AIBullisharXiv – CS AI · 6h ago7/10
🧠
SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer
SANA-Streaming introduces a real-time video editing system that achieves 24 FPS at 1280x704 resolution on consumer GPUs through a hybrid diffusion transformer architecture and specialized optimization for NVIDIA hardware. The breakthrough combines algorithmic improvements in temporal consistency with system-level co-design, enabling practical applications in live broadcasting and gaming that were previously computationally infeasible.
🏢 Nvidia