Vchitect T2V is a video generation dataset released by Shanghai Artificial Intelligence Laboratory in 2025. The related paper results are "Vchitect-2.0: Parallel Transformer for Scal Up Video Diffusion Models"Aims to focus on improving the model's ability to convert between text and visual content, helping researchers and developers make progress in image generation, semantic understanding, cross-modal tasks, etc.

The dataset contains 14 million high-quality videos, each with detailed text captions.