ControlVideo: Training-free Controllable Text-to-Video Generation

TL;DR

ControlVideo is a training-free framework that enables efficient, coherent, and long text-to-video generation by leveraging structural cues and novel modules to reduce flicker and appearance inconsistency.

Contribution

It introduces a training-free, modular approach for controllable text-to-video synthesis that improves coherence and reduces flickering without extensive training.

Findings

Outperforms state-of-the-art methods quantitatively and qualitatively.

Generates both short and long videos within minutes on a single GPU.

Effectively maintains appearance consistency and structural stability.

Abstract

Text-driven diffusion models have unlocked unprecedented abilities in image generation, whereas their video counterpart still lags behind due to the excessive training cost of temporal modeling. Besides the training burden, the generated videos also suffer from appearance inconsistency and structural flickers, especially in long video synthesis. To address these challenges, we design a \emph{training-free} framework called \textbf{ControlVideo} to enable natural and efficient text-to-video generation. ControlVideo, adapted from ControlNet, leverages coarsely structural consistency from input motion sequences, and introduces three modules to improve video generation. Firstly, to ensure appearance coherence between frames, ControlVideo adds fully cross-frame interaction in self-attention modules. Secondly, to mitigate the flicker effect, it introduces an interleaved-frame smoother that employs frame interpolation on alternated frames. Finally, to produce long videos efficiently, it utilizes a hierarchical sampler that separately synthesizes each short clip with holistic coherency. Empowered with these modules, ControlVideo outperforms the state-of-the-arts on extensive motion-prompt pairs quantitatively and qualitatively. Notably, thanks to the efficient designs, it generates both short and long videos within several minutes using one NVIDIA 2080Ti. Code is available at https://github.com/YBYBZhang/ControlVideo.