|
Ceramic Shot posted:Thanks, I tested MJ's icon-making abilities and it did pretty well, though .25/.25 inches was a bit too small for my printer to get all the details. The upper-middle blue icon was a bit too dark, and the upper-right yellow one is too light, especially with the tan background, but I can go back and change them. Stable Diffusion can be run locally if you have the GPU for it, and can also be run directly in Krita with a plugin, meaning you could have a template and then generate whatever you'd like directly in that template at full resolution. Plus put whatever text you want in that template right there. It's not as easy to use as Midjourney both in terms of setup or image generation, but infinitely more tweakable and, of course, ~free~ since you are providing the GPU cycles yourself. I'm classically used to Photoshop and it didn't take too long to get used to Krita in order to use it. Plus, free!
|
#
¿
Jan 3, 2023 15:27
|
|
|
|
| # ¿ May 22, 2024 10:54 |
|
|
Shadowrun is my most favorite of all PnP role-playing universes and this whole AI art deal has finally allowed me to make it real      A combination of MidJourney to 'block' out everything, then I bring it into Stable Diffusion and Krita and with my drawing tablet draw all over it, using Stable Diffusion as some uber content aware brush. I've spend the last two weeks working out a work-flow using it all, getting really precise with inpainting and trying my best to eliminate the AI tells as best I can, biggest one being the hands. Not even close to where I want to be but I think I'm making progress to, uh, something. I adore these tools for letting my imagination bring things into reality quicker than ever before. I'm never satisfied with one-shot generations as there is always something I notice that I want to reach in and fix. Being able to generate within Krita is so, so powerful and compelling to me.
|
|
#
¿
Feb 6, 2023 06:17
|
|
|
Doctor Zero posted:How dare you put artists out of work. I don't have a like, teachable good flow yet, all this stuff is bleeding edge and nobody knows what they are doing, especially me. I do have a background in art and especially photo editing, which I'd say this is mostly the nearest analog. The analogy of the content aware tool works really well for this. I should mention that the Krita plugin presents as new layers every time you ask it for a new image. If you ask for a new txt2img, you get that over whatever the image is underneath, ignoring it the picture below. If you ask it to img2img, it will take whatever is visible in your image and render a new one based off that with whatever settings you have set. Inpainting works the same way as img2img, but will only render the masked area. This allows you to paint directly on the image (or an entirely new layer) then render a new image on top of those, being informed by whatever is underneath. Here is what I've had good luck with on these Shadowrun images. Tools: MidJourney account, though I don't always use it. For these Shadowrun ones though each one started out as MidJourney. Automatic1111 with a big pile of models, for these combinations of Protogen Infinity, Analog Diffusion, and various others. Krita Auto SD Paint Extension which allows Stable Diffusion to be run inside of Kirta itself. I've got a pretty powerful computer with a 3090 and a whole heap of RAM as well. I'd like to upgrade to a 4090 or depending on how far I go into this, maybe a non-videogame render card with even more VRAM. I've also got an XP-Pen Artist 24 Pro along with two other monitors. I'll have Krita with the plugin on the drawing tablet, with Auto1111's interface in a different window on another monitor. You can use both at different times to generate using Stable Diffusion, just have to take turns and also share the model, if you switch the model back and forth within Krita or the Auto1111 interface it switches it for the other as well. However Auto1111 recently added an option to keep models in memory, and I'll do 4 at once. This means that switching between models is very quick. It ALSO means that I never use just one model, no reason to. Different models are better at different things, switching as needed. With how precise inpainting can get I don't find the absolute need for inpainting specific models, however I do want to explore than and see if they help avoid seams when I have to cut across an seamless expanse. They might be a lot better at that aspect, I'll have to see. I'll have Auto1111 on the one monitor because sometimes I want to generate something outside of Krita quickly, then just pull the generation into Krita by dragging and dropping directly in. Having two work services like this helps me work. Likewise the other monitor can be used for other stuff. More monitors is always better pretty much. I'll go into MidJourney and just kinda generate some images and see if a vague idea comes about. I did the more somber ones first which is cool but I wanted more emotion. I thought a more relaxed setting with a running team during downtime laughing with each other would be cool, so I tried 'telling jokes' and built a