Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Lossy Compression with Pretrained Diffusion Models

About

We apply the DiffC algorithm (Theis et al. 2022) to Stable Diffusion 1.5, 2.1, XL, and Flux-dev, and demonstrate that these pretrained models are remarkably capable lossy image compressors. A principled algorithm for lossy compression using pretrained diffusion models has been understood since at least Ho et al. 2020, but challenges in reverse-channel coding have prevented such algorithms from ever being fully implemented. We introduce simple workarounds that lead to the first complete implementation of DiffC, which is capable of compressing and decompressing images using Stable Diffusion in under 10 seconds. Despite requiring no additional training, our method is competitive with other state-of-the-art generative compression methods at low ultra-low bitrates.

Jeremy Vonderfecht, Feng Liu• 2025

Related benchmarks

TaskDatasetResultRank
Image CompressionKodak (test)--
32
Image CompressionDIV2K (test)
BD-DISTS0.00e+0
9
Image CompressionCLIC 2020 (test)
BD-DISTS0.00e+0
9
Showing 3 of 3 rows

Other info

Follow for update