AIMv2 Collection A collection of AIMv2 vision encoders that supports a number of resolutions, native resolution, and a distilled checkpoint. • 19 items • Updated 2 days ago • 47
DiTFastAttn: Attention Compression for Diffusion Transformer Models Paper • 2406.08552 • Published Jun 12 • 22
Interpreting the Weight Space of Customized Diffusion Models Paper • 2406.09413 • Published Jun 13 • 18
Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models Paper • 2406.09416 • Published Jun 13 • 28
RMT: Retentive Networks Meet Vision Transformers Paper • 2309.11523 • Published Sep 20, 2023 • 33