Sketching the Future (STF): Applying Conditional Control Techniques to Text-to-Video Models

TL;DR

This paper introduces a novel method combining zero-shot text-to-video generation with ControlNet, using sketched frames to produce high-quality, motion-consistent videos aligned with user input, advancing flexible video synthesis.

Contribution

The paper presents a new approach that integrates ControlNet with Text-to-Video Zero, enabling control over generated videos using sketches and interpolated frames, which was not previously achieved.

Findings

Produces high-quality, consistent videos

Aligns video motion with user sketches

Leverages combined zero-shot and control techniques

Abstract

The proliferation of video content demands efficient and flexible neural network based approaches for generating new video content. In this paper, we propose a novel approach that combines zero-shot text-to-video generation with ControlNet to improve the output of these models. Our method takes multiple sketched frames as input and generates video output that matches the flow of these frames, building upon the Text-to-Video Zero architecture and incorporating ControlNet to enable additional input conditions. By first interpolating frames between the inputted sketches and then running Text-to-Video Zero using the new interpolated frames video as the control technique, we leverage the benefits of both zero-shot text-to-video generation and the robust control provided by ControlNet. Experiments demonstrate that our method excels at producing high-quality and remarkably consistent video content that more accurately aligns with the user's intended motion for the subject within the video. We provide a comprehensive resource package, including a demo video, project website, open-source GitHub repository, and a Colab playground to foster further research and application of our proposed method.