MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation

TL;DR

MicroCinema introduces a divide-and-conquer framework for text-to-video generation, leveraging text-to-image models and novel mechanisms to produce high-quality, coherent videos guided by text prompts.

Contribution

It proposes a two-stage approach combining text-to-image and image-to-video generation, with new modules for appearance preservation and noise prior to improve video quality.

Findings

Achieves state-of-the-art zero-shot FVD scores on UCF-101 and MSR-VTT datasets.

Effectively leverages existing text-to-image models for video generation.

Demonstrates high-quality, coherent videos guided by text prompts.

Abstract

We present MicroCinema, a straightforward yet effective framework for high-quality and coherent text-to-video generation. Unlike existing approaches that align text prompts with video directly, MicroCinema introduces a Divide-and-Conquer strategy which divides the text-to-video into a two-stage process: text-to-image generation and image\&text-to-video generation. This strategy offers two significant advantages. a) It allows us to take full advantage of the recent advances in text-to-image models, such as Stable Diffusion, Midjourney, and DALLE, to generate photorealistic and highly detailed images. b) Leveraging the generated image, the model can allocate less focus to fine-grained appearance details, prioritizing the efficient learning of motion dynamics. To implement this strategy effectively, we introduce two core designs. First, we propose the Appearance Injection Network, enhancing the preservation of the appearance of the given image. Second, we introduce the Appearance Noise Prior, a novel mechanism aimed at maintaining the capabilities of pre-trained 2D diffusion models. These design elements empower MicroCinema to generate high-quality videos with precise motion, guided by the provided text prompts. Extensive experiments demonstrate the superiority of the proposed framework. Concretely, MicroCinema achieves SOTA zero-shot FVD of 342.86 on UCF-101 and 377.40 on MSR-VTT. See https://wangyanhui666.github.io/MicroCinema.github.io/ for video samples.