https://hackerpaper.kaipfister.de/p/2206.08889/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=32674959urn:hackerpapers:mention:2206.08889:32674959Thu, 01 Sep 2022 11:36:54 GMT<p>Diffusion models can be used to lossily compress images for real, see for example Lossy Compression with Gaussian Diffusion (https://arxiv.org/abs/2206.08889). I would expect this to work with text-conditional diffusion models too and give you better compression when supplying a correct caption.</p><p><a href="https://hackerpaper.kaipfister.de/p/2206.08889/">Paper and discussion history</a>. A mention is not an endorsement.</p>stat.MLhttps://news.ycombinator.com/item?id=31806696urn:hackerpapers:submission:2206.08889:31806696Mon, 20 Jun 2022 05:41:51 GMT<p>Lossy Compression with Gaussian Diffusion</p><p></p><p>2 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2206.08889/">Paper and source history</a>. A submission is not an endorsement.</p>stat.ML