prompt around that. Then I thought about a troll telling jokes and altered the prompt toward that. Lucky for me I checked to see if MidJourney knew what a 'Shadowrun troll' is, since for Shadowrun a troll is just a big human with maybe tusks and maybe horns, but is normal human skin colors. MidJourney for some reason has the trolls as more goblin like and blue probably because classically trolls would be more like this in other universes. Still, I think I can work with this. Prompt: 'shadowrun troll'  Right, let's try this prompt then: Year 1985, Shadowrun, cyberpunk 2077, intimate conversation, troll metahuman telling jokes, laughing, humor, smiling, joyous, dynamic camera angle, film grain, movie shot, ektachrome 100 photo Lucky for me the first roll I did after I learned it vaugley knew what I meant with 'shadowrun' and 'troll' yielded this output.  The first image seemed like a good direction to go, kinda big monsterous sorta guy, blue sure but that's easy enough to change in Krita. Click upscale and see what we get.  Cool, I can see a future with this image. I'm sure most people can't easily tell, but it seems like I can see a MidJourney image, it has a style all its own. Into Auto1111 and make a few passes first to de-Midjourney the style. img2img, de-noising at a low setting of 0.3 with Protogen a few passes to see what comes out. The trick is to make slow changes but multiple passes so you don't radically alter the base image yet steer the results where you want to go. It's going to be a dramatic change from MidJourney to Stable Diffusion anyway. Changed the prompt to this and looped it into itself two or three times: intimate conversation, troll telling jokes, laughing, humor, smiling, joyous, cyberpunk, 1985, ektachrome 100 movie still  I work on the troll first. I want a horn so I swipe a picture of some plastic horns, trim them out, flip and warp them around and place it over the guy's head in a way that might work.  I also gotta un-blue the guy so I mask the face and gently caress with the colors and get it reasonably closer to human skin tones AND draw in the pointed ear. You can see that the horn isn't perfectly trimmed and there is a bunch of outline noise, and that the top of the ear is literally me using the airbrush tool and swiping altered colors from the bottom of the ear and just vaguely suggesting a pointed ear.  I then use the airbrush tool and mask over the face and inpaint the mask (using neon green so I can see the mask easier, you can use whatever color you'd like though) with this new, altered prompt: dark skinned native american troll with horns and pointed ears, telling jokes, laughing, humor, smiling, joyous, cyberpunk, 1985, ektachrome 100 movie still   Awesome result, but what the gently caress the ear isn't pointed at all!  I redraw the ear like last time with the airbrush tool and sampling the colors as needed and mask ONLY it, change the prompt to: pointed ears on a dark skinned native american troll with horns and pointed ears, telling jokes, laughing, humor, smiling, joyous, cyberpunk, 1985, ektachrome 100 movie still    Good, looks great. You might notice that his mouth is hosed up with a weird bit of flesh, or the outline around where the mask is. These are things I will take care of when the rest of the image is done and I'm doing the last bit of tweaking to finalize the whole image. Learned my lesson with the ear. I do this sort of thing to all sorts of bits of the image. The troll's hands holding the bottle which is me painting out whatever stuff the guy is holding and mashing a bit of hand together, cloning the bottle in the center of the image and roughly putting it his hand, masking it and changing the prompt to compensate. Here is what I did to the woman's hand holding the cup:     I then started working on her overall but came back to the hand and tweaked it later. Still wasn't fully aware I needed to work up but the hand was not in her main mask so it was ok. Speaking of the lady, mask her off and change the prompt yet again. I iterate a few times till I get a result I like. New prompt: gorgeous techno disco queen, telling jokes, laughing, humor, smiling, joyous, cyberpunk, 1985, ektachrome 100 movie still      Last one is THE one. It's her smile, it feels more full, more joyous and real. She's not being polite, she can't help but crack up. Combined with her body's stance is like she's heaving with a deep laugh. Again with the masking I'll attempt to tackle that towards the end of me messing with the image. The rest of the work is variations on that, masking out things, changing the prompt, refining things down. It still does have that thing where you'll be working towards something then go "NOPE!" and just back right out from the last 40 minutes of work you put in to go a completely different direction. This is how the plate of food ended up on the table, I got rid of all the extra cups and the hosed up hands. The plate of food was a stock image of wings. For getting rid of the tell-tale signs of masking I will mask like normal, but not bound it with the selection tool. Finally I'll switch to analog_diffuision, then strip the prompt down to the original prompt, set denoising to 0.1 and run it through a couple times to add in some nice noise and help even out everything so it looks more like an 80s movie. Not entirely happy with this specific image, but it was the first one where I did a combination of a lot of things to make it. Lots of errant halos still, the hands are hosed up, if less so than normal AI stuff. I doubt I'll come back to this image, but it's all in a single krita file with all its layers at least! Big takeaways are: 1. Like drawing, work towards details. If I did that going in I wouldn't have wasted my time with drawing that ear twice. Work in broad strokes and 'layer' up as you finish parts. 