Dataset · GokuScraper
Seedance 2.0 prompts and videos
GokuScraper/seedance-2-prompts-datasets
Over 8,100 English and Chinese prompts together with generated videos and preview frames.
What's inside
Contains over 8,100 pairs of text prompts for the Bytedance Seedance 2.0 model and resulting video clips with metadata and preview frames. Data is in English and Chinese, with a total volume exceeding 50 GB.
What you can do with it
- Training or fine-tuning text-to-video models
- Creating prompt generators and enhancers for video neural networks
- Analyzing text-to-visual generation pairs
- Tasks
- Text → video
- Languages
- English, Chinese
- Size
- 1K–10K rows
- Downloads this month
- 126.4K
- Likes
- 61
Models trained on it
How to load it
from datasets import load_dataset
ds = load_dataset("GokuScraper/seedance-2-prompts-datasets")