sbloyd

It does introduce a way to stop having us play second fiddle to the Recluses and the Positrons and the like. Kill them. Kill them all.

With anthro animals, it may be that the large amount of furry art out there has skewed the results to something Microsoft considers inappropriate.

Yup! I'm at work; my students are working on posters, so I had time to kill. My prompt was: slim caucasian man, style of artstation, wearing a white trilby hat with a black band, wearing a white shirt under a white vest under a white suit coat, wearing a white tie, wearing white slacks and white wingtip shoes, with close-cropped white hair, wearing white glasses with crimson red lenses, wearing white gloves, surrounded by a white aura of power

My attempt just from describing what I see there omitted the suit jacket for some reason, but I rather like the result:

In this case, suicide IS the answer! Debt erases patrol xp, no?

Yeah, the number of fingers phoenomena is a thing. I hate when I get a perfect render, but one hand only has three fingers, or the fists have six each.

I'll admit I sometimes overbid when buying bulk garbage recipes for the purpose of flipping them. Not by millions, of course.

Double post.

When the description bar becomes too short for what you need, shift over to Copilot and tell it "Create me a picture with the following prompt:" and put it there. Copilot has a longer input limit, and will create them using the same engine. You can hit shift-Enter after the colon to start a new line without sending the request to Copilot immediately.

Ha! I get off work in 15 minutes. Perfect timing!

I dunno, I get tells complimenting my costumes and bios all the time. And I do the same to others. What, you think I stand under Atlas all day doing nothing?

Up. They go up.

Chibi Blue!

RISE FROM YOUR GRAVE! Hey, just came back recently after about a year off. Did they change the order of execution in popmenu commands? My voice scripts for my MM Bots play in reverse now.

Macro editing is something that has been broken since the Old Days. Not to say they shouldn't fix it, but in the meantime what I do is keep a Google Doc full of all my macros and just re-create them when I want to change something.

I wish it was just mold. I really do. I do still have a copy of Shogun that only got some mold spots on the outside edge, and some fantasy books that happened to be in a cardboard box on a high shelf in the garage.

But... my billions!

About seven years ago my house flooded and I lost almost every book I have. For that reason I deal mostly in ebooks now. I vastly prefer physical, paper books but I can't go through that again.

Really, if I were gonna do a comic with AI generated work, I'd still probably want to do the *actual* panels and layout myself in something like Clip Studio; you could probably even use Clip Studio's posable figures to arrange the character(s) how you want them and import them to your generator as a base image.

BTW, anyone know what's up with being able to select certain parts of a generated image in Copilot? Like, I can click on and select the face, the hair, a hand, a background element, etc and it highlights it. But I don't see what function that has, if any.

Mainly I'm just salty because I don't normally do LotG, but dropped about fifty on the AH right before this destabilization happened. Glad to see some reasoned conversation coming out of it.

Yeah, takes some legwork but it can be done, as Krimson says. You kind of have to set up a subset of data to include with what you're working on. You can find some of these at civit.ai, and there's examples of how to make your own on websites out there. I've seen instructions for creating a lora file for your own likeness so that you can put yourself in a generated image (and this is how we get deepfakes, btw). So you *could* create a comic book by creating a lora for each character and referencing each one for the characters present in each panel. It's something I've been looking into but creating the source images would be a big step. I wonder if you could use source pictures of actual COH toons, do some infill and upscale work using AI tools, and go from there; some heavy lifting in Photoshop might need to be done.

It appears that if you ask Copilot to generate your images, you can select one and have it re-generate them selectively.

So you're saying it wasn't Stable?

If Synapse weren't such a slog, I think it would make for a good 'learn the ropes' TF.