Your AI-enhanced images (tutorial with your pictures)

[Little Sally]

In a few months we will see so many incredible sw pictures, it will be crazy. And posting them on DA will be fun, there are already so many "artists" posting this stupid "NoAI" sign...

Yes I've noticed that myself, with this page an example of what you say. https://www.deviantart.com/jeromebrack

I would have thought that if folks using the AI format are honest enough to state they use it in their work, then artists who are non users shouldn't be too concerned about it.

But time will tell, of course.

[foreverlurk]

Uh, that's interesting : earlier this week, someone trained a model for Stable Diffusion XL that improves its understanding of perspective and size. Previous versions of SD could kinda generate those too, but required much more complex prompting. It's still in beta for now, but I'll keep an eye on it. It'll be years (if not a decade) before it reaches the level of prompt comprehension that ChatGPT offers, but hey at least Stable Diffusion is free from corporate bullshit.

Model name is ShrunkXL :
https://civitai.com/models/151689?modelVersionId=175451