sbloyd

...and stop-motion puppet sure looks interesting!

I'm 100% confident that my Warshade is not. I just find respeccing a PITA.

Adding style of vector art alongside cel shaded yields some nice results for my usual prompt lead-up:

CoH is just that EXTREEEEEEEME!

I really like Bottom Middle.

I've been tinkering from time to time trying to get a rendition of my Beam Rifle Sentinel, Sox, an alleycat implanted in the chest of a suit of powered armor. a suit of human shaped red and gold steampunk powered armor with an entire black and white alleycat sitting where the head and chest should be, carrying a futuristic beam rifle The hard part was getting to to not just put a cat head on a Space Marine.

1- No. They're totally dependant upon what models the generator is trained on. If I have a generator that's trained only on, say, Pixar characters the results will be a lot different than one that's trained on everything on DeviantArt. 2 - It's hard to get a drow; I guess there's a lot of dark elf pr0n out there. Best I was able to get is... ...but that was after a LOT of tries the system kicked out. The prompt was wide angle, full body, cel shaded, fantasy, style of artstation, character design, character turnaround, concept art, reference sheet, elf woman, pointy ears, long white hair, dark purple skin, glowing red eyes Trash guy, though... is a little TOO humanoid: character design, humanoid shape made out of garbage, tricicyle for a head, crouched in an alleyway

Using the Microsoft creator, I've hit the text limit on the prompts; luckily it appears that going into Copilot and saying "Draw me a picture with the following prompt: blah blah" gets you around that. Whew!

Being able to also place our chest insignia on the back and on the shoulders would be fun: ...but I don't know if the system can "read" our logo from other costume parts. While we're at it, a nice undercut or sideshaved hairstyle would be keen.

Adding "concept art" to my character-turnaround prompt looks pretty good, too. Here's one:

Microsoft Creator does a pretty decent job of rendering Kheldian forms, surprisingly!

A lot depends on playing style and what one finds fun versus tolerable versus tedious. My riches were built off the Auction House and Converter Roulette. I can absolutely see how many would find such a thing tedious to the extreme; I get around the tedium by having a second monitor and watching Warhammer 40k battles while I churn my sales... and I don't push it near as hard as some of our mercantile heroes. I don't think it's appropriate to tell someone "you're just not trying hard enough" when they say they can't afford to purchase enough Aether for a tier 3 costume. If it weren't for my deep pockets I wouldn't be able to afford it either, as my play interests don't get me any Aether at all (with the exception of the Halloween event, and that was almost accidental). Adding new avenues to access Aether is a good thing, IMHO.

Yo, dawg, we heard you liked goggles...

Shower thought time: maybe an intermediate difficulty step where the self-res is instead a self-Extracted Essence summon? (To represent the Nictus fragment tearing free.)

RE: my character being a total dump truck... I think I actually did have a Pixar preset flagged, hah hah!

Back to the fun stuff! One interesting thing about Stable Diffusion is that you can feed it a base image alongside a text prompt. I took a screenshot of my main, Horizon Twilight, and did a couple iterations of generation on it: ...might have to go visit Icon, I think! (And hoo-boy, my Stable Diffusion likes them thicc!)

Yeah, AI generative art doesn't *directly* take anything from anyone. It does , for lack of a better word, learn by examining thousands of pieces of art to create algorithmic data which is associated with certain keywords, and which gets used as part of the output when we use various keywords in our prompt requests. The question, which is beyond the scope of discussion here, is whether this is ethical or not. I have a fine art degree equivalent to a Masters, and I'll tell you, we are made to mimic other artists' work over and over; you have to ask yourself whether there's any difference between the two. Me, I see AI generative art as a toy, and a tool, to work on my own art. One of the software packages I use includes built-in, posable 3D models of people, common locations, et cetera. You can literally load them into the drawing program, pose them, and trace them. It's just another tool. One nice thing Bing has done is an attempt to exclude using specific peoples' likenesses - generally it will kick out a prompt with someone's name - though from time to time people have figured out ways around it. Those situations - from MS's generator to Stable Diffusion to other generators - are where we get weird and disturbing things involving deepfakes. Anyhow, it's up to each of us individually to decide how we use these tools. If you feel like it's inappropriate... then don't use 'em. I certainly don't try to pass off the results as my own work, but it's very interesting to generate a dozen or so images and see how the different weights and randomizers and seeds all fall together to create an image. Either way, I hope we can agree to let it rest (at least here - this doesn't feel like the right venue for such discussions).

It's just a way to make the system limit itself in certain ways. A lot of the front-page artists on Artstation have some similar design themes, so it's a handy one I can remember. You could also do "Style of John Byrne" and it transforms results to something like and "cyberpunk style" gets me . Not very different, but consistent. Taking out the style requestor, I get these four results: ...which, while not BAD, are inconsistent in style from result to result. At the same time, you can pull out "cel shaded" which forces a cartoon/comic book style and replace it with something like "painterly style" and get something akin to which can be very appealing. Sometimes it doesn't know what to do with some style prompts; I asked it for "Impressionistic style" and got and and in the same round of outputs. Really though, that wasn't fair, since Impressionism isn't something there's a lot of superhero picture samples around. A "watercolor painting" style prompt yields . You can also try things like "lineart style" or you could go way retro with "style of roy lichtenstein" and get type results.

Depends. Using Microsoft's image creator, using their tokens, it's a couple seconds. Once you run out of tokens, it's a few minutes.

My first billions were made on the Everlasting CC circuit, though that's not as active as it used to be. Once I had a nest egg, I went all-in on Converter Roulette on the AH. For the longest time my "system" was to run with Veracor's afternoon Hamidon, pick Reward Merits for both rewards, then beeline over to the MSR and do that, converting everything to Rewards, then shifting the whole shebang to Converters. Then I bought a bunch of crap recipes off the AH, and started rolling the dice!

I work in a big, ancient school building, solid as a rock. No signal. 😞

I would love flag designs on a center panel - separate from the keyed colors and patterns, similar to some of the later designs like Imperial (I think) that had static gold design elements. Like... or

I wish I could see these, but work blocks your image provider.

Oh, man, I wish I knew about this. I have a rather nice bayou base....