Upload 30 files

.gitattributes

@@ -33,3 +33,30 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/comfyui_kandinsky5.png filter=lfs diff=lfs merge=lfs -text
+assets/generation_examples/1036335634.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/generation_examples/1512407739[[:space:]](1).mp4 filter=lfs diff=lfs merge=lfs -text
+assets/generation_examples/1512407739.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/generation_examples/642423904[[:space:]](1).mp4 filter=lfs diff=lfs merge=lfs -text
+assets/generation_examples/642423904[[:space:]](2).mp4 filter=lfs diff=lfs merge=lfs -text
+assets/generation_examples/642423904.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/generation_examples/68941856[[:space:]](1).mp4 filter=lfs diff=lfs merge=lfs -text
+assets/generation_examples/68941856.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/generation_examples/distill/1.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/generation_examples/distill/2.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/generation_examples/distill/3.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/generation_examples/distill/4.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/generation_examples/sft/1.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/generation_examples/sft/2.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/generation_examples/sft/3.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/generation_examples/sft/4.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/generation_examples/sft/5.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/generation_examples/sft/6.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/generation_examples/test[[:space:]](1)[[:space:]](1).mp4 filter=lfs diff=lfs merge=lfs -text
+assets/generation_examples/test2[[:space:]](1).mp4 filter=lfs diff=lfs merge=lfs -text
+assets/generation_examples/video5237959401997893857.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/sbs/kandinsky_5_video_lite_vs_sora.jpg filter=lfs diff=lfs merge=lfs -text
+assets/sbs/kandinsky_5_video_lite_vs_wan_2.1_14B.jpg filter=lfs diff=lfs merge=lfs -text
+assets/sbs/kandinsky_5_video_lite_vs_wan_2.2_5B.jpg filter=lfs diff=lfs merge=lfs -text
+assets/sbs/kandinsky_5_video_lite_vs_wan_2.2_A14B.jpg filter=lfs diff=lfs merge=lfs -text
+assets/vbench.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,327 @@
+<div align="center">
+  <picture>
+    <img src="assets/KANDINSKY_LOGO_1_BLACK.png">
+  </picture>
+</div>
+
+<div align="center">
+  <a href="">Habr</a> | <a href="https://gen-ai-team.github.io/kandinsky-5-inference/">Project Page</a> | Technical Report (soon) | <a href=https://huggingface.co/collections/ai-forever/kandisnky-50-t2v-lite-68d71892d2cc9b02177e5ae5> Models🤗 </a>
+</div>
+
+<h1>Kandinsky 5.0: A family of diffusion models for Video & Image generation</h1>
+
+In this repository, we provide a family of diffusion models to generate a video or an image (<em>Coming Soon</em>) given a textual prompt and distilled model for faster generation.
+
+https://github.com/user-attachments/assets/b9ff0417-02a4-4f6b-aacc-60c44e7fe6f1
+
+## 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 distillation in 16 steps. 5s checkpoints are capable of generating videos up to 5 seconds long. 10s checkpoints is faster models checkpoints trained with [NABLA](https://huggingface.co/ai-forever/Wan2.1-T2V-14B-NABLA-0.7) algorithm and capable to generate videos up to 10 seconds long.
+
+## Kandinsky 5.0 T2V Lite
+
+Kandinsky 5.0 T2V Lite is a lightweight video generation model (2B parameters) that ranks #1 among open-source models in its class. It outperforms larger Wan models (5B and 14B) and offers the best understanding of Russian concepts in the open-source ecosystem.
+
+We provide 8 model variants, each optimized for different use cases:
+
+* 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.
+
+All models are available in two versions: for generating 5-second and 10-second videos.
+
+## Pipeline
+
+**Latent diffusion pipeline** with **Flow Matching**.
+
+**Diffusion Transformer (DiT)** as the main generative backbone with **cross-attention to text embeddings**.
+
+- **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.
+
+<img width="1600" height="477" alt="Picture1" src="https://github.com/user-attachments/assets/17fc2eb5-05e3-4591-9ec6-0f6e1ca397b3" />
+
+<img width="800" height="406" alt="Picture2" src="https://github.com/user-attachments/assets/f3006742-e261-4c39-b7dc-e39330be9a09" />
+
+
+## Model Zoo
+
+| Model                               | config | video duration | NFE | Checkpoint | Latency* (H100) | VBench score |
+|-------------------------------------|--------|----------------|-----|------------|----------------|--------------|
+| Kandinsky 5.0 T2V Lite SFT 5s       |configs/config_5s_sft.yaml | 5s             | 100 |🤗 [HF](https://huggingface.co/ai-forever/Kandinsky-5.0-T2V-Lite-sft-5s) |      139 s     |     84.02    |
+| Kandinsky 5.0 T2V Lite SFT 10s      |configs/config_10s_sft.yaml| 10s            | 100 |🤗 [HF](https://huggingface.co/ai-forever/Kandinsky-5.0-T2V-Lite-sft-10s) |      224 s     |     85.36    |
+| Kandinsky 5.0 T2V Lite pretrain 5s  |configs/config_5s_pretrain.yaml | 5s             | 100 |🤗 [HF](https://huggingface.co/ai-forever/Kandinsky-5.0-T2V-Lite-pretrain-5s) |      139 s      |              |
+| Kandinsky 5.0 T2V Lite pretrain 10s |configs/config_10s_pretrain.yaml | 10s            | 100 |🤗 [HF](https://huggingface.co/ai-forever/Kandinsky-5.0-T2V-Lite-pretrain-10s) |     224 s      |              |
+| Kandinsky 5.0 T2V Lite no-CFG 5s    |configs/config_5s_nocfg.yaml| 5s             | 50  |🤗 [HF](https://huggingface.co/ai-forever/Kandinsky-5.0-T2V-Lite-nocfg-5s) |       77 s     |              |
+| Kandinsky 5.0 T2V Lite no-CFG 10s   |configs/config_10s_nocfg.yaml| 10s            | 50  |🤗 [HF](https://huggingface.co/ai-forever/Kandinsky-5.0-T2V-Lite-nocfg-10s) |     124 s      |              |
+| Kandinsky 5.0 T2V Lite distill 5s   |configs/config_5s_distil.yaml| 5s             | 16  | 🤗 [HF](https://huggingface.co/ai-forever/Kandinsky-5.0-T2V-Lite-distilled16steps-5s)|       35 s     |              |
+| Kandinsky 5.0 T2V Lite distill 10s  |        | 10s            | 16  |            |      55 s      |              |
+
+*Latency was measured after the second inference run. The first run of the model can be slower due to the compilation process. For 5-second models Flash Attention 3 was used.
+
+### Examples:
+
+#### Kandinsky 5.0 T2V Lite SFT
+
+<table border="0" style="width: 200; text-align: left; margin-top: 20px;">
+  <tr>
+      <td>
+          <video src="https://github.com/user-attachments/assets/bc38821b-f9f1-46db-885f-1f70464669eb" width=200 controls autoplay loop></video>
+      </td>
+      <td>
+          <video src="https://github.com/user-attachments/assets/9f64c940-4df8-4c51-bd81-a05de8e70fc3" width=200 controls autoplay loop></video>
+      </td>
+  <tr>
+      <td>
+          <video src="https://github.com/user-attachments/assets/77dd417f-e0bf-42bd-8d80-daffcd054add" width=200 controls autoplay loop></video>
+      </td>
+      <td>
+          <video src="https://github.com/user-attachments/assets/385a0076-f01c-4663-aa46-6ce50352b9ed" width=200 controls autoplay loop></video>
+      </td>
+  <tr>
+      <td>
+          <video src="https://github.com/user-attachments/assets/7c1bcb31-cc7d-4385-9a33-2b0cc28393dd" width=200 controls autoplay loop></video>
+      </td>
+      <td>
+          <video src="https://github.com/user-attachments/assets/990a8a0b-2df1-4bbc-b2e3-2859b6f1eea6" width=200 controls autoplay loop></video>
+      </td>
+  </tr>
+
+</table>
+
+
+#### Kandinsky 5.0 T2V Lite Distill
+
+<table border="0" style="width: 200; text-align: left; margin-top: 20px;">
+  <tr>
+      <td>
+          <video src="https://github.com/user-attachments/assets/861342f9-f576-4083-8a3b-94570a970d58" width=200 controls autoplay loop></video>
+      </td>
+      <td>
+          <video src="https://github.com/user-attachments/assets/302e4e7d-781d-4a58-9b10-8c473d469c4b" width=200 controls autoplay loop></video>
+      </td>
+  <tr>
+      <td>
+          <video src="https://github.com/user-attachments/assets/3e70175c-40e5-4aec-b506-38006fe91a76" width=200 controls autoplay loop></video>
+      </td>
+      <td>
+          <video src="https://github.com/user-attachments/assets/b7da85f7-8b62-4d46-9460-7f0e505de810" width=200 controls autoplay loop></video>
