Skip to content

Open-Sora: Democratizing Efficient Video Production for All

Python

update pllava readme

Tom Youngf274683d96b0
diff --git a/tools/caption/README.md b/tools/caption/README.md
index 01ac7f3..168566e 100644
--- a/tools/caption/README.md
+++ b/tools/caption/README.md
@@ -60,7 +60,7 @@ nohup python caption_pllava.py \
> pllava_caption.out 2>&1 &
```
-### PLLaVA VS LLaVA
+### PLLaVA vs. LLaVA
In our previous releases, we used [LLaVA](#llava-captioning) for video captioning.
Qualitatively speaking, we observe that PLLaVA has a somewhat higher chance of accurately capture the details in the video than LLaVA. See below for their comparison on a video sample.
<!-- <img src="../../assets/readme/llava_vs_pllava_sample.gif" width="300" height="200" alt="LLaVA vs PLLaVA"> -->