DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer

ArXi:2604.13509v1 Announce Type: new Recent advances in video generation models has significantly accelerated video generation and related downstream tasks. Among these, video stylization holds important research value in areas such as immersive applications and artistic creation, attracting widespread attention. However, existing diffusion-based video stylization methods struggle to maintain stability and consistency when processing long videos, and their high computational cost and multi-step denoising make them difficult to apply in practical scenarios.