+      </td>
+
+</table>
+
+### Results:
+
+#### Side-by-Side evaluation
+
+The evaluation is based on the expanded prompts from the [Movie Gen benchmark](https://github.com/facebookresearch/MovieGenBench), which are available in the expanded_prompt column of the benchmark/moviegen_bench.csv file.
+
+<table border="0" style="width: 400; text-align: left; margin-top: 20px;">
+  <tr>
+      <td>
+          <img src="assets/sbs/kandinsky_5_video_lite_vs_sora.jpg" width=400 ></img>
+      </td>
+      <td>
+          <img src="assets/sbs/kandinsky_5_video_lite_vs_wan_2.1_14B.jpg" width=400 ></img>
+      </td>
+  <tr>
+      <td>
+          <img src="assets/sbs/kandinsky_5_video_lite_vs_wan_2.2_5B.jpg" width=400 ></img>
+      </td>
+      <td>
+          <img src="assets/sbs/kandinsky_5_video_lite_vs_wan_2.2_A14B.jpg" width=400 ></img>
+      </td>
+
+</table>
+
+#### VBench results
+
+<div align="center">
+  <picture>
+    <img src="assets/vbench.png">
+  </picture>
+</div>
+
+## Quickstart
+
+#### Installation
+Clone the repo:
+```sh
+git clone https://github.com/ai-forever/Kandinsky-5.git
+cd Kandinsky-5
+```
+
+Install dependencies:
+```sh
+pip install -r requirements.txt
+```
+
+To improve inference performance on NVidia Hopper GPUs, we recommend installing [Flash Attention 3](https://github.com/Dao-AILab/flash-attention/?tab=readme-ov-file#flashattention-3-beta-release).
+
+#### Model Download
+```sh
+python download_models.py
+```
+
+#### Run Kandinsky 5.0 T2V Lite SFT 5s
+
+```sh
+python test.py --prompt "A dog in red hat"
+```
+
+#### Run Kandinsky 5.0 T2V Lite SFT 10s 
+
+```sh
+python test.py --config ./configs/config_10s_sft.yaml --prompt "A dog in red hat" --video_duration 10 
+```
+
+#### Run Kandinsky 5.0 T2V Lite pretrain 5s
+
+```sh
+python test.py --config ./configs/config_5s_pretrain.yaml --prompt "A dog in red hat"
+```
+
+#### Run Kandinsky 5.0 T2V Lite pretrain 10s
+
+```sh
+python test.py --config ./configs/config_10s_pretrain.yaml --prompt "A dog in red hat" --video_duration 10
+```
+
+#### Run Kandinsky 5.0 T2V Lite no-CFG 5s
+
+```sh
+python test.py --config ./configs/config_5s_nocfg.yaml --prompt "A dog in red hat" 
+```
+
+#### Run Kandinsky 5.0 T2V Lite no-CFG 10s
+
+```sh
+python test.py --config ./configs/config_10s_nocfg.yaml --prompt "A dog in red hat" --video_duration 10
+```
+
+#### Run Kandinsky 5.0 T2V Lite distill 5s
+
+```sh
+python test.py --config ./configs/config_5s_distil.yaml --prompt "A dog in red hat"          
+```
+
+#### Run Kandinsky 5.0 T2V Lite distill 10s
+
+Coming soon
+
+### Inference
+
+```python
+import torch
+from IPython.display import Video
+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/config_5s_sft.yaml")
+
+images = pipe(
+    seed=42,
+    time_length=5,
+    width=768,
+    height=512,
+    save_path="./test.mp4",
+    text="A cat in a red hat",
+)
+
+Video("./test.mp4")
+```
+
+Please, refer to [inference_example.ipynb](inference_example.ipynb) notebook for more usage details.
+
+### Distributed Inference
+
+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
+```
+
+### ComfyUI
+
+See the instruction [here](comfyui)
+
+## 📑 Todo List
+- Kandinsky 5.0 Lite Text-to-Video
+    - [x] Multi-GPU Inference code of the 2B models
+    - [ ] Checkpoints 2B models
+      - [x]  pretrain
+      - [x] sft
+      - [ ] rl
+      - [x] cfg distil 
+      - [x] distil 16 steps
+      - [ ] autoregressive generation
+    - [x] 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
+<B>Project Leader:</B> Denis Dimitrov</br>
+
+<B>Team Leads:</B> Vladimir Arkhipkin, Vladimir Korviakov, Nikolai Gerasimenko, Denis Parkhomenko</br>
+
+<B>Core Contributors:</B> Alexey Letunovskiy, Maria Kovaleva, Ivan Kirillov, Lev Novitskiy, Denis Koposov, Dmitrii Mikhailov, Anna Averchenkova, Andrey Shutkin, Julia Agafonova, Olga Kim, Anastasiia Kargapoltseva, Nikita Kiselev</br>
+
+<B>Contributors:</B> Anna Dmitrienko,  Anastasia Maltseva, Kirill Chernyshev, Ilia Vasiliev, Viacheslav Vasilev, Vladimir Polovnikov, Yury Kolabushin, Alexander Belykh, Mikhail Mamaev, Anastasia Aliaskina, Tatiana Nikulina, Polina Gavrilova</br>
+
+# 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}, 
+}
+```

