|
--- |
|
license: apache-2.0 |
|
--- |
|
|
|
## Open-Sora: Democratizing Efficient Video Production for All |
|
We present [Open-Sora](https://github.com/hpcaitech/Open-Sora), an initiative dedicated to **efficiently** produce high-quality video and make the model, |
|
tools and contents accessible to all. By embracing **open-source** principles, |
|
Open-Sora not only democratizes access to advanced video generation techniques, but also offers a |
|
streamlined and user-friendly platform that simplifies the complexities of video production. |
|
With Open-Sora, we aim to inspire innovation, creativity, and inclusivity in the realm of content creation. |
|
|
|
<h4>Open-Sora is still at an early stage and under active development.</h4> |
|
|
|
More details can be founded at [Open-Sora GitHub](https://github.com/hpcaitech/Open-Sora). |
|
|
|
|
|
## 📰 News |
|
|
|
* **[2024.03.18]** 🔥 We release **Open-Sora 1.0**, a fully open-source project for video generation. |
|
Open-Sora 1.0 supports a full pipeline of video data preprocessing, training with |
|
[ColossalAI](https://github.com/hpcaitech/ColossalAI) acceleration, |
|
inference, and more. Our provided checkpoints can produce 2s 512x512 videos with only 3 days training. |
|
[[blog]](https://hpc-ai.com/blog/open-sora-v1.0) |
|
* **[2024.03.04]** Open-Sora provides training with 46% cost reduction. |
|
[[blog]](https://hpc-ai.com/blog/open-sora) |
|
|
|
|
|
## 🛠 Usage |
|
|
|
You can launch this video generation with this model in a Gradio application. |
|
|
|
```bash |
|
# git clone Open-Sora |
|
git clone https://github.com/hpcaitech/Open-Sora.git |
|
cd Open-Sora |
|
|
|
# launch gradio |
|
python scripts/demo.py --model-type v1-16x256x256 |
|
``` |
|
|
|
If you want to use this STDiT model in code, |
|
|
|
```python |
|
from transformers import AutoModel |
|
|
|
stdit = AutoModel.from_pretrained("hpcai-tech/OpenSora-STDiT-v1-16x256x256") |
|
``` |
|
|
|
Do note that this model alone cannot generate video, it should work alongside a vae model and a text encoder model like how we did in the demo. |
|
|
|
|
|
|
