English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

High computational overhead is a troublesome problem for diffusion models.Recent studies have leveraged post-training quantization (PTQ) to compressdiffusion models. However, most of them only focus on unconditional models,leaving the quantization of widely-used pretrained text-to-image models, e.g.,Stable Diffusion, largely unexplored. In this paper, we propose a novelpost-training quantization method PCR (Progressive Calibration and Relaxing)for text-to-image diffusion models, which consists of a progressive calibrationstrategy that considers the accumulated quantization error across timesteps,and an activation relaxing strategy that improves the performance withnegligible cost. Additionally, we demonstrate the previous metrics fortext-to-image diffusion model quantization are not accurate due to thedistribution gap. To tackle the problem, we propose a novel QDiffBenchbenchmark, which utilizes data in the same domain for more accurate evaluation.Besides, QDiffBench also considers the generalization performance of thequantized model outside the calibration dataset. Extensive experiments onStable Diffusion and Stable Diffusion XL demonstrate the superiority of ourmethod and benchmark. Moreover, we are the first to achieve quantization forStable Diffusion XL while maintaining the performance.

Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing