Having a go at using ControlNet to help with poses and Regional Prompting to get more variety in different zones. So many options to play with!
All prompts are embedded in the original PNGs, click over to the catbox.moe file and open in https://pngchunk.com.
Those fingers don’t look mangled. I think you’re reverse catfishing us with a real picture.
That’s one of the advantages of ControlNodes. You can maintain finger lengths and quantity with Open Pose wireframes or depth masks.
Those are definitely words. It’s scary how fast AI is bridging the gaps.
AI once in a while really seems to like women who do a thousand crunches every morning.
Your stuff is the best in this community, love it!
♥️
I agree! Inspiring stuff.
Completely agree. The faces are stunning, the bodies are stunning, the outfits are stunning. Everything’s damn close to perfect. Have you ever thought of doing hardcore pictures?
FYI, png metadata get truncated in lemmy
Correct. Thats why i post all my images as links to catbox.moe, which doesn’t touch jpg exif or png chunks.
I do post the first image as a jpg on lemmy so that it shows the thumbnail in the thread, but theres a duplicate link to the original png in the post body.
Ah didn’t see they were links. My mistake. Thanks!
Wow this is amazing!
Those look a bit like AI arts. Or a lot. Stunning nonetheless