2. Smaller the better. If you can work in smaller areas within Krita you get the whole resolution for just the area you are working on. This means that two major AI tells for me, car wheels and people's faces, are rendered 'full res' when you draw a bounding box around your mask and inpaint only within there. The overall resolution doesn't change but you render that detail into the small area, like super sampling. Maybe it IS super sampling, idk. The exception to this is when I'm cleaning up errant seam lines from masking. Those I'll paint on the image directly to obfuscate the seam behind some brush strokes, then inpaint without the bounding box (thus giving a lower resolution result because it's doing the whole image even though the result is just the mask) and adjust the layer opacity as needed. Easy! 3. Using actual pictures is better than drawing details yourself. This is because the AI wants noise, that's in-built to any image you take off the internet. In the Native American troll guy above the horn ended up turning into some sort of fuzzy talisman like horn thing, but that's cool by me because it gives character that I like. It worked that I had a picture, even of cheap plastic horns, because the noise was in the image so Stable Diffusion could use that in a realistic way. If I drew a flat-shaded horn it wouldn't work as well because it's trying to put detail where there isn't any. A worse image with more noise is better than a well-drawn, flat one when it comes to realistic photo-like images. You can almost completely ignore watermarks too as that is noise that will certainly get lost in the first past, or if needed you can roughly paint them out using the surrounding colors and the AI is smart enough to know what you are going for, depending on the prompt. 4. Leave the overall bit of your prompt and change as needed. I'd keep the prompt the same, but add whatever I was inpainting on the front for that specific inpaint. Pointed ears, holding a coffee cup, etc. 5. It is easier to have a vague idea about the emotion of whatever image you want, rather than being specific. In making these I'm not saying to myself 'Ok I am going to have a troll on the left and then a woman on the right and another person just out of frame and...' instead it's 'a troll telling a joke and everyone legit enjoying it would be cool' and see what comes up. Working with things the system provides you is a lot easier to make a cohesive image. The hands are hosed up but there are fingers there for the woman so I used those and built her hand in a way that didn't immediately make my brain go "AI HANDS" and notice it to a fault. 6. SAVE YOUR PROMPTS. You can alleviate this a bit if you keep your generations and can toss them back into the 'PNG INFO' tab in Auto1111, but the prompts are NOT saved within Krita at all or the file itself. I've taken to just putting the prompts I use in a .txt file where I keep the main Krita file. KakerMix fucked around with this message at 06:26 on Feb 9, 2023 |
|
#
¿
Feb 9, 2023 06:11
|
|
|
Appreciate the kind words, thanks. I would like and hope that anyone that is even remotely interested in diving in though to go ahead and do it. At worst you spend some time exploring the tech, at best you feel pretty good exploring your own head. reignonyourparade posted:Tbh I think it sounds like in a way OP's process makes things more like writing where, imo, with enough edits anyone can produce perfectly serviceable writing. If you followed the same process perhaps it would take you more iterations than OP but I doubt it's as out of reach as you might be feeling. It's very much exactly like this, yeah. I can't draw anything presentable at all on my own without an extreme time commitment, but I'm decently good at writing and have a grasp on visuals and things. It really seems like I've been waiting for these AI systems my whole life, if I were a kid I'd be losing my poo poo that this tech is real. I suppose I am, just now I'm approaching 40 years old rather than being in high school. It's just a combination of having an idea of what looks good enough, being able to convince the system to give you want you want through actual writing, and editing or like I think of it as, refining. Most of what people are making with MidJourney or Stable Diffusion is, in my opinion, trash garbage that needs only the slightest touch, the most remote little push to really elevate it.
