nicolabs/Open-Sora
1
0
Fork 0
mirror of https://github.com/hpcaitech/Open-Sora.git synced 2026-04-09 20:33:26 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

add DCAE download cmd (#817)

Browse source 
* add DCAE download cmd

* update download cmd

* update readme
This commit is contained in:
Xiwen Wu 2025-03-14 18:41:20 +08:00 committed by GitHub
parent 1bc0b169b8
commit afb7cc7dcc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 13 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
README.md
View file

@ -3,7 +3,7 @@
</p>
<div align="center">
<a href="https://github.com/hpcaitech/Open-Sora/stargazers"><img src="https://img.shields.io/github/stars/hpcaitech/Open-Sora?style=social"></a>
<a href="https://github.com/hpcaitech/Open-Sora-Demo/blob/main/paper/Open_Sora_2_tech_report.pdf"><img src="https://img.shields.io/static/v1?label=Tech Report 2.0&message=Arxiv&color=red"></a>
<a href="https://arxiv.org/abs/2503.09642v1"><img src="https://img.shields.io/static/v1?label=Tech Report 2.0&message=Arxiv&color=red"></a>
<a href="https://arxiv.org/abs/2412.20404"><img src="https://img.shields.io/static/v1?label=Tech Report 1.2&message=Arxiv&color=red"></a>
<a href="https://hpcaitech.github.io/Open-Sora/"><img src="https://img.shields.io/badge/Gallery-View-orange?logo=&amp"></a>
</div>
@ -40,7 +40,7 @@ With Open-Sora, our goal is to foster innovation, creativity, and inclusivity wi
## 📰 News
- **[2025.03.12]** 🔥 We released **Open-Sora 2.0** (11B). 🎬 11B model achieves [on-par performance](#evaluation) with 11B HunyuanVideo & 30B Step-Video on 📐VBench & 📊Human Preference. 🛠️ Fully open-source: checkpoints and training codes for training with only **$200K**. [[report]](https://github.com/hpcaitech/Open-Sora-Demo/blob/main/paper/Open_Sora_2_tech_report.pdf)
- **[2025.03.12]** 🔥 We released **Open-Sora 2.0** (11B). 🎬 11B model achieves [on-par performance](#evaluation) with 11B HunyuanVideo & 30B Step-Video on 📐VBench & 📊Human Preference. 🛠️ Fully open-source: checkpoints and training codes for training with only **$200K**. [[report]](https://arxiv.org/abs/2503.09642v1)
- **[2025.02.20]** 🔥 We released **Open-Sora 1.3** (1B). With the upgraded VAE and Transformer architecture, the quality of our generated videos has been greatly improved 🚀. [[checkpoints]](#open-sora-13-model-weights) [[report]](/docs/report_04.md) [[demo]](https://huggingface.co/spaces/hpcai-tech/open-sora)
- **[2024.12.23]** The development cost of video generation models has saved by 50%! Open-source solutions are now available with H200 GPU vouchers. [[blog]](https://company.hpc-ai.com/blog/the-development-cost-of-video-generation-models-has-saved-by-50-open-source-solutions-are-now-available-with-h200-gpu-vouchers) [[code]](https://github.com/hpcaitech/Open-Sora/blob/main/scripts/train.py) [[vouchers]](https://colossalai.org/zh-Hans/docs/get_started/bonus/)
- **[2024.06.17]** We released **Open-Sora 1.2**, which includes **3D-VAE**, **rectified flow**, and **score condition**. The video quality is greatly improved. [[checkpoints]](#open-sora-12-model-weights) [[report]](/docs/report_03.md) [[arxiv]](https://arxiv.org/abs/2412.20404)
@ -125,7 +125,7 @@ see [here](/assets/texts/t2v_samples.txt) for full prompts.
## 🔆 Reports
- **[Tech Report of Open-Sora 2.0](https://github.com/hpcaitech/Open-Sora-Demo/blob/main/paper/Open_Sora_2_tech_report.pdf)**
- **[Tech Report of Open-Sora 2.0](https://arxiv.org/abs/2503.09642v1)**
- **[Step by step to train or finetune your own model](docs/train.md)**
- **[Step by step to train and evaluate an video autoencoder](docs/ae.md)**
- **[Visit the high compression video autoencoder](docs/hcae.md)**

11
docs/hcae.md
View file

@ -11,7 +11,16 @@ we explore training video generation models with high-compression autoencoders (
Nevertheless, despite the advantanges in drastically lower computation costs, other challenges remain. For instance, larger channels low down convergance. Our generation model adapted with a 128-channel Video DC-AE for 25K iterations achieves a loss level of 0.5, as compared to 0.1 from the initialization model. While the fast video generation model underperforms the original, it still captures spatial-temporal
relationships. We release this model to the research community for further exploration.
Checkout more details in our [report]().
Checkout more details in our [report](https://arxiv.org/abs/2503.09642v1).
## Model Download
Download from 🤗 [Huggingface](https://huggingface.co/hpcai-tech/Open-Sora-v2-Video-DC-AE):
```bash
pip install "huggingface_hub[cli]"
huggingface-cli download hpcai-tech/Open-Sora-v2-Video-DC-AE --local-dir ./ckpts
```
## Inference