We started this thread with: *sambleckley> producing a specific image with gener... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		jefftk on Aug 21, 2023 \| parent \| context \| favorite \| on: Don't fire your illustrator We started this thread with: sambleckley> producing a specific image with generative AI is sometimes almost impossible justrealist> Who could possibly think this will be the case six months from now? me> I'd bet on this being true six months from now I thought you disagreed with me on this, but it sounds like maybe not?

raincole on Aug 21, 2023 [–]

I was just stating the improvement on SD we've seen since DELL-E 2 and Midjourney came out wasn't just about "quality of image", but also about "have something specific and moderately complex in mind". Thus I mentioned textual inversion vs LoRA/ControlNet.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact