Update docs/source/en/training/cogvideox.md

Co-authored-by: Steven Liu <[email protected]>

Author: glide-the

docs/source/en/training/cogvideox.md

@@ -78,7 +78,7 @@ When using this format, the `--caption_column` must be `<CAPTION_COLUMN>` and `-
 
 You are not strictly restricted to the CSV format. As long as the `load_dataset` method supports the file format to load a basic `<PATH_TO_VIDEO_COLUMN>` and `<CAPTION_COLUMN>`, you should be good to go. The reason for going through these dataset organization gymnastics for loading video data is because we found `load_dataset` from the datasets library to not fully support all kinds of video formats. This will undoubtedly be improved in the future.
 
->![NOTE]
+> [!TIP]
 > CogVideoX works best with long and descriptive LLM-augmented prompts for video generation. We recommend pre-processing your videos by first generating a summary using a VLM and then augmenting the prompts with an LLM. To generate the above captions, we use [MiniCPM-V-26](https://huggingface.co/openbmb/MiniCPM-V-2_6) and [Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct). A very barebones and no-frills example for this is available [here](https://gist.github.com/a-r-r-o-w/4dee20250e82f4e44690a02351324a4a). The official recommendation for augmenting prompts is [ChatGLM](https://huggingface.co/THUDM?search_models=chatglm) and a length of 50-100 words is considered good.
 
 >![NOTE]