Home Artists Posts Import Register

Content

It's quite fun, and fascinating, trying to create images from text, though also somewhat frustrating. There's so much going on here, from the "unconscious" biases of the learning model (initially, I didn't indicate either gender or race for the image, for example) to its stubborness regarding some details - but still great fun to play with.  I had a go at the same scene Bobbie experimented with, using getimg.ai, which does allow for some nudity. I then tried using one of the more successful generations as the basis for another image - Cindy's first therapy session with Crystal, and how I described her in that.  The AI really struggled with this one - first, simply making the babydoll into something a bit more leather-like - and really resisting the idea of a mesh top (or any kind of top!) over the bra.  Weird.  It struggled with colours as well. When I tried to add a bit of pink to lips and fingernails, it turned her hair and clothes pink as well.  The AI, at least in this drawing model, also struggled with the idea of an "angry look".  Still, these complaints seem pretty petty considering what an absolute numpty like me can create with these things!  AI is exciting and terrifying in equal measure....

In any case, I'll leave the AI Art for the time being (but welcome contributions, AI or otherwise) - I've got writing to do!

Files

Comments

Asklepios

They are very definitely AI derived - the second image has 6 fingers and the first has an interesting leather to lace transition at the hem of her shorts.... These kind of images are fascinating but they have an unworldy flavour to them that I find myself at odds with... (Bah humbag, modern world, mutter mutter). Its amazing that it works at all though!

Fakeminsk TG Fiction: Constant in All Other Things

Ha! I hadn't noticed the sixth finger. But yeah, there's a real uncanny valley aspect to them. AI Art and AI Writing seem to be kinda running in parallel - both absolutely amazing in that they actually work and can generate something that passes as either visual or written art; but up close, the flaws become obvious. AI writing veers off into nonsense pretty quickly, and even when directed can be quite bland or generic; and the art generation seems to do the same at times. Then again, with a firm hand and a little skill, both seem capable of producing good stuff. All in a Sea of Wonder isn't great literature, but I think I managed to coax the AI into generating something decent - I really should get back to that someday. Same with the AI Art - I wish I had more ability (or time to learn it!) to get the best out of it. Amazing and scary to think where it'll be in 5 - 10 - or 25 years from now, though!