FrameDiT: Diffusion Transformer with Frame-Level Matrix Attention for Efficient Video Generation
This work addresses the problem of efficient spatio-temporal modeling in video generation for AI and multimedia applications, representing an incremental improvement over existing methods.
The paper tackled the challenge of efficient high-fidelity video generation in diffusion models by proposing Matrix Attention, a frame-level temporal attention mechanism, and FrameDiT architectures, achieving state-of-the-art results with improved temporal coherence and video quality while maintaining efficiency comparable to Local Factorized Attention.
High-fidelity video generation remains challenging for diffusion models due to the difficulty of modeling complex spatio-temporal dynamics efficiently. Recent video diffusion methods typically represent a video as a sequence of spatio-temporal tokens which can be modeled using Diffusion Transformers (DiTs). However, this approach faces a trade-off between the strong but expensive Full 3D Attention and the efficient but temporally limited Local Factorized Attention. To resolve this trade-off, we propose Matrix Attention, a frame-level temporal attention mechanism that processes an entire frame as a matrix and generates query, key, and value matrices via matrix-native operations. By attending across frames rather than tokens, Matrix Attention effectively preserves global spatio-temporal structure and adapts to significant motion. We build FrameDiT-G, a DiT architecture based on MatrixAttention, and further introduce FrameDiT-H, which integrates Matrix Attention with Local Factorized Attention to capture both large and small motion. Extensive experiments show that FrameDiT-H achieves state-of-the-art results across multiple video generation benchmarks, offering improved temporal coherence and video quality while maintaining efficiency comparable to Local Factorized Attention.