Merge pull request #82 from hpcaitech/release

Release
hpcaitech · Mar 17, 2024 · 4516134 · 4516134
2 parents 1d732ab + 21ef592
commit 4516134
Show file tree

Hide file tree

Showing 3 changed files with 10 additions and 2 deletions.
diff --git a/README.md b/README.md
@@ -18,7 +18,7 @@ With Open-Sora, we aim to inspire innovation, creativity, and inclusivity in the
 
 ## 📰 News
 
-* **[2024.03.18]** 🔥 We release **Open-Sora 1.0**, an fully open-sourced project for video generation.
+* **[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
 <a href="https://github.com/hpcaitech/ColossalAI"><img src="assets/readme/colossal_ai.png" width="8%" ></a> acceleration,
 inference, and more. Our provided [checkpoints](#model-weights) can produce 2~5s 512x512 videos with only 3 days training.

diff --git a/tools/intepolate/README.md b/tools/intepolate/README.md
@@ -0,0 +1 @@
+# To be added
diff --git a/tools/scenedetect/README.md b/tools/scenedetect/README.md
@@ -1,2 +1,9 @@
-# Data Preprocessing Tools
+# Scene Detection and Video Split
 
+Raw videos from the Internet may be too long for training. 
+Thus, we detect scenes in raw videos and split them into short clips based on the scenes.
+First prepare the video processing packages.
+```bash
+pip install scenedetect moviepy opencv-python
+```
+Then run `scene_detect.py`. We provide efficient processing using `multiprocessing`. Don't forget to specify your own dataset path.