https://hackerpaper.kaipfister.de/p/2111.13606/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=31361142urn:hackerpapers:mention:2111.13606:31361142Thu, 12 May 2022 23:03:39 GMT<p>In this formulation, no, you have no control over the output other than the fact that it is similar to your training data. If you need to have control over the generated image, you would need to use a conditional diffusion model. https://arxiv.org/pdf/2111.13606.pdf</p><p><a href="https://hackerpaper.kaipfister.de/p/2111.13606/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG