DiTFastAttn: Attention Compression for Diffusion Transformer Models

Neural Information Processing Systems 

Diffusion Transformers (DiT) excel at image and video generation but face computational challenges due to the quadratic complexity of self-attention operators. We propose DiTFastAttn, a post-training compression method to alleviate the computational bottleneck of DiT.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found