Spaces:

ml-energy
/

leaderboard

Running

Jae-Won Chung

New leaderboard prototype

b10121d 9 months ago

484 Bytes

A newer version of the Gradio SDK is available: 5.32.1

Upgrade

ShareGPT4Video dataset

For the text-to-video task, we sample 100 video captions from the ShareGPT4Video datset to feed to the diffusion model to generate videos.

Download the dataset with captions and video paths.

wget https://huggingface.co/datasets/ShareGPT4Video/ShareGPT4Video/resolve/main/sharegpt4video_40k.jsonl

Sample video-caption pairs. The sampled dataset will be saved under sharegpt4video_100.json.

python sample.py