Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models

arXiv:2405.04233v1 Announce Type: cross
Abstract: We introduce Vidu, a high-performance text-to-video generator that is capable of producing 1080p videos up to 16 seconds in a single generation. Vidu is a diffusion model with U-ViT as its backbone, which unlocks the scalability and the capability for handling long videos. Vidu exhibits strong coherence and dynamism, and is capable of generating both realistic and imaginative videos, as well as understanding some professional photography techniques, on par with Sora -- the most powerful …

abstract arxiv capability consistent cs.cv cs.lg diffusion diffusion model diffusion models dynamic generator performance scalability skilled text text-to-video text-to-video generator type video video generator videos vidu vit