Wilshire@lemmy.world to Technology@lemmy.worldEnglish · 8 个月前Ridiculed Stable Diffusion 3 release excels at AI-generated body horrorarstechnica.comexternal-linkmessage-square45fedilinkarrow-up1260arrow-down15cross-posted to: cursed_ai@lemmy.mltechnology@lemmy.zipartificial_intel@lemmy.ml
arrow-up1255arrow-down1external-linkRidiculed Stable Diffusion 3 release excels at AI-generated body horrorarstechnica.comWilshire@lemmy.world to Technology@lemmy.worldEnglish · 8 个月前message-square45fedilinkcross-posted to: cursed_ai@lemmy.mltechnology@lemmy.zipartificial_intel@lemmy.ml
minus-squareBetaDoggo_@lemmy.worldlinkfedilinkEnglisharrow-up5·8 个月前The model does have a lot of advantages over sdxl with the right prompting, but it seems to fall apart in prompts with more complex anatomy. Hopefully the community can fix it up once we have working trainers.
minus-squarefruitycoder@sh.itjust.workslinkfedilinkEnglisharrow-up2·8 个月前Gotta think most sfw pictures of people are portraits. Poses are more advanced for sure
The model does have a lot of advantages over sdxl with the right prompting, but it seems to fall apart in prompts with more complex anatomy. Hopefully the community can fix it up once we have working trainers.
“Laying on grass” is complex?
Gotta think most sfw pictures of people are portraits. Poses are more advanced for sure