Alright so, I attempted to make the PSG-style characters again except without wrists. It was very difficult to make it generate that consistently. I managed to get one with Erin but it needed big edits & inpainting. When I tried to generate Vivian with the thick arms + holding a gun it was practically impossible so I eventually gave up & moved on to something else.

I practically never see it generate Vivian with her hood on so I definitely had to keep that & refine it. I think it fits the delinquent theme well, especially using Kill La Kill style. Kill La Kill Style: https://civitai.com/models/625836 Pepe Punch Meme: https://civitai.com/models/537610 I noticed when I search for Kill La Kill Style it doesn't appear when logged out of civit.ai so I guess it's content filtering bullshit that's making these things I found before disappear from results. Weird since it had at least one SFW image on it.

New LoRA! https://civitai.com/models/945166 I know there's other Julie Power LoRAs already, but they have their own issues, a big one being none of them really did her costume better. I was convinced I could do better, and uh... I did? Already working on her sister: Dataset is cleaned but I need to tag it (figuring out some tags for the venom version in particular). Also: >one of my creations made the OP Neat.

I'm amazed at how very abstracted training data can translate to other styles in PDXL. >>1039404 A gallery needs a PG rated image to show up without an account. Aggressive navel and cleavage get most of Synthdark8's styles marked PG-13.

>>1039408 A lot of the fun is seeing things in different art styles. >>1039404 This really needed more cleanup. I didn't get it perfect, but a lot of artifacts are gone. Figured I may as well remove the background entirely.

>>1039391 >Making a new thread right after the bump limit while the old one is still on page 2 and active

>>1039427 I'd love to have confused looking anime girls with interrogation marks by their head pictures to do a LoRA for that, but I'm only in the low 20s and need more for a concept like that to really shine.

>>1039427 Do you still think it's 2015?

>>1039432 Where should I dump them? /b/?

>>1039432 >>1039436 >>1039433 The only thing that officially changed most recently that I can recall, is "700 posts or page 13" is now "700 posts [some other number I forget]". The goober threads still follow that rule. Otherwise, you may as well make the thread cyclical if not for the fact that the threads are sent to /ais/, and otherotherwise there may as well not be a bump limit.

>>1039437 >>1039436 /b/ works fine.Will be a few days before I can actually bake it, but it seems like a fun thing to make.

>>1039437 >make a thread about content generation cyclical You really aren't very bright are you.

>>1039436 >>1039440 Have you guys actually used /b/? The board is full of lost normalfags. Just post them on /ais/.

>>1039442 >The board is full of lost normalfags Why does that matter for an image dump on a garbage board?

>>1039443 Because I don't want to go to the bad part of town to visit the anime girl gallery. You might get guys spamming gore or spergs screaming about Christianity. /vb/ is another option

>>1039444 Nice trips, but I'm still posting it on /b/, and there will be little to none of the issue you describe. It's a slow board.

>>1039432 Done. >>>/b/464951

>>1039464 Thanks. These and the ones I already had should provide enough. Going to have to sort these for the right style matches, but I should be able to make this once I'm done with Katie.

>>1039392 Repost from the last thread. Something I requested in the draw threads long ago that I'm gonna ask again in this thread. A parody of this image but with shortstack from video game franchises with the title replaced with "shorties" instead. Character examples being Midna, Poppy, or Tristana (League of Legends), Betila (Rayman Legends), and Rouge the Bat (Sonic). You can use any other examples if you wish that would fit as long as it's Video Games related.

*First image.

Still using Forge Couple to make separate prompts for two characters, kind of a hassle regardless. I thought this would work well for Vivian & Gilda though. Vegeta in the Rain Meme: https://civitai.com/models/910694 Rain: https://civitai.com/models/521990

>>1039467 I'll be waiting ;)

Rouge dump >>>/h/5853

Are there any uncensored flux checkpoints?

>>1039641 Thanks for using my h thread as well. Wish more people would go there.

>>1039391 I appreciate the high energy behind the threads, but please, wait until it's like around 700 posts before making a new thread. Don't want to clog the entirety of /v/ with AI art. By the by, did you gents ever try this site? https://websim.ai/ https://websim.ai/p/ltw9yi7pzmnnqkft4u8u Apparently it lets you create your own custom websites using prompts and people have been using it to recreate games, host their own models and even bypass ChatGPT's restrictions.

>>1039668 Forgot to mention, you technically need a jewgle/dicksord account to join and creare your own custom stuff, but you can still load individual sites without an account if you have a direct link. Some examples: https://websim.ai/p/nc75r9lxp99kzw2zoonx Mario 64 online https://websim.ai/p/_xdhbhemv6x376dzfjhd Multiplayer Windows XP https://websim.ai/p/8zjjrizklamo6zpu5mnv GPT uncensored And of course it can run DOOM https://websim.ai/p/2k1mom8sn42y__okr9iy It's basically as if Flash never really died and just evolved into an even bigger shitposting machine.

>>1039646 if you want anime stuff, FLUX isn't very good at it and you should stick to Pony or Auraflow (apparently Pony V7 is going to be Auraflow) as for realism, flux is pretty good and most finetunes and merges already have a degree of nsfw trained back into them but you can always try LoRAs to enhance the details and other missing stuff.

Need a voice clone of Hat Kid saying: "The only MAP you're gonna need is directions to the nearest morgue." That (with some background rain noise) would complete this image.

And here's the Katie Power LoRA I mentioned in >>1039405 https://civitai.com/models/946423/katherine-katie-margaret-power-energizer-power-pack-earth-5631?modelVersionId=1059625 Also Civitai now has video generation with their on-site generator, but it's so stupidly high price I wouldn't bother.

>>1039672 Is Auraflow tag or natural language based? After I actually tried working with it I grew to despise the "natural language" of Flux (and SD3.5). It ultimately became clear it was just tags but with extra steps and with no way of knowing what phrases actually worked before generating (with tags you can just check against a list of tags) in the vast majority of instances. Flux is also incredibly inconsistent stylistically, even when you specify what to use, and how it draws common things. The character limit on prompts also makes it lose any theoretical advantage in making higher complexity images.

Did you know there are LoRAs that let you see farther up a skirt? We have the technology. Extended Upskirt: https://civitai.com/models/778722

>>1039666 Any time Satan.

Anyone tried PixNova AI? I just discovered it. No account needed. https://pixnova.ai

>>1039850 I tried this Lora-less. This was fun.

Every online service I want to use requires a Google account. Does anyone know a good site for free phone numbers so I can make an account with a VPN?

>>1039392 make ai phoebe plox thx

>>1039905 BUG PUSSY

>>1039905 did you use a lora for hornet? >>1039915 who?

>>1039905 >thig bug butt very nice

Lain Iwakura: https://civitai.com/models/328752

Confused looking anime girls with interrogation marks on their heads https://civitai.com/models/950882/confused-looking-anime-girls-with-interrogation-marks-on-their-heads?modelVersionId=1064608 >>1039432 >>1039436 >>1039437

>>1040146 >It actually worked Sugoi.

>>1039984 mascot of >>>/vb/ theres more pics in >>>/vb/964 if you want

>>1040147 Honestly, I'm not even sure it was necessary. Without the LoRA loaded the same settings as the first one (including seed) give pic related

>>1039984 No character Lora either. Check out the prompt. >>1039915 What is her canon hairstyle supposed to be?

>>1040191 the one on the right with the shoulder-length hair and big titties the titties are supposed to end around the ribcage, i think

>>1040164 Could maybe be useful for consistency when piling on other LoRAs.

(づ｡◕‿‿◕｡)づ I got VPred checkpoints working.

>>1040238 >goth coco bandicoot YES. You should make a goth version of coco like these or anyone who feels up to it.

>>1040296 This is the only big booba Coco that is canon.

>>1040323 Look at Tawna & the trophy girls. There's no WAY coco doesn't become fairly stacked when she's older.

>>1040296 >>1040323 >>1040325 Bandicussy. Bandisnatch. Bandibooba. Bandiawooga.

>>1040327 NOW THAT'S WHAT I'M TALKING ABOUT! inverted nipples fuggen wew lad. It almost hurts to look at, so wonderful

>>1040335 Here's the full grid since you liked it. Inverted nips look like funny lips. https://files.catbox.moe/hy2irp.png

>>1040340 That's a lot of Coco. Thanks, i should get into AI stuff. I got an nvidia gpu with 12 GB of vram.

>>1040388 >credit system Ew

>>1040146 Really great, thanks anon.

>>1040381 It's nice seeing Lina out in the wild again. Got any more?

https://civitai.com/models/951957?modelVersionId=1065794 New LoRA: Rena from Metal Max 2 Reloaded. It got a fan translation 3 years ago and is an awesome game with awesome OST that you should totally go and play.

>>1039392 Requesting Shantae transforming into her Harpy form and flying into the world trade center.

>>1040412 I doubt this request but I'd also like some goth Shantae's with nice hips & thighs.

>>1040418 You can't request that without at least giving a reference.

Anyone know of styles for Pony that generate sharp black shadows? I wish there were a LoRA for a style like Dead Leaves the anime film, I think that'd look really neat. Here's what I have found. Toon Graffiti: https://civitai.com/models/689853 >won't consistently make dark shadows on characters & background Vixon's Bold Anime: https://civitai.com/models/888211/vixons-animemanga-styles-bold-anime-bwpink Vixon's Contrast: https://civitai.com/models/888251 Dark Charcoal: https://civitai.com/models/400401/dark-charcoal-style-pony >these kinda do it, but they're geared for monchrome https://civitai.com/models/612648/decreased-coloring-pony-xl >makes edges look shitty Most the time these apply super dark shadows to backgrounds & not to characters. I can't find much that really does what I'm looking for.

>>1040427 Damn this would go great in an horror themed spin off with rottytops al

>>1039392 I want to see >>1039405 >>1039792 in just their panties (the kind worn by their 616 counterparts. Pics related) standing and looking at the viewer embarrassed to be seen like that.

>>1040137 I like how it can keep the details of Lain's eyes.

>>1040481 >>1040483 Very 40K/Divine Cybermancy esque.

>>1040406 >>1040381 >>1039393 Okay, made another one.

>>1039392 Requesting a Thanksgiving or Christmas-themed Vita-tan. Halloween Vita-tan would be fine too but it feels too late for it.

>>1040599 Brilliant stuff anon!

Do not open.

>>1040418 >>1040427 >>1039393 Excluding background & style terms, this can take you to an approximation of Gothtae: Shantae LoRA: https://civitai.com/models/453587 Punk Boots LoRA: https://civitai.com/models/935750 POSITIVE PROMPT: <lora:shantae-pdxl-nvwls-v1:0.7>, defshan, pointy ears, blue eyes, (hair over one eye), black nail polish, dark purple hair, very long hair, high ponytail, (circlet), hoop earrings, pale skin, black crop top, low-cut top, short sleeves, skinny belly, exposed belly, midriff, (cutoff shorts, denim shorts, micro shorts, fishnet pantyhose), <lora:punk_boots_doc_martens:0.5>, boots, black footwear, lace-up boots, knee-high boots, (black fingerless gloves), (black spiked bracelet:1.1), (half-closed eyes), NEGATIVE PROMPT: spiked hair accessory, (partial stocking, thigh high stocking, exposed thighs), eyeshadow, thong, garters, gold spikes, black shorts, bare hands, two-tone hair, gem circlet, text on shirt, I used Wakfu/Dofus style LoRA for good waist/hips body shape. Envy Pony Cute 03 Wakfu-Dofus LoRA: https://civitai.com/models/391228

>>1040670 Do painted fingers nails have a positive effect on the proper generation of hands due to there being more clear end points?

>>1040670 Also, forgot the body shape prompts. This helped with the shape I was going for. big head, short, 1girl, teen, large breasts, (large cleavage), narrow waist, (wide hips), slender calves, (chibi:0.4), Putting (realistic) in the Negative Prompt also helps if some style LoRA is changing the face. >>1040674 Kinda. Can also mention (fingernails) or (detailed fingers) in the prompt. Chose to keep her eyes blue although the goth Shantae has purple eyes. Forgot to put (black choker) in the prompt. The long striped glove on one arm would require regional prompt or in-painting. The prompt got rather cluttered & the boots it was generating sucked so I got a LoRA to do them. Regardless, you got an idea of how to prompt most of that.

Best Castlevania girl.

Looking for tags for this character for next LoRA while I'm waiting for one to finish baking. In particular: What the hell do I call the split cape/double scarf thing? >Karst_GS, pink skin, facial mark, red eyes, pointy ears, red hair, short hair with long locks, ponytail, double ahoge, bare shoulders, scales, ???, crop top, print shirt, miniskirt, print skirt, elbow gloves, thigh boots, pointy boots,

https://civitai.com/models/957773/the-road-warrior-jacket?modelVersionId=1072314 And said LoRA is now out. Show me random characters dressed in the jacket from Mad Max 2: The Road Warrior.

>>1040343 Neat. You'll probably be faster than my AyyyMD rig. I sugg you start genning with Illustrious and work your way into Pony. This way, you may avoid having a Lora folder that's over 180GB.

>>1040754 >>1039393

>>1040809 Nice.

>>1040471 >>1039405 >>1039792 >>1039393 Different poses, but very embarrassed. 1st attempt I think the hair wasn't quite right, 2nd attempt was too ambitious with multiple prompts so it took ages to fix things. 1940s Illustration mixed with Alkemanubis for the style,

I feel bad asking this anywhere, but I want to get started learning this stuff, and I have no idea where to start. Everywhere I turn, people seem to already know basics that I do not comprehend. What websites do I go to? What programs do I use? What do various terms mean? What are the free options and how badly do they suck compared to paid options? What are techniques that you guys consider important? All I know is how to search "free AI image generation," click on websites until I find one that is actually free, then type in words and be disappointed with results. >tl;dr: spoonfeed me newfag info. I've clicked on the resources pastebin and it's not spoonfeedy enough. A complete retard's guide to this would likely be something good to put in the OP. You might get more activity that way. I'd join in, at least.

>>1041006 The good online ones are usually dead or a pain in the ass to use, I still weep for nemusona

>>1041006 >programs At this point you want PDXL ("Pony"), and/or ILXL ("Illustrious") for most purposes, with Flux being a more GPU intense option that has some advantages (acceptable text handling, ability to pull off some interesting things with natural commands) at cost of extreme disadvantages (awful license, much more resource expensive to run, poor with non-realistic styles without being taught to copy a specific style). SD1.5 is lighterweight and has a more open license as well as a lot of plugins made for it, but it has some very frustrating limitations and is outdated for most things. If you want the absolute basics of "What is all this?" level, Civitai's intro video is decent but a bit outdated in software/model recommendations (despite not even being a year old. This field moves fast) https://youtu.be/IIy3YwsXtTE?list=PLlVSBOQWxoKntlHmA3eLvODWb7uCttbfK Civitai also has a free generator with customizable settings (for web) and relatively loose restrictions (essentially no real people, no loli/shota, no bestiality, no guro). The main catch is the "buzz" use, which is really just site credit. You get ~220 a day(rollover at midnight GMT) from doing basic site interactions (takes just a couple minutes) and need 3 to generate most images (just set the images returned to 1 and tip to 0). You can get more by browsing without blocking ads, having users interact with stuff you've posted on site (as an established user, I get maybe 150 a day from this on a good day) or (outside the scope of free) buying it at a rate of 10 USD for 10,000 buzz.

>>1041145 I prefer running local to avoid censor limitations & pay-pigging, but there are shortcomings. Firstly, it's harder to make the installation of everything required idiot-proof. Even supposedly simple one-click installers can wind up with an incompatible version of Torch or something that you'd have to remove & swap manually. I've had plenty of issues where something that should work doesn't & I have to either reinstall everything or search everywhere for a solution that requires more effort & most often doesn't solve the issue. This leads to paranoia over updates so I'd get left behind by staying on an old install that I had stable & working. There's also people who simply can't learn or require explanation on a level that is like trying to navigate a boomer through tech troubleshooting over the phone. Nightmarish. One guy early on became a meme for not comprehending things that were spelled out in many ways, to the point where a video was made to spoonfeed such people. Outdated now as most things, but the process is still similar & at least demonstrates a "git clone". I'd recommend Forge over Automatic1111 at this point as Forge is much faster. Forge can't use Regional Prompter though, it has to use Forge Couple (if you want to do multiple prompts for multiple characters, otherwise this doesn't matter). Even if you're not being nickel & dimed by some online AI site so they can comfortably over-fund their upkeep, there's still a cost with local AI since you're best off with an expensive high-end GPU. Sure you can use mid-lvl hardware, but you're gonna be waiting a while or else making smaller images to compensate. Regardless, a high-end GPU can do far more than AI & you actually OWN the hardware, for many people owning the hardware & not being subject to any censorship is non-negotiable. I'm likely stubborn enough that if my GPU failed I would not be using the online stuff & instead save that $$ for another GPU.

in the mood for some citrus!

>>1041231 >SD1.4 >2022 dates in explorer That's even more outdated.

>>1041271 Post this shit on Facebook claiming to be a young African artist and you'd get 50000 comments all saying "amen!! amen 🙏"

>>1041231 >Sure you can use mid-lvl hardware, but you're gonna be waiting a while or else making smaller images to compensate. By "smaller images," do you mean in terms of resolution? Because that might not matter for what I have in mind. Basically what I want to learn to do is do basic sketches (though I'm not good, I could at least do layouts or whatever), then have AI improve it so it looks like a reasonable drawing, then I can manually touch up the AI result, even tracing it fully if needed. I even figure if doing multiple characters at once is hard, I can do them one at a time, then edit them together in GIMP or whatever. I can use AI to make sketches better, right? I'm more interested in that than I am in text to image generation. But when I look up tools, they all want money, or at least accounts, and I really don't know where to turn. I don't want to shell out money or even make an account when I'm just blind guessing at what is actually going to be a good tool to use.

>>1041362 >what I want to learn to do is do basic sketches (though I'm not good, I could at least do layouts or whatever), then have AI improve it so it looks like a reasonable drawing What you want image to image or some specific stuff (this isn't an area I know well, but do know it is possible). There are local solutions, for this, but I don't know enough to guide you through it >I can use AI to make sketches better, right? Better is subjective. Be prepared to curate and correct a lot of "AIness" when doing this.

https://civitai.com/models/963390/atsuko-inspector-gadget?modelVersionId=1078606 Turns out nobody has made a LoRA for Atsuko (from Inspector Gadget) yet, so I made her. >>1039392 Atsuko holding hands with Penny.

>>1041231 >Sure you can use mid-lvl hardware, but you're gonna be waiting a while or else making smaller images to compensate >you're best off with an expensive high-end GPU. The RX 7600/3060/Arc 580 is good enough.

I'm gonna share a few BA gens that came out kind of nice.

>>>/h/5887 Fuzzy breast milk.

Can someone give me a quick rundown on how to train a LoRa on specific artists/poses/characters? I really want to make some for very niche stuff but I have no clue where to start and what are the best practices/fastest routes.

>>1041571 >3rd and 4th I wonder what the AI is trying to say here.

>>1041586 https://github.com/derrian-distro/LoRA_Easy_Training_Scripts?tab=readme-ov-file#installation I got as far as downloading this. I think anon explained how pretty well in the previous thread.

>>1041586 use the civitai trainer. you have to create an account on that site and then you may need to pay to have enough "credits" to train a lora but it's definitely the best alternative to actually buy the hardware to do it locally, also it's probably the cheapest way

>>1041586 https://civitai.com/articles/8370/ Ultimately comes down to four things you need to do >gather a training data set >use basic image manipulation techniques to "clean" training data to remove other characters/text if needed/possible >tag training data >set the settings on the trainer and hit run Poses are a bit different. You can train a pose like any other LoRA (and is likely better if you want some degree of style bleed, like for a pose from a meme), but for local gen there's also openpose, which lets you arbitrarily pose your results by moving wireframes (which can be saved and shared). Using openpose means you don't actually have to train to get a pose. >>1041639 You can easily get enough credits to train a LoRA just the daily tasks for three days. That's less than it sounds since it rolls over all at once at midnight GMT and you only need a few minutes to do the tasks (so do tasks right before changeover, wait till changeover, and do tasks again). I think you get a one time bonus for joining and that's enough to get it with just 2 days of credits. You can do it even faster if you browse with ads off.

>>1041651 but I want to train a lora for FLUX since that seems to be the best at realism and real people and FLUX training seems to cost a lot of credits, a lot more than pony and 1.5 at least.

>>1041639 Carizard.

>>1041271 >>1039392 >orange megaman I request the Yellow Devil but in a giant lemon form in that similar style.

>>1041671 >I want to train a lora for FLUX 17614f didn't specify base model >since that seems to be the best at realism and real people It's more that Flux can only really do realistic without having a style LoRA attached. In my experience it's impossible to get the thing to have any kind of consistent art style or consistently draw the same article of clothing in a particular way without a LoRA. (Honestly, I don't understand the point of making stuff with real people outside of shitpost/memes about public figures.)

>>1041680 >Stuff with real people Honestly, I can only think of porn, aside from the memes

>>1041712 Yeah, but who cares about seeing famous real people naked? They're either underage, already taken their clothes off, or are hags. Why bother when superior 2D girls exist?

>>1041717 Yeah I agree, most actresses get their nudes "leaked" by the age of 20 nowadays so there isn't really a point to actresses LoRAs. But what if the real person isn't famous, what if the LoRA 17614f wants to make is someone they know IRL?

New video game girl LoRA I made. https://civitai.com/models/960286?modelVersionId=1075145 Training data wasn't the greatest, so details are off (ears aren't quite right, facial mark isn't right at all) but overall functional.

>>1041785 >shantae based on Apostles style Very nice.

CAT - Citron Pony Styles - Realistic Anime: https://civitai.com/models/362745?modelVersionId=420176 Autumn Dark Academia: https://civitai.com/models/580598 Shadows Lighting - Concept: https://civitai.com/models/675108 I don't think these LoRA style Lain quite the same as other characters. Lain's eyes look cool regardless.