Spark-H3: Adaptive Block Sparse Attention for Video Diffusion Models
Abstract
Long video sequences make attention a substantial cost in video diffusion models. Block sparse attention (BSA) reduces this cost by computing selected blocks exactly while compressing the remaining blocks. However, fixed token grouping can place tokens with dissimilar attention preferences in the same group, while uniform key averaging can underestimate the attention mass of compressed blocks. We introduce Spark-Attn, a training-free BSA method comprising Spark-Reblock and Spark-Reweight. Spark-Reblock recursively groups tokens by attention preference while preserving regular block shapes for efficient GPU execution. Spark-Reweight uses the global mean query as an anchor to construct attention-weighted key-value representations and logit biases for the compressed blocks, calibrating their attention mass. We instantiate Spark-Attn in MiniMax-H3 as Spark-H3. At 10% exact-block density, Spark-H3 delivers a 2.49times DiT speedup and reaches 24.81 dB PSNR against the corresponding dense outputs on MiniMax-H3 (20 denoising steps, 345 frames, 1344times768). Increasing the density to 20% further improves PSNR to 26.76 dB while still achieving a 2.26times DiT speedup. These results demonstrate that Spark-H3 achieves a state-of-the-art quality-efficiency trade-off for training-free BSA on video diffusion models.
Get this paper in your agent:
hf papers read 2611.24256 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper