Tag
HiLo-Token introduces an input-adaptive token compression framework for Diffusion Transformers that allocates more tokens to high-frequency regions, achieving up to 3.13x speedup in image editing tasks without quality loss.
A unified framework for camera motion cloning using grid motion videos and multimodal diffusion transformers, enabling director-level control without cross-paired data.
RhymeFlow accelerates diffusion transformers for video generation by decoupling denoising trajectories across frames, using keyframe anchoring and latent trajectory projection to reduce computational overhead while maintaining visual quality.
SEGA is a training-free method that improves high-resolution text-to-image generation by adaptively scaling attention across RoPE components based on spatial-frequency structure during denoising steps.
This paper proposes Diffusion-Adaptive Routing (DAR), a learnable, timestep-adaptive residual replacement that improves cross-layer information flow in Diffusion Transformers, leading to significant training acceleration and quality improvements.