Skip to yearly menu bar Skip to main content


Virtual presentation / poster accept

Make-A-Video: Text-to-Video Generation without Text-Video Data

Uriel Singer · Adam Polyak · Thomas Hayes · Xi Yin · Jie An · Songyang Zhang · Qiyuan Hu · Harry Yang · Oron Ashual · Oran Gafni · Devi Parikh · Sonal Gupta · Yaniv Taigman

MH1-2-3-4

Keywords: [ Generative models ]


Abstract:

We propose Make-A-Video -- an approach for directly translating the tremendous recent progress in Text-to-Image (T2I) generation to Text-to-Video (T2V). Our intuition is simple: learn what the world looks like and how it is described from paired text-image data, and learn how the world moves from unsupervised video footage. Make-A-Video has three advantages: (1) it accelerates training of the T2V model (it does not need to learn visual and multimodal representations from scratch), (2) it does not require paired text-video data, and (3) the generated videos inherit the vastness (diversity in aesthetic, fantastical depictions, etc.) of today's image generation models. We design a simple yet effective way to build on T2I models with novel and effective spatial-temporal modules. First, we decompose the full temporal U-Net and attention tensors and approximate them in space and time. Second, we design a spatial temporal pipeline to generate high resolution and frame rate videos with a video decoder, interpolation model and two super resolution models that can enable various applications besides T2V. In all aspects, spatial and temporal resolution, faithfulness to text, and quality, Make-A-Video sets the new state-of-the-art in text-to-video generation, as determined by both qualitative and quantitative measures.

Chat is not available.