Efficient Autoregressive Video Diffusion with Dummy Head
The autoregressive video diffusion model has recently gained considerable research interest due to its causal modeling and iterative denoising. In this work, we identify that the multi-head self-attention in these models under-utilizes historical frames: approximately 25% heads attend almost exclusively to the current frame, and discarding their KV caches incurs only minor performance degradation. Building upon this, we propose Dummy Forcing, a simple yet effective method to control context accessibility across different heads. Specifically, the proposed heterogeneous memory allocation reduces head-wise context redundancy, accompanied by dynamic head programming to adaptively classify head types. Moreover, we develop a context packing technique to achieve more aggressive cache compression. Without additional training, our Dummy Forcing delivers up to 2.0x speedup over the baseline, supporting video generation at 24.3 FPS with less than 0.5% quality drop. Project page is available at https://csguoh.github.io/project/DummyForcing/.
Code (0)
등록된 구현이 없습니다.
Tasks
Video GenerationSimilar Papers 제목 키워드 기반
HeadCast: Casting Attention Heads for Efficient Autoregressive Video Generation
Autoregressive (AR) video diffusion models have become a promising paradigm for long and streaming video synthesis, but the continuously growing Key-Value (KV) cache makes attention the dominant inference cost, especiall…
Video GenerationForcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models
Autoregressive (AR) video diffusion models adopt a streaming generation framework, enabling long-horizon video generation with real-time responsiveness, as exemplified by the Self Forcing training paradigm. However, exis…
Video GenerationDAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking Head Video Generation
Talking head generation intends to produce vivid and realistic talking head videos from a single portrait and speech audio clip. Although significant progress has been made in diffusion-based talking head generation, alm…
Talking Head GenerationVideo GenerationHead Forcing: Long Autoregressive Video Generation via Head Heterogeneity
Autoregressive video diffusion models support real-time synthesis but suffer from error accumulation and context loss over long horizons. We discover that attention heads in AR video diffusion transformers serve function…
Video GenerationDSA: Dynamic Step Allocation for Fast Autoregressive Video Generation
Video diffusion transformers have achieved state-of-the-art visual quality, but their high inference cost remains a major bottleneck for real-time applications. Recent distillation frameworks produce autoregressive video…
Video Generation