Re:Qwen-Image-3.0: Rich Content, Authentic Details, Deep Kno...
by pal9000i on Tuesday July 21, 2026 @05:56AM
(#48990159)
How long until we get rid of the AI "plasticness" in portrait kind of generated images?
[ Parent
| on HN ]
Re:Qwen-Image-3.0: Rich Content, Authentic Details, Deep Kno...
by jrs100000 on Tuesday July 21, 2026 @06:16AM
(#48990320)
The right models and LORAs can get rid of it right now. People apparently really like everyone to look like over exposed over filtered mannequins, so the big companies target that look.
Re:Qwen-Image-3.0: Rich Content, Authentic Details, Deep Kno...
by cubefox on Tuesday July 21, 2026 @11:48AM
(#48993910)
I think it's unintentional. People usually dislike any recognizable "AI look", but they do like other aspects which might have an unrealistic AI look as a side effect.
For example, Google's Imagen 3 usually looked a lot less fake than the newer Imagen 4, but the latter still scored higher on most benchmarks because it made fewer mistakes and had better prompt following capabilities.
A similar thing happened with Dalle-E 2 and Dell-E 3: The new model was better but also more fake looking.
Re:Qwen-Image-3.0: Rich Content, Authentic Details, Deep Kno...
by lifeofpi331144 on Tuesday July 21, 2026 @12:50PM
(#48994876)
what are the right models and loras?