# ToDo: Token Downsampling for Efficient Generation of High-Resolution Images Source: [ToDo: Token Downsampling for Efficient Generation of High-Resolution Images]() Collection index: [llms.txt]() Data updated: 2025-10-26T02:43:27.234Z Authors: Ethan Smith, Nayan Saxena, Aninda Saha Published: 2024-02-21T07:10:28.000Z ## Abstract Attention mechanism has been crucial for image diffusion models, however, their quadratic computational complexity limits the sizes of images we can process within reasonable time and memory constraints. This paper investigates the importance of dense attention in generative image models, which often contain redundant features, making them suitable for sparser attention mechanisms. We propose a novel training-free method ToDo that relies on token downsampling of key and value tokens to accelerate Stable Diffusion inference by up to 2x for common sizes and up to 4.5x or more for high resolutions like 2048x2048. We demonstrate that our approach outperforms previous methods in balancing efficient throughput and fidelity. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on Oxford-IIIT Pets (test) (Reporting Baseline Delta)](): Image Classification; Oxford-IIIT Pets (test); Top-1 Accuracy: 79.15. ## Original sources and implementation [Original paper]() [PDF]()