6 datasets found

ControlVideo: Training-free controllable text-to-video generation.

The MultiStudioBench dataset contains 25 subjects, including objects, animals, etc., and there are few images for each subject. Images in the dataset are from previous works or...

Text2video-zero: Text-to-image diffusion models are zero-shot video generators.

Videofusion: Decomposed diffusion models for high-quality video generation.

Latent-shift: Latent diffusion with temporal shift for efficient text-to-video generation.

Text-to-video is a rapidly growing research area that aims to generate a semantic, identical, and temporal coherence sequence of frames that accurately align with the input text...