Skip to content

Open-Sora: Democratizing Efficient Video Production for All

Python

update readme

zhengzangw3a0063c2818e
diff --git a/README.md b/README.md
index 417d6e0..3d0dd66 100644
--- a/README.md
+++ b/README.md
@@ -59,7 +59,7 @@ More samples are available in our [gallery](https://hpcaitech.github.io/Open-Sor
## πŸ”† New Features/Updates
* πŸ“ **Open-Sora 1.1** released. Model weights are available [here](). It is trained on **0s~15s, 144p to 720p, various aspect ratios** videos. See our **[report 1.1](docs/report_02.md)** for more discussions.
-* πŸ”§ **Data processing pipeline v1.1** is released. An automatic processing pipeline from raw videos to (text, video clip) pairs is provided, including scene cutting$\rightarrow$filtering(aesthetic, optical flow, OCR, etc.)$\rightarrow$captioning$\rightarrow$managing. With this tool, you can easily build your video dataset.
+* πŸ”§ **Data processing pipeline v1.1** is released. An automatic processing pipeline from raw videos to (text, video clip) pairs is provided, including scene cutting $\rightarrow$ filtering(aesthetic, optical flow, OCR, etc.) $\rightarrow$ captioning $\rightarrow$ managing. With this tool, you can easily build your video dataset.
* βœ… Modified ST-DiT architecture includes rope positional encoding, qk norm, longer text length, etc.
* βœ… Support training with any resolution, aspect ratio, and duration (including images).
* βœ… Support image and video conditioning and video editing, and thus support animating images, connecting videos, etc.
@@ -274,6 +274,8 @@ python -m tools.datasets.csvutil meta_caption_processed_aes.csv --aesmin 5 --out
python -m tools.datasets.csvutil ~/dataset_ready.csv --fmin 48
```
+![Data Processing Pipeline](assets/readme/report_data_pipeline.png)
+
## Training
### Open-Sora 1.1 Training