Dataset - LDM

OpenShot

The dataset used for speech-to-speech translation, lip-syncing, and talking face generation.
- Dataset
- JSON
MEAD and HDTF datasets

MEAD and HDTF datasets are used for training and testing the proposed SAAS model.
- Dataset
- JSON
MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers

Text-based video editing using MaskINT, a two-stage pipeline involving keyframe joint editing and structure-aware frame interpolation.
- Dataset
- JSON
EVE: Efficient zero-shot text-based Video Editing

Zero-shot text-based video editing with depth map guidance and temporal consistency constraints
- Dataset
- JSON

You can also access this registry using the API (see API Docs).

4 datasets found