Improve model card for Kandinsky 5.0: Add metadata, links, usage, and citation (#2)

- Improve model card for Kandinsky 5.0: Add metadata, links, usage, and citation (c08ebf218462e5b4800853e530d98e2e35e7bdc5)


Co-authored-by: Niels Rogge <[email protected]>

README.md

@@ -1,3 +1,76 @@
 ---
 license: mit
----
+pipeline_tag: text-to-video
+library_name: diffusers
+---
+
+<div align="center">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="assets/KANDINSKY_LOGO_1_WHITE.png">
+    <source media="(prefers-color-scheme: light)" srcset="assets/KANDINSKY_LOGO_1_BLACK.png">
+    <img alt="Shows an illustrated sun in light mode and a moon with stars in dark mode." src="https://user-attachments.githubusercontent.com/25423296/163456779-a8556205-d0a5-45e2-ac17-42d089e3c3f8.png">
+  </picture>
+</div>
+
+<div align="center">
+  <a href="https://habr.com/ru/companies/sberbank/articles/951800/">Habr</a> | <a href="https://kandinskylab.ai/">Project Page</a> | <a href="https://arxiv.org/abs/2511.14993">Technical Report</a> | 🤗 <a href=https://huggingface.co/collections/kandinskylab/kandinsky-50-video-lite> Video Lite </a> / <a href=https://huggingface.co/collections/kandinskylab/kandinsky-50-video-pro> Video Pro </a> / <a href=https://huggingface.co/collections/kandinskylab/kandinsky-50-image-lite> Image Lite </a> | <a href="https://huggingface.co/docs/diffusers/main/en/api/pipelines/kandinsky5"> 🤗 Diffusers </a>  | <a href="https://github.com/kandinskylab/kandinsky-5/blob/main/comfyui/README.md">ComfyUI</a>
+</div>
+
+# Kandinsky 5.0: A family of diffusion models for Video & Image generation
+
+This repository provides a family of state-of-the-art diffusion models for high-resolution image and 10-second video synthesis, presented in the paper "Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation". The framework includes Kandinsky 5.0 Image Lite for image generation, and Kandinsky 5.0 Video Lite and Video Pro for fast and high-quality text-to-video and image-to-video generation.
+
+-   **Paper**: [Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation](https://huggingface.co/papers/2511.14993)
+-   **Project Page**: https://kandinskylab.ai/
+-   **Code**: https://github.com/kandinskylab/kandinsky-5
+
+## Sample Usage
+
+You can use the `kandinsky` library, which integrates with `diffusers`, to perform text-to-video inference.
+
+First, clone the repository and install dependencies:
+```bash
+git clone https://github.com/kandinskylab/kandinsky-5.git
+cd kandinsky-5
+pip install -r requirements.txt
+```
+
+Then, you can use the following Python snippet for text-to-video generation:
+
+```python
+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",
+)
+```
+
+## Citation
+
+If you find Kandinsky 5.0 useful in your research, please cite the following paper:
+
+```bibtex
+@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}, 
+}
+```