UFO: Enhancing Diffusion-Based Video Generation with a Uniform Frame Organizer
This work addresses consistency and quality problems in video generation for AI and creative applications, representing an incremental improvement as a plug-in for existing models.
The paper tackles issues of weak consistency and declining image quality in diffusion-based video generation by proposing UFO, a non-invasive plug-in that enhances foreground-background consistency and image quality without altering original model parameters, achieving superior results on public benchmarks.
Recently, diffusion-based video generation models have achieved significant success. However, existing models often suffer from issues like weak consistency and declining image quality over time. To overcome these challenges, inspired by aesthetic principles, we propose a non-invasive plug-in called Uniform Frame Organizer (UFO), which is compatible with any diffusion-based video generation model. The UFO comprises a series of adaptive adapters with adjustable intensities, which can significantly enhance the consistency between the foreground and background of videos and improve image quality without altering the original model parameters when integrated. The training for UFO is simple, efficient, requires minimal resources, and supports stylized training. Its modular design allows for the combination of multiple UFOs, enabling the customization of personalized video generation models. Furthermore, the UFO also supports direct transferability across different models of the same specification without the need for specific retraining. The experimental results indicate that UFO effectively enhances video generation quality and demonstrates its superiority in public video generation benchmarks. The code will be publicly available at https://github.com/Delong-liu-bupt/UFO.