Sketching the Future (STF): Applying Conditional Control Techniques to Text-to-Video Models
This addresses the need for flexible video generation tools for content creators, though it is incremental as it builds on existing architectures.
The paper tackles the problem of generating video content that aligns with user-specified motion by combining zero-shot text-to-video generation with ControlNet, using sketched frames as input to produce high-quality and consistent videos.
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.