Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists

Paper | Code | Huggingface

This is the official implementation of Señorita. The original model requires 50 denoising steps to generate a video. However, due to GPU usage limitations on Hugging Face Spaces, we have reduced the number of denoising steps to 20, which takes about 240s to generate one video. As a result, the performance may be slightly affected. Thank you for your understanding! This UI is made by PengWeixuanSZU.
0 2147483647
1 10
Frame number
Examples
Video input First frame guidence Positive prompt Negative prompt Guidance Seed Frame number