May 8, 2024 · We introduce the Attention-driven Training-free Efficient Diffusion Model (AT-EDM) framework that leverages attention maps to perform run-time pruning of ...
A framework that leverages attention maps to perform run-time pruning of redundant tokens during inference without retraining.
To this end, we introduce the Attention-driven Training-free. Efficient Diffusion Model (AT-EDM) framework that lever- ages attention maps to perform run-time ...
To this end, we introduce the Attention-driven Training-free. Efficient Diffusion Model (AT-EDM) framework that lever- ages attention maps to perform run-time ...
Therefore, we propose AT-EDM to accelerate attention blocks in the model through token pruning. AT-EDM contains two important parts: a single-denoising-step ...
Attention-Driven Training-Free Efficiency Enhancement of Diffusion ...
www.computer.org › csdl › cvpr
We introduce the Attention-driven Training-free Efficient Diffusion Model (AT-EDM) framework that leverages attention maps to perform run-time pruning of ...
Jun 17, 2024 · We introduce the Attention-driven Training-free Efficient Diffusion Model (AT-EDM), a framework that leverages attention maps to perform run-time pruning of ...
May 24, 2024 · This is computationally expensive and not very scalable. To this end, we introduce the Attention-driven Training-free Efficient Diffusion Model ...
May 9, 2024 · Proposes AT-EDM, a training-free framework to accelerate diffusion models by leveraging attention maps for run-time token pruning without retraining.
Duration: 13:55
Posted: May 9, 2024
Posted: May 9, 2024