Instructions to use epfl-vita/svi-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use epfl-vita/svi-model with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("epfl-vita/svi-model", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -23,13 +23,14 @@ papers:
|
|
| 23 |
|
| 24 |
<div align="center">
|
| 25 |
|
| 26 |
-
<h1>Stable Video Infinity: Infinite-Length Video Generation with Error Recycling<h1>
|
| 27 |
|
| 28 |
<p align="center">
|
| 29 |
<a href="https://huggingface.co/papers/2510.09212"> <img src="https://img.shields.io/badge/Paper-HuggingFace-red?logo=huggingface&logoColor=yellow" alt="Paper on Hugging Face"/> </a>
|
| 30 |
<a href="https://stable-video-infinity.github.io/homepage/"> <img src="https://img.shields.io/badge/Project-Page-green" alt="Project Page"/> </a>
|
| 31 |
<a href="https://github.com/vita-epfl/Stable-Video-Infinity"> <img src="https://img.shields.io/badge/SVI-GitHub-black?logo=github&logoColor=white" alt="SVI on GitHub"/> </a>
|
| 32 |
<a href="https://huggingface.co/datasets/vita-video-gen/svi-benchmark"> <img src="https://img.shields.io/badge/SVI_Dataset-Hugging%20Face-orange?logo=huggingface&logoColor=yellow" alt="SVI Dataset"/> </a>
|
|
|
|
| 33 |
<a href="https://huggingface.co/vita-video-gen/svi-model"> <img src="https://img.shields.io/badge/SVI_models-Hugging%20Face-FFCC00?logo=huggingface&logoColor=yellow" alt="SVI Models"/> </a> </p> </div>
|
| 34 |
|
| 35 |
## 🎯 About This Repository
|
|
@@ -41,6 +42,17 @@ This repository contains the model weights of SVI Family.
|
|
| 41 |
- **Infinite Length**: No inherent limit on video duration; generate arbitrarily long stories (see the 10‑minute “Tom and Jerry” demo).
|
| 42 |
- **Versatile**: Supports diverse in-the-wild generation tasks: multi-scene short films, single‑scene animations, skeleton-/audio-conditioned generation, cartoons, and more.
|
| 43 |
- **Efficient**: Only LoRA adapters are tuned, requiring very little training data: anyone can make their own SVI easily.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
## 📦 Resources
|
| 45 |
| **Model** | **Task** | **Input** | **Output** | **Hugging Face Link** | **Comments** |
|
| 46 |
|-------|------|-------|--------|-------------------|------------------|
|
|
@@ -65,4 +77,4 @@ If you find our work helpful for your research, please consider citing our paper
|
|
| 65 |
year={2025},
|
| 66 |
url={https://huggingface.co/papers/2510.09212},
|
| 67 |
}
|
| 68 |
-
```
|
|
|
|
| 23 |
|
| 24 |
<div align="center">
|
| 25 |
|
| 26 |
+
<h1>Stable Video Infinity: Infinite-Length Video Generation with Error Recycling</h1>
|
| 27 |
|
| 28 |
<p align="center">
|
| 29 |
<a href="https://huggingface.co/papers/2510.09212"> <img src="https://img.shields.io/badge/Paper-HuggingFace-red?logo=huggingface&logoColor=yellow" alt="Paper on Hugging Face"/> </a>
|
| 30 |
<a href="https://stable-video-infinity.github.io/homepage/"> <img src="https://img.shields.io/badge/Project-Page-green" alt="Project Page"/> </a>
|
| 31 |
<a href="https://github.com/vita-epfl/Stable-Video-Infinity"> <img src="https://img.shields.io/badge/SVI-GitHub-black?logo=github&logoColor=white" alt="SVI on GitHub"/> </a>
|
| 32 |
<a href="https://huggingface.co/datasets/vita-video-gen/svi-benchmark"> <img src="https://img.shields.io/badge/SVI_Dataset-Hugging%20Face-orange?logo=huggingface&logoColor=yellow" alt="SVI Dataset"/> </a>
|
| 33 |
+
<a href="https://www.modelscope.cn/models/epfl-vita/svi-model"> <img src="https://img.shields.io/badge/SVI_Model-ModelScope-624AFF?logo=alibabacloud&logoColor=white" alt="SVI Model on ModelScope"/> </a>
|
| 34 |
<a href="https://huggingface.co/vita-video-gen/svi-model"> <img src="https://img.shields.io/badge/SVI_models-Hugging%20Face-FFCC00?logo=huggingface&logoColor=yellow" alt="SVI Models"/> </a> </p> </div>
|
| 35 |
|
| 36 |
## 🎯 About This Repository
|
|
|
|
| 42 |
- **Infinite Length**: No inherent limit on video duration; generate arbitrarily long stories (see the 10‑minute “Tom and Jerry” demo).
|
| 43 |
- **Versatile**: Supports diverse in-the-wild generation tasks: multi-scene short films, single‑scene animations, skeleton-/audio-conditioned generation, cartoons, and more.
|
| 44 |
- **Efficient**: Only LoRA adapters are tuned, requiring very little training data: anyone can make their own SVI easily.
|
| 45 |
+
|
| 46 |
+
## 🚀 Quick Access
|
| 47 |
+
|
| 48 |
+
For users who prefer ModelScope, the SVI model weights are also mirrored here:
|
| 49 |
+
|
| 50 |
+
<p align="center">
|
| 51 |
+
<a href="https://www.modelscope.cn/models/epfl-vita/svi-model">
|
| 52 |
+
<img src="https://img.shields.io/badge/Download%20on-ModelScope-624AFF?style=for-the-badge&logo=alibabacloud&logoColor=white" alt="Download SVI on ModelScope"/>
|
| 53 |
+
</a>
|
| 54 |
+
</p>
|
| 55 |
+
|
| 56 |
## 📦 Resources
|
| 57 |
| **Model** | **Task** | **Input** | **Output** | **Hugging Face Link** | **Comments** |
|
| 58 |
|-------|------|-------|--------|-------------------|------------------|
|
|
|
|
| 77 |
year={2025},
|
| 78 |
url={https://huggingface.co/papers/2510.09212},
|
| 79 |
}
|
| 80 |
+
```
|