DiffRatio: Training One-Step Diffusion Models Without Teacher Supervision ยท HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2502.08005/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:27:26 GMTDiffRatio: Training One-Step Diffusion Models Without Teacher Supervision โ€” HN submissionhttps://news.ycombinator.com/item?id=46713753urn:hackerpapers:submission:2502.08005:46713753Thu, 22 Jan 2026 00:41:50 GMT<p>DiffRatio: A SOTA one-step Diffusion model with 50% less GPU memory</p><p></p><p>1 point; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2502.08005/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LGDiffRatio: Training One-Step Diffusion Models Without Teacher Supervision โ€” HN submissionhttps://news.ycombinator.com/item?id=46702621urn:hackerpapers:submission:2502.08005:46702621Wed, 21 Jan 2026 08:21:14 GMT<p>DiffRatio โ€“ A One-Step Diffusion Model with SOTA quality and 50% less memory</p><p></p><p>4 points; 1 discussion reply on HN. <a href="https://hackerpaper.kaipfister.de/p/2502.08005/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LG