Posts

BGM - Fluttershy Still REALLY Likes Humans

Post what you’re listening to
Staind - Outside

Go to «My favourites» page, click random image button and then post result here.

@Teaspoon
Yeah, same here. I’ve had it happen on plenty of non AI art I uploaded as well. I just haven’t really been back to non AI art much since I started doing AI instead.

@tyto4tme4l
@Lord Waite
Yep.

Mind, this isn’t specific to AI, I’ve made loads of vectors where I notice something’s wrong or missing after I considered it “done”, and have heard the same from more “traditional” digital artists.

@tyto4tme4l
Definitely. Happens embarrassingly often when I’m in the middle of tagging something before I hit submit. Often I was distracted by something else in the picture I really liked, or it snuck in while I was changing something else…

@Background Pony #D936
Noticing a glaring flaw once you think you’re finished.

@Teaspoon
what is the most frustrating thing about the process of getting a good ai image?

@Background Pony #D936
Character aware prompting, or some form of smart regional prompting. Ala “Character A has red eyes and yellow hair, character B has blue eyes and red hair, character A is dancing”.

Would just make life easier…

(there’s much more impressive stuff going on ofc)

so what is the most impressive ai development you are excited about?

@Scarlet Ribbon
That’d be nice! I would appreciate it if you’re willing to share with us. I’m always looking for ways to improve my workflow and learn new techniques. Though I’m not in the Discord I’ve seen mentioned so I can only assume that’s where most of that sharing happens.

I did have a question about that. I’m not an artist, but I did wonder if it’s valid for me to generate images to trace. It’d be a step up for me to be tracing something instead of not drawing at all.

@Star Streaker
I’m rebuilding it right now, but this new version is designed to potentially be distributed and is less dependent on Wildcards in favor of ComfyUI nodes that handle everything in the workflow directly. The only things that would be needed would be the various LoRAs that are invoked, and I’m making a toggle for each one of those, with clearly labelled notes that link to the needed LoRA downloads.

@Scarlet Ribbon
That just makes me want to see your workflow even more… Mine are pretty basic, all things considered. I let SwarmUI handle the wildcard stuff.

@Background Pony #D936
Difficult to say. AI-generated backgrounds could be detected, but using AI-generated images as a reference or a base for tracing can’t really be detected, as far as I know.
More popular artists wouldn’t even need a LoRA for their style. Models like ZoinksNoob can already mimic a lot of artists’ styles to some extent.

It would be especially tempting if a lora for your art style already existed, I’d imagine.

(And I’m sure I saw a comment once somewhere where an artist had decided to go all in on AI art and personally trained a lora on their own art style. Not a pony artist, though.)

@tyto4tme4l
what do you think would be some tells? i don’t want to put anyone on the spot by naming names but i am curious as to what might be signs of ai usage

@Background Pony #D936
Oh yeah, totally. The temptation is too strong.

do you think there are pony artists that are using AI and hiding it?

Or maybe they just want the humanoids to be on same difficulty level as generating ponies. They are just so easy to generate without any major flaws, unlike other species.

I have a theory that MLP ponies are biomutants, genetically engineered specifically to withstand the corruption of rawgens.

@Denatural
oh thanks for that. interesting point on the hands. i guess they are trying to keep in mind mistakes an artist might make?