|
|
#
¿
Feb 10, 2023 04:26
|
|
|
Hey so I like Shadowrun, GPT-4 just came out so I gave it a shot and see what it could do. This is a crosspost from the GBS AI thread but fits here more considering the context: I caved and subbed to the Chat GPT+ thing to mess with GTP-4 and boy howdy. If you play pen and paper RPGs and like me, think Shadowrun rules, well this thing has you covered. If you don't know or care about Shadowrun then this might not mean much, but I am wholly impressed. Again. My Prompt to GPT-4 posted:I would like you to write me a backstory for a 40 year old Street Samurai (he is a Hawaiian dwarf) in the Shadowrun Universe. In the story the year is currently 2058. This 40 year old Dwarf had a father he was close with that was uncomfortably close with the corporate world and specifically the dragon Dunkelzahn. GPT-4 posted:Name: Kainalu "Tidal Wave" Kahananui I am by no means some Shadowrun lore expert, but I'm reading this and going  This is wild, wild poo poo to me, for it to understand context like it does completely in universe. Feed it a few details and it goes hog-wild, well above and beyond anything I'd write for my own character, let alone an NPC. It understands that metahumans typically have it tough, it understands the whole corporate world thing, but beyond all that it gave the dude a nickname and then at the very end used the theme of his nickname to end the text as a story hook tying it all together. It named his father, tied in where he was from with Hawaiian lore, sprinkled in a lot of hooks for other ways to enrich the story. A whole lot of role players are about to get way better stories in their games for sure. EDIT lmao gently caress My Continued Prompt to GPT-4 posted:Can you describe Kainalu, physically? GPT-4 posted:Kainalu "Tidal Wave" Kahananui is a distinctive figure, embodying both the strength of his dwarf heritage and the grace of his Hawaiian roots. Standing at 4 feet 2 inches tall, he possesses a solid, muscular build that belies his small stature. His broad shoulders and powerful limbs are a testament to his years of rigorous training in the martial art of Lua and the grueling life of a street samurai. My Continued Prompt to GPT-4 posted:Can you describe Kainalu's childhood friend? Make them human, but otherwise the details can be anything. It's also up to you to decide if they are still friends now that they are adults, and how this friend fits into Kainalu's life. GPT-4 posted:Name: Leilani "Whirlwind" Kealoha My Continued Prompt to GPT-4 posted:Can you describe Leilani physically? GPT-4 posted:Leilani "Whirlwind" Kealoha is a striking figure who embodies the grace and power of the Hawaiian islands. Standing at 5 feet 8 inches tall, she possesses a lean, athletic build, honed through years of rigorous training in the martial art of Kapu Kuialua. Her toned muscles and agile movements speak to her dedication and expertise in her chosen discipline. this is loving nuts Just spin up fully formed NPCs or hell, even main characters in minutes. EDIT x2 I won't keep posting blocks of text because boring as poo poo no matter the context, BUT I asked it to make the Tidal Wave guys dad, and it made a mistake. It made him a dwarf too, but born in 1990. I told GTP4 this fact, and asked it to change the father into a human but also take into account UGE (Unexplained Genetic Expression, when elves and dwarves were born to human parents). It gave me the same story with the details changed and a section on him dealing with his UGE baby. KakerMix fucked around with this message at 22:25 on Mar 15, 2023 |
|
#
¿
Mar 15, 2023 22:08
|
|
|
|
| # ¿ May 22, 2024 10:54 |
|
|
Ghost Leviathan posted:I'm not touching this poo poo with a presumably public domain ten foot pole, I'm pretty sure sooner or later we're gonna see a IP law takedown rampage to rival the early days of YouTube. Then I question what you're doing in the thread? Is this not touching?
|
|
#
¿
Mar 17, 2023 14:48
|
|