assets/generation_examples/1036335634.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d3657c36760e1694a4d3533b04e0d28ddd16d8d8e6373953e8f754742e2a54b
+size 4199589

assets/generation_examples/1512407739 (1).mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54b887c2c5cca6a4b5d8cc7f433a01a1c72c2592f07187b3c530126ac77aa601
+size 7227407

assets/generation_examples/1512407739.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00f48b1d0ddd97c7d802136d1a9090eb397ce34d95569fd4c4d6eb64eb46d06f
+size 6778347

assets/generation_examples/642423904 (1).mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:612d2a1340475f79b20f90cc5e85a5b9e79193af631e8bd7fa50cdc5fc47dee8
+size 3038994

assets/generation_examples/642423904 (2).mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55bed6367e8c4de29f082cfbaa8af357fef81dc339e8abbadea50901ac635d10
+size 3092127

assets/generation_examples/642423904.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:464da305ce36af41a1fb7fa842de1357b601008d128f1693f12f9674c906243c
+size 2466511

assets/generation_examples/68941856 (1).mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8274aa1cbc087465f6a1b72842c8d1cb1860c61232dd29ee0f17ea7ff2d2ac08
+size 5856930

assets/generation_examples/68941856.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:759e825e4b6bd05ab92621390b1f5aa97240cd18a76312395ff39fd636dc8a9d
+size 6942715

assets/generation_examples/distill/1.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06953c45987011d08aef79f7ae1368f9a69d480a509554fb55d0d46d4498255f
+size 6916245

assets/generation_examples/distill/2.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d199141bd7cffb4cb30ac84f2879da330b83cd2429aa7a95c3406f8dce49134a
+size 5384100

assets/generation_examples/distill/3.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bfdc9c8cf2ada22de4ffc1d0281e56ed7c0d61a66bdff28697cbe6a2a8e97f5
+size 3957258

assets/generation_examples/distill/4.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bbebdd5de15721f082785bbc02dc7422b0d9d9a6ac244c02e1bfbecc22ba22e
+size 6328091

assets/generation_examples/sft/1.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bfc00348d1fdb09c43687e086cd912ba15097ecf3f85b6302827a54eafab3a2
+size 4486280

assets/generation_examples/sft/2.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:612eb63051314d50bb333ee1c797e95a5df7522ca5df3dc853266b135a27ce06
+size 4600755

assets/generation_examples/sft/3.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8cc13e558964138ef53a098d4b1174db5a58979f7dbf021788a39ad41c2fcff
+size 8193301

assets/generation_examples/sft/4.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:462f02343590e07e5ac2a919f566438d2ddd990d0c5ddcd8c92e15feae63eb11
+size 7697517

assets/generation_examples/sft/5.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e89d9d0ae048df05fc2f00e9acc009a261b38810f5792967a969bb3147a5e6d
+size 3528986

assets/generation_examples/sft/6.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8226569ad637d3b179ce895685e52cfcf81372bbbab623386fddde8e0352c9db
+size 4109417

assets/generation_examples/test (1) (1).mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:949f1a6c6056307026430aa0809fc7b02ac6deb3732973b305aaad20e6754c76
+size 1592811

assets/generation_examples/test2 (1).mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d626185c2e14dcca33b4e315529dd9555fc34f9dc96a327a28935bdb659406b
+size 1103150

assets/generation_examples/video5237959401997893857.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4df397dc2d8032875aaccb58ef563f90c6cd25d50ce73bae40c5776dc9818ac0
+size 5977768