🤗 HF | - |
| Kandinsky 5.0 I2V Pro SD 5s | configs/k5_pro_i2v_5s_sft_sd.yaml | 5s | 100 | 🤗 HF | - |
*Latency was measured after the second inference run. The first run of the model can be slower due to the compilation process. Inference was measured on an NVIDIA H100 GPU with 80 GB of memory, using CUDA 12.8.1 and PyTorch 2.8. For 5-second models Flash Attention 3 was used.
|
|
| Comparison with Veo 3 | Comparison with Veo 3 fast |
|
|
| Comparison with Wan 2.2 A14B Text-to-Video mode | Comparison with Wan 2.2 A14B Image-to-Video mode |
Clone the repo:
git clone https://github.com/kandinskylab/kandinsky-5.git
cd kandinsky-5
Install dependencies:
pip install -r requirements.txt
To improve inference performance on NVidia Hopper GPUs, we recommend installing Flash Attention 3.
python download_models.py
use models argument to download some specific models, otherwise all models will be downloaded
example to download only kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s and kandinskylab/Kandinsky-5.0-T2V-Pro-sft-5s:
python download_models.py --models kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s,kandinskylab/Kandinsky-5.0-T2V-Pro-sft-5s
python test.py --prompt "A dog in red hat"
python test.py --config ./configs/k5_lite_t2v_10s_sft_sd.yaml --prompt "A dog in red hat" --video_duration 10
python test.py --config ./configs/k5_lite_i2v_5s_sft_sd.yaml --prompt "The bear plays balalaika." --image "./assets/test_image.jpg" --video_duration 5
import torch
from kandinsky import get_T2V_pipeline
device_map = {
"dit": torch.device('cuda:0'),
"vae": torch.device('cuda:0'),
"text_embedder": torch.device('cuda:0')
}
pipe = get_T2V_pipeline(device_map, conf_path="configs/k5_lite_t2v_5s_sft_sd.yaml")
images = pipe(
seed=42,
time_length=5,
width=768,
height=512,
save_path="./test.mp4",
text="A cat in a red hat",
)
import torch
from kandinsky import get_I2V_pipeline
device_map = {
"dit": torch.device('cuda:0'),
"vae": torch.device('cuda:0'),
"text_embedder": torch.device('cuda:0')
}
pipe = get_I2V_pipeline(device_map, conf_path="configs/k5_lite_i2v_5s_sft_sd.yaml")
images = pipe(
seed=42,
time_length=5,
save_path='./test.mp4',
text="The bear plays balalaika.",
image = "assets/test_image.jpg",
)
Please, refer to examples folder in github for more examples in various notebooks.
For a faster inference, we also provide the capability to perform inference in a distributed way:
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
For less memory consumption you can use offloading of the models.
python test.py --prompt "A dog in red hat" --offload
Also we provide Magcache inference for faster generations (now available for sft 5s and sft 10s checkpoints).
python test.py --prompt "A dog in red hat" --magcache
To reduce GPU memory needed for Qwen encoder we provide option to use NF4-quantized version from bitsandbytes.
python test.py --prompt "A dog in red hat" --qwen_quantization
Depending on your hardware you can use the follwing full attention algorithm implementation:
The attention algorithm can be selected using an option "--attention_engine" of test.py script for 5 second (and less) video generation. For 10-second generation we use sparse attention algorithm NABLA.
Note that currently (19 Oct. 2025) version build from source contains a bug and produces noisy output. A temporary workaround to fix it is decribed here.
python test.py --prompt "A dog in red hat" --attention_engine=flash_attention_3
python test.py --prompt "A dog in red hat" --attention_engine=flash_attention_2
python test.py --prompt "A dog in red hat" --attention_engine=sdpa
python test.py --prompt "A dog in red hat" --attention_engine=sage
By default we use option --attention_engine=auto which enables automatic selection of the most optimal algorithm installed in your system.
cache-dit offers Fully Cache Acceleration support for Kandinsky-5 with DBCache, TaylorSeer and Cache CFG. Visit their example for more details.
You can apply to participate in the beta testing of the Kandinsky Video Lite via the telegram bot.
Core Contributors:
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
@misc{arkhipkin2025kandinsky50familyfoundation,
title={Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation},
author={Vladimir Arkhipkin and Vladimir Korviakov and Nikolai Gerasimenko and Denis Parkhomenko and Viacheslav Vasilev and Alexey Letunovskiy and Nikolai Vaulin and Maria Kovaleva and Ivan Kirillov and Lev Novitskiy and Denis Koposov and Nikita Kiselev and Alexander Varlamov and Dmitrii Mikhailov and Vladimir Polovnikov and Andrey Shutkin and Julia Agafonova and Ilya Vasiliev and Anastasiia Kargapoltseva and Anna Dmitrienko and Anastasia Maltseva and Anna Averchenkova and Olga Kim and Tatiana Nikulina and Denis Dimitrov},
year={2025},
eprint={2511.14993},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2511.14993},
}
@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},
}
We gratefully acknowledge the open-source projects and research that made Kandinsky 5.0 possible:
We deeply appreciate the contributions of these communities and researchers to the open-source ecosystem.