Dual-Stream Diffusion Net for Text-to-Video Generation
This work addresses a bottleneck in text-to-video generation for applications requiring high-quality video output, representing an incremental improvement.
The paper tackles the problem of flickers and artifacts in text-to-video generation by proposing a dual-stream diffusion net (DSDN), which improves content consistency and smoothness, resulting in videos with fewer flickers as demonstrated in experiments.
With the emerging diffusion models, recently, text-to-video generation has aroused increasing attention. But an important bottleneck therein is that generative videos often tend to carry some flickers and artifacts. In this work, we propose a dual-stream diffusion net (DSDN) to improve the consistency of content variations in generating videos. In particular, the designed two diffusion streams, video content and motion branches, could not only run separately in their private spaces for producing personalized video variations as well as content, but also be well-aligned between the content and motion domains through leveraging our designed cross-transformer interaction module, which would benefit the smoothness of generated videos. Besides, we also introduce motion decomposer and combiner to faciliate the operation on video motion. Qualitative and quantitative experiments demonstrate that our method could produce amazing continuous videos with fewer flickers.