This paper introduces two scaled-down variants of the Stable Diffusion XL (SDXL) text-to-image model, achieved through progressive removal of layers and losses. These models effectively emulate the original SDXL while reducing parameters and latency, making them more accessible for deployment in resource-constrained environments.

https://arxiv.org/abs//2401.02677

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers