/v/ - Video Games

Vidya Gaems

Index Catalog Archive Bottom Refresh
Options
Subject
Message

Max message length: 12000

files

Max file size: 32.00 MB

Total max file size: 50.00 MB

Max files: 5

Supported file types: GIF, JPG, PNG, WebM, OGG, and more

E-mail
Password

(used to delete files and posts)

Misc

Remember to follow the Rules

The backup domains are located at 8chan.se and 8chan.cc. TOR access can be found here, or you can access the TOR portal from the clearnet at Redchannit 3.0.

Interboard /christmas/ Event
Help Needed! Inquire Within!


8chan.moe is a hobby project with no affiliation whatsoever to the administration of any other "8chan" site, past or present.

Reminder that 8chan.se exists, and feel free to check out our friends at: Animanga ES, Traditional Games, Comics, Anime, Weekly Shonen Jump, /b/ but with /v/ elements Official 8chan server: mumble.8ch.moe:64738

AI General ( DALL-E 3 / Stable Diffusion / Voice Cloning / Chatbot ) Anonymous 11/13/2024 (Wed) 20:25:09 Id: 3563d2 No. 1039391
Just Like One Of My Japanese Animes Edition [Copied OP from previous thread] Use this thread as a catch-all for AI related topics. Try to stick to vidya and help your fellow anons out. PLEASE SHARE EVERY NEW RESOURCE YOU FIND ───────── ✦ ✦ ✦ ───────── Resources: https://pastebin.com/fLMeAMb1 Previous Thread: https://archive.fo/SLOaP Previous threads are moved to >>>/ais/
(1.01 MB 960x704 Request Anchor Dog.png)

Request Anchor
(943.80 KB 960x704 Delivery Anchor Cat.png)

Delivery Anchor
(984.26 KB 2398x2143 Erin Sword.png)

(1018.13 KB 1920x1080 00173-3355690205.png)

(1.50 MB 1920x1080 Reaching.png)

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.
(1.33 MB 3840x2160 Vivian Delinquent.jpg)

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.
(137.66 KB 832x1216 FC7CVNX3KPM2AH18RD68155GH0.jpeg)

(115.77 KB 832x1216 65FXR8YKH4WF8D9H45A3FMSB90.jpeg)

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.
(2.28 MB 3840x2160 Vivian Delinquent.png)

>>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.
(234.39 KB 571x469 nepquestion.png)

>>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.
>>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.
(1.47 MB 1930x2160 Autistic Imouto.jpg)

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
(184.08 KB 1210x796 1731560284670_image.jpg)

>>1039467 I'll be waiting ;)
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.
(7.26 KB 400x400 ZS4Kfmt8_400x400.jpg)

>>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.
(155.20 KB 1216x1024 image.webp)

>>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.
(2.60 MB 2880x2400 Hat Kid with a Gun.jpg)

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.
(224.05 KB 832x1216 DTKS2PS2TF34FEHGDYEBKBY6K0.jpeg)

(192.70 KB 832x1216 NJGZ82RSCZ6CRQ8BCWXNGXD9E0.jpeg)

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.
(1.37 MB 2880x2400 Sayaka (Extended Upskirt).jpg)

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
Anyone tried PixNova AI? I just discovered it. No account needed. https://pixnova.ai
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?
(117.87 KB 733x465 pb.png)

(603.05 KB 1730x1129 pb2.png)

>>1039392 make ai phoebe plox thx
>>1039905 BUG PUSSY
(35.03 KB 896x1152 image.webp)

>>1039905 did you use a lora for hornet? >>1039915 who?
>>1039905 >thig bug butt very nice
(4.45 MB 3840x2160 Lain Dialing Up.jpg)

>>1040146 >It actually worked Sugoi.
>>1039984 mascot of >>>/vb/ theres more pics in >>>/vb/964 if you want
(195.44 KB 1024x1024 0XYEQ6B1KTX9MB5WP9S06KWNY0.jpeg)

>>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
(1.28 KB hornet.txt)

(1.18 MB 1024x1488 00738-1837409462.png)

(1.31 MB 1024x1488 00741-1837409462.png)

(1.39 MB 1024x1488 00742-1837409462.png)

>>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.
>>1040238 >goth coco bandicoot YES. You should make a goth version of coco like these or anyone who feels up to it.
(411.75 KB 1100x1203 coconuts by squidapple.png)

>>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.
>>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.
(3.04 MB 3840x2160 Lina (Envy).jpg)

(2.75 MB 3840x2160 Ashley Graham (Mess).jpg)

>>1040388 >credit system Ew
>>1040146 Really great, thanks anon.
>>1040381 It's nice seeing Lina out in the wild again. Got any more?
(231.54 KB 832x1216 HYCBJETRGVN9DTCZDAVPQC0H90.jpeg)

(184.51 KB 832x1216 9S639VGHF58TBB157SWDXXT6E0.jpeg)

(208.66 KB 832x1216 JA262YTKY1ZTTD4EJZG628YVK0.jpeg)

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.

(131.59 KB 800x1216 IMG_8301.webp)

(122.12 KB 800x1216 IMG_8302.webp)

(133.19 KB 800x1216 IMG_8303.webp)

(170.42 KB 800x1216 IMG_8305.webp)

(137.56 KB 800x1216 IMG_8306.webp)

(2.54 MB 3840x2160 Lain (Low Angle).jpg)

>>1040137 I like how it can keep the details of Lain's eyes.
(169.15 KB 1920x1080 not AI.jpg)

>>1040481 >>1040483 Very 40K/Divine Cybermancy esque.
(3.20 MB 3840x2160 Lina (Rage).jpg)

>>1040406 >>1040381 >>1039393 Okay, made another one.
(721.77 KB 1472x2048 Vita smile.jpg)

>>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!
(3.06 MB 2160x3840 Gothtae.jpg)

>>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
(2.79 MB 2600x3600 thinking kuppahime.jpg)

>>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.
(152.21 KB 523x775 GSKarst.jpg)

(173.20 KB 296x483 87979170_p0.png)

(95.49 KB 209x440 twitterdrawing.png)

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,
(237.01 KB 832x1216 HD3KE8M6GCXD1M4D8RHNHK3W20.jpeg)

(190.42 KB 832x1216 K29MWDZY5QBCTE59VN7X218T20.jpeg)

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.
>>1040809 Nice.
(3.74 MB 3840x2160 Julie Power.jpg)

(2.95 MB 3840x2160 Julie & Katie (Caught).jpg)

>>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.
(45.82 KB 1024x1024 image.webp)

(40.86 KB 1024x1024 image.webp)

(37.08 KB 1024x1024 image.webp)

(32.71 KB 1024x1024 image.webp)

(42.62 KB 800x1216 image.webp)

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.
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.
(346.55 KB 565x565 clueless.png)

>>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.
(53.92 KB 1184x1024 image.webp)

(50.73 KB 1184x1024 image.webp)

(47.68 KB 1184x1024 image.webp)

(52.77 KB 1184x1024 image.webp)

(157.18 KB 1184x1024 image.webp)

>>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.
(1.30 KB 600x555 YellowDevil.png)

(126.34 KB 695x585 Yellow_Devil_MK-III.png)

>>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.
(1.76 MB 3840x2160 Lain (Dark).jpg)

(2.66 MB 3840x2160 Alice (Daily Treatment).jpg)

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.
>>1041678 I tried since base Schnell doesn't know yellow devil fruit from MegaMan, here's the orange pulp base prompt if you want to try it out yourself. > hyper-realistic image showcasing an extraordinary piece of orange pulp, meticulously sculpted into an elaborate [OBJECT] form. This single, standout pulp segment should be the central focus, with its [OBJECT]-like contours and features exquisitely defined. The texture should be remarkably detailed, showcasing the natural, fibrous quality of orange pulp, and its color should be a vivid, true-to-life orange, emblematic of fresh citrus. The [OBJECT]-shaped pulp must be vivid and pronounced, set against a soft, unobtrusive background that enhances its striking form. The image should encapsulate the imaginative fusion of natural fruit textures with the majestic form of a [OBJECT], all while maintaining a lifelike appearance.
>>1039392 I want to request a LoRA for Grace the >>>/monarchy/ & >>>/8flags/ macsot OC she is also popular on /leftypol/ I just think she is really cute. more images of her on this thread: https://8chan.moe/hisparefugio/res/227639.html#241249
(30.41 KB 1024x1024 IMG_8355.webp)

>>1039393 Forgot to tag the delivery anchor >>1041984 for >>1041678 Here's another attempt
(967.31 KB 2160x1616 Lina.jpg)

(1.12 MB 2160x1616 Elaine (Lockup).jpg)

(2.01 MB 2880x1616 Cirno Snowy.jpg)

(663.21 KB 2160x1800 She-Goat.jpg)

(2.05 MB 2880x1616 She-Goat (Pillory).jpg)

Franco Saudelli: https://civitai.com/models/632276 Dark Charcoal: https://civitai.com/models/400401 Used these LoRAs together. Results vary.
https://civitai.com/models/644586/karis-golden-sun-dark-dawn?modelVersionId=1085886 Updated one of my oldest LoRAs to my modern standards since I found a bunch of new training data when looking for data for >>1041793 Already got my last few LoRAs of the year planned out. All video games.
(432.73 KB 758x721 so good.png)

>>1042088 Fucken sweet.
(3.32 MB 2048x2400 PROMOTIONS.png)

(107.79 KB 1024x1216 image.webp)

(156.71 KB 1024x1216 image.webp)

(70.78 KB 1024x1216 image.webp)

(82.02 KB 1024x1216 image.webp)

(115.40 KB 1024x1216 image.webp)

vidya babez
(2.35 MB 2400x2880 Megumin (Bandaids).jpg)

>>1042262 >>1042356 I see nothing since it's covered. However, the subsequent post joking about micro coverings on nipples & pussies got deleted so perhaps mods are changing their PROMOTIONAL standards over 130 posts into the thread. There's more examples in here to spoiler, if they want that extra work go for it.
>>1042495 >so perhaps mods are changing their PROMOTIONAL standards over 130 posts into the thread. If the edge of the nipple is visible, that's still part of the nipple that's visible. Those things just get away with it sometimes by virtue of being unnoticeable at a glance.
>>1042088 The Crino picture is nearly indistinguishable from a pixiv or dA piece, the only thing that stands out is the odd perspective on her icicle wings. AI singularity when?
>>1042530 The "edge" is the areola. In anatomical diagrams areola & nipple are labeled as separate parts, yet I suppose the areola could be colloquially considered with "the nipple" as a whole. Still, I don't think the whole area of the areola releases milk as the nipple does so functionally they're separate. Regardless, by north american censorship standards showing the areola wouldn't be permitted. Those standards are of course are ever-changing & certainly unfriendly to loli content. (puffy areola) & (erect nipples) in the prompt are fun. (from below) & (low angle) are great as well. >>1042538
The horny just won't go away x_X >>>/h/5906 >>1042541 Torpedo breasts and inverted nipples are also a blast.
And now a wholesome story about two girls hooking up. Also why using the Norman Rockwell with Penthouse comic stylings does a nice detailed retro feel for things.
>>1042660 Oh god, the bimbo + bubblegum autist is back. Try adding some wonderbread to the mix.
(2.29 MB 2880x1616 Hex Maniac 1.jpg)

(2.48 MB 2880x1616 Hex Maniac 2.jpg)

(2.26 MB 2880x1616 Hex Maniac 3.jpg)

(1.52 MB 2880x1616 Videl.jpg)

(2.08 MB 2880x1616 Hat Kid.jpg)

(2.32 MB 2880x1616 Etna.jpg)

(1.67 MB 2880x1616 Edward.jpg)

(2.20 MB 2880x1616 Edward Lift.jpg)

I later found that I should increase weight of a certain term in the prompt so it might give more texture to everything. (hatching /(texture/):1.2)
There was this chinese "text to video" site posted a while back, I checked it again on a whim and now it redirects you to an english version and requires you to sign in to use the site, the only available sign in method is with a google account, so I'm pretty sure it's exclusively for data harvesting users now. I actually wonder how much of google is run by china, with so many websites exclusively requiring login via social media accounts it seems like the perfect transition to social credit scores.
(2.73 MB 2880x1616 Gwen-vitation.jpg)

(2.10 MB 2880x1616 SprEdward.jpg)

The range of what can be done with Stable Diffusion is neat, but rarely without issue. On one seed I couldn't hi-res upscale at 0.4 denoise as usual, since it kept fucking anatomy up by reversing one of the feet, but using a lower a denoise doesn't increase detail so I had to continuously hunt for a seed that didn't give the AI whatever room it needed to screw that up. I remember using OpenPose on SD 1.5. Although it seemed like a godsend in theory, in practice it was taking more time to generate images & devaluing my prompt. I went back to using LoRAs for poses after that. Dunno if OpenPose has improved or if there's any means of speeding it up. Forge has spoiled me with greater speed. If I had a 40 series GPU it'd be even quicker & I wonder how quick the 50 series will be for SD.
>>1042946 >that Ed My God it's full of stars!
(1.75 MB 2880x1616 NOT lewd.jpg)

The drawing style often reminded me of those lewd single-panel comics with bottom text. Erich Sokol comics from old Playboy magazine have a neat style, but there's no style LoRA for that. There are some Playboy comic style LoRA, but they didn't impress me.
>what if Zeon was a cute girl? https://civitai.com/models/975461 Alma Stirner from Mobile Suit Gundam Battle Operation Code Fairy. Going to finish out the month with the four "main" girls from this game.
>>1042984 >there's no style LoRA for that How many of the original do you have?
(2.15 MB 3840x2160 Elaine Pirate Lifestyle.jpg)

(1.16 MB 2880x1616 Elaine Gambling 2.jpg)

(1.17 MB 2880x1616 Elaine Gambling.jpg)

>>1043002 Only a handful. Saw more on Google Images. >>1042983 Didn't save the prompt, sorry. >>1042984 Played with this idea more.
>>1043048 If you could assemble ~100+ (multiple panels can be broken up into multiple pics) you could train a style (and honestly it may be below that. Number of pics needed for a character is very well documented compared to pics needed for styles.). If you're really desperate, Flux only needs ~10 examples to learn a style.
(1.73 MB 1760x1216 00080-2516469940.png)

(1.41 MB 1760x1216 00078-638929600.png)

(1.32 MB 1760x1216 00077-2516469940.png)

(1.42 MB 1344x1944 00076-3468059599.png)

(1005.18 KB 1520x1048 00006-3134908286.png)

Î̷̤́̈́̄͐̂̎̍̑͑͑͂̈́͌̑̚͘ ̵̨̜̤̯̱͓̙̊ͅf̸̨̨̛̛̛̛̳͇̳̹̖̘̮͔̲̞̞̺͕̜̼̣̮̦̣̬̺̄̈̏̇́̾͐̀̉͂́͋̆̇͊̒̐̃́̈́͊̓͐̔́̃́̏͊̎̑͘̚̚͝͠͝͝ͅo̴͚͚̭͖̬̓͋̿̎̃̀̌̿̓̾͗́̏̎̒̓̀̐͌̾̓̈̎͂̂̊̒̐́̚̚̕͘ư̵̛͍̜͇̜͚̜̦̙̜̣̾̔̌̎́͛́͑̋̏̓̆̈́̾̎̋̍̿̽̎̏̈͆͛͋̂̎̓̿͋͐̀̚̚͜͠͝ͅn̶̢̧̨̨̢͍͈̮͖̖͇̦̰̤̳͇͉̥̩̠̤̥̯̦̙͕̦̍͐͌̀͝ḑ̶̢̧̯̹͕͇̯̘̖͍͎̤͉͔̭̗̀̑̈́̇͊͆͐ ̶̡̨̧̨̢̧̙̻͈̹͔̖͙̳̬͔̠̺̻̰̩̖̪͚̟̣̭̟̝̱̤̬͕̙̙̙̩̭͙̘̦̊́̆̋͗̈́̍̓͐̀̓̋̂̆͋̑̒̽͊̑̀͑͜͝͝t̴̡̡̡̡̹̻̥̣͈͕̰̥͈̜̩̮̺͈̲̖͇̞̯̖͈͗͑͌̈́͌͋̂͗̋̋̌͂̑̿̐͂́̌́͛̄̕̚͜h̷̛̠͈̻̜̖̘͙̭͆̄͒̿́̍̍̀̄̏̀̈́̎̒̍͒̽͂́̽͂͂̄͗̄̔̈͋̀̐̅̐̚̕͜͝͝ȩ̶͉̟̻̙̗̞͓̜̯̱͇̬̺̹̺̤̤͙̺̼͈̩̙͙͍̞̒̔͑̎̏̃͘͜͜͠͝ͅ ̷̛̰̟͍̞͈̳̗͎̖͉̙̫͂͐̊̀́́̈́͒̃̾͗̓̓̐̀̿̎̔̇̈́͑̿̽̊̒̆̇̄͐͌̔̏̚̕͘͘͘̕̚͜͝͝š̶̡̧̨͈̰̲̲̰̺̬̤͕̼͓͔͚̭̤͕̦͈̞̈́̈́̃̉͗̾̏̀́̓͋̈́̏̆̊̊̌̋͋̈́͘͜͝ͅț̵̢̨̡̛̜̬̹̲̫̻̤͕̻͓̺̞̣̱̝̞̲̩͈̭̬̞̭͇̤̀̓̄̊͆͒̿͗̅͑͐͗̎̾̊̈́͑͌̃͛̋̔́̅͛̿̿̀̏̈́͠͝͝ͅŷ̷̢̢͇̳̤̟̖̺̻͈̋͑́̌̋́̋͊͒̇̓̀͂̽́̉͗͗̑͌͒̇̅̿̃̅̑̈͛̑͛̀̍̅̃̆̓͌̒̂̋̚̕͜͠͝͝ͅl̷̡̨̧̨̧̛̥͕̪̙͕̝̦̠͇͓͖̣͇̰̳̮͖͓̪̥̽̔͛͌̈́̔͆̈͋̋̔͂̒̃̽̓͒̍̉̈̽̽̕̚͝͝ͅͅệ̸̢̛̛͕̯͙̬̈́̃͊̅́̄̾̀́͗̇͒̍͐̃̚͘͘͘͝ ̴̺̮̀͋̉̃͗̆̒̎̓͒̐͐͂́̍̽̔̽̀̄͐̐̒̈́̇͛̀̅̀͂̾̎̓͘̚f̸̟̙̪̖̖̙̞͙̠̬̮̜͎̤̤̺̤͓̮͍͚͉͈̌̅̇̑̃̓͛̎̏͐̉̆̔̇͛͛̈́͜ͅơ̵̡̧̢̛̛̛͔̠͈̲̼̥͚̭̬͉̫͙̘̗̪̗͈̟͎̰̯̪͚̜̻̰͙̳̺͔͉̬̖̙̬͕̺̹̲̼͍̣͇̙̊̃́̿́͐̒̉̏͂̑̒̈́̊̈́̑̀̈̾̽̽̀͊̌͠͝͝͝ͅŕ̵̮͎̲̯̫̜͚̱̫̭̦̼͈̪̫̻͉͇͇͖̬͚͈͎̤̮͖̬̠̺͗̅͛̾̉͛̅̊̈́̈́̈́̀͋̒̾̌̿͐͋́̏̉̓̃͗̀̌̚̕͜͝͝ͅ ̶̢̨̢̧̢̨̧͕͍̳̰̙̠͙̠̞͚͈̞̠̘̙̣̩͔͖̣͎̗̰̖͎̤̯̥͍̩̘̞͍̜͇̗͙̫̮͉̰͓̈́͘͜ş̵̨̢̨͇̞͖͖̱͔̫̫̪̘̫̞̘͓̖̺͓̲͐̿͜ḩ̸̢̡̣͙̥̣͕̪͖̺̝̼̱̳̹̟̫͈̘͚̼̘̭̯̜̄̀̆ǫ̷̧̨̛̹̜̩̝̣͍̟̬̺͎͇̞̯͉͚̺̞̣̟͉̗͈̰̰̮͙̘̳͉͉̲̺̍̅̌̈̆̋̀̂͐̿̓̃̌̒͂͂́͗̅̂̀̄̉̏̅̍̾͒͒̾͗̈́̈́̊͑̎͂̅̈́̆̓̃͛̚̚͘͝ͅr̵̢̧̨̡̧̮͖̲̬̯̲̹̲̺̩̭̝̟̯̲͖̬̼͍̤̯͐̓̿̒̈̽͌̈́́̿̽̓̔̍̍͘͝ͅt̶̡̡̖̗̼̲̗̥̹̖͙̟̗̖̻̮̜̪̘͎̲̙̦͓͇̤͇̹̲͉̦͂̉̂̀̎̈́̽̃̕ͅs̶͖̞͓̖͂̀́̃͐̒͌̒̊̎̈́̓̊̈́͊͒̑̈́̇t̸̢̧̧̧̧̙̮̤̗̙̗̮̮̫̠͔̠̟͎̥̤͔͕͔̦̤͔̻̳̯̹̼̳͇͚͕͈̙̝̰̩̪̻̗̀̈́̉̉̈́̐̎͋̀̍̕͜ą̸̛̛̦̙̘͈̠̩̣̯̩̻̠̩̞͖͈̮̱̤̪̗͎͓̩̈́̂̓͐̐̐̔̒̈́͋͑͌̉͂̒̄͜͝͠c̴̡̪͈̬̠͊́̓̑̔̿̔̆̓̀̂͒̃͊̃͛͐̇̀͊͛͛̉̒͂͆̄͐̍͐͗͑̚̕͝͠k̷̨̢̡̧̛̛̛͕̝̦͙̬̩̠̮͖͚̜̠̗̜̙̣̱̙̩̹̣̯̘̼͎̠̯̺̺̠̬̙̻͇̠̼̝͒͋̑̈́̇͌͗̾̈́̇͌̈́͛͐͐͂̐̆͛̎̒̂̂̌̾̑̅͑̓̾̈́̀̀̀͘̚̕̚͝ ̵̡̡͇͙̬̟̤̮̟͚̮͉͇̱̖̦͉̫̝͂͋̿̃̈̈́͆̒̔̇̂͋̽̚̕͜c̸̢̨͔̟̞͖̻͚͉͚̳͎̻͔̲̝̭̥̤̲̼͇̖͈̭̪̖̻̲͙̰̪̹̱̱̮͊̍͜ͅͅĩ̶̧̢̡̼͕̰̙̞̮͉̹͇̪̯̗͔͚̙̞̤͈͙̱͆͛̾̑̑̇̍͆̽̐̄̂̎̓̆̌̓̂͂̀̄̿̈́̈́̚̚̚ẗ̵̨̧̧͇̙̼͔̣̣̩͎͎̺̪͓̻̗͓̰̻̮̳͎͔͖͚̗̙̜̦́͐̀̽̆̾͐̀̒̌̕͜ͅy̴̧̧̢̨̧̰̻͙͍̟̲̮̫̝̮̤͇͖̳͔̘̫̗͈̭͚̯̹̘͖̳̘̘͇̜̞͍͉̲̒͗͛̀́̈́̒̅̏̂͂͋̄̊̂͜͠͝ͅ
(1.07 MB 1944x1344 00032-2616735650.png)

(1.18 MB 1944x1344 00031-2616735649.png)

(1.43 MB 1944x1344 00029-2100103774.png)

(1.48 MB 1944x1344 00021-2100103766.png)

(1.30 MB 1944x1344 00019-2100103764.png)

(853.74 KB 1200x1440 Vivian (Anon KYS).jpg)

(295.44 KB 520x632 KYS.png)

(242.81 KB 1201x1267 SD-Forge-ControlNet.png)

(50.39 KB 1174x1269 SD-ForgeCouple-Mask.png)

Playing around with the MistoLine model for ControlNet. Couldn't get their recommended preprocessor Anyline to show up in Forge unfortunately, but Forge still has some lineart preprocessors I can use to extract lineart information to use with MistoLine. The guy who wanted to improve sketches could maybe use something like this. I'm seeing if I can use it as a substitute for OpenPose. I also used Forge Couple for regional prompting the two characters separately. In Mask mode you can draw masks for the areas you want each prompt to affect while using your first or last line as a global prompt that effects everything. AI kept generating her toes bare no matter what so I had to give up on her wearing black socks like the source image.
https://civitai.com/models/978880/mia-brinkman-gundam-code-fairy-code-fairy?modelVersionId=1096363 Made Mia Brinkman to go with >>1042990 . Going to do Helena and Lilith this week to complete the set. >>1043289 What about it?
(418.71 KB 803x993 Tired Vivian Face.jpg)

(838.35 KB 1920x1080 Chel Excess 1.jpg)

(632.67 KB 1920x1080 Chel Excess 2.jpg)

(915.61 KB 2560x1440 Lina Denied.jpg)

(2.79 MB 5400x2240 Kanker Sisters.jpg)

Made a Vivian based on a reaction image, some excessively lewd Chel images, a cute Lina, then I tried to do another Kanker set. Mixed these LoRA for style: Ed Edd n Eddy Style, 0.2 weight : https://civitai.com/models/888464 CAT - Citron Pony Styles - Realistic Anime, 0.8 weight: https://civitai.com/models/362745?modelVersionId=420176 Semi-Realism Style, 0.6 weight: https://civitai.com/models/701339 Used Kanker Sister LoRAs, 0.8 weight for each. Lee: https://civitai.com/models/386785 Marie: https://civitai.com/models/377013 May: https://civitai.com/models/385685 I think May's tits should be slightly bigger than Marie's for muh headcanon as I strongly dislike when they're all drawn with huge tits not differentiating their sizes-shapes. but that's the best gen I had for the time it was taking. It's hard to make May short enough without the head size being too big. Maybe should've used shotstack tag on all of them, but Lee is too tall, tried chibi & big head tags with varying weights. Hard to balance proportions to be unique to each sister, but similar enough to still fit together. I enjoy seeing all three sisters in styles uncommon to see them in, yet still leaving them recognizable. It's rather challenging to do that though.
(32.22 KB 482x549 it-s-all-so-tiresome.jpg)

>>1043374 Such a lovely mirror.
>>1043384 MistoLine with ControlNet is pretty good. Was even matching up the hair strands as you can see. Seems to work easier with an anime/cartoon reference & can get it very close if not spot-on while using my prompt to change things. Tried with poses from real nude model photos & results weren't so great unless I turned the weight down which had it partly ignore the reference image, yet it still imitates aspects of the reference that are useful for getting a similar pose, camera angle, framing, etc. >>1043389 I'm on AutismMix-confetti, but I keep using character LoRAs. Maybe I'm just wasting drive space if it already know these characters anyways. I waste a lot of drive space on LoRAs, often finding something I might use or it just looks neat.
>>1043401 That's really useful. Thanks.
Man we need more wide hips with good thighs Chel & the same with Raven but she also has a big ass..
>>1043410 At first I thought you meant Chel from Portal, and was going to counter with all of the other Portal girls as better choices.
(459.25 KB 2669x2833 1710180701946271.jpg)

>>1043414 Chell has TWO L's for fuck sake. why would I refer to anyone else? >>1043433 bleagh, this freak isn't attractive at all.

(69.58 KB 842x848 bully2.jpg)

>>1043282 >>1043282 Another AI edit.
(143.71 KB 832x1216 VADBV3XYYD3HATJFA9J3MKZ380.jpeg)

(192.55 KB 832x1216 DQ0XKE2EG9YQKJJA18N1ES37A0.jpeg)

(212.50 KB 832x1216 1653YYQMEZJ215RPAQV9Q7X690.jpeg)

Anyone know of any poses that are all of >reliable/consistent >not just a single tag >work with just base model ? I recently discovered >leaning forward, bent over, hand on own hip, hand on own thigh/knee works pretty reliably and is pretty cute. Pics related is trying it with various art styles.
(1.85 MB 2400x3232 Bullied Straight.jpg)

(334.92 KB 886x1200 bully_guns.jpg)

BAM! "Thought you could hide, faggot? Pants. Off. Now!" This was time consuming. Styled it like Trigger animation by using LoRAs for Kill La Kill & Edgerunners: https://civitai.com/models/625836/kill-la-kill-style https://civitai.com/models/630275/cyberpunk-edgerunners-style
(1.13 MB 1800x2160 Lain Reveal.jpg)

(1.82 MB 2400x2880 Ed Machine 1.jpg)

(1.89 MB 2400x2880 Ed Machine 2.jpg)

Still using lines from existing images to get poses with MistoLine. Next level would be posing 3D models to use as reference for the AI, but for now I'm just using images I already have.
>>1039392 I'd like to use a funny pic in next month's GotM, could someone redo this but with Vivian or something along those lines?
>>1043754 Vivian standing up, Erin behind her, /v/ at the wheel, infinity symbol as the hood ornament.
>>1039392 Anything with Silk spectre if possible. I read watchmen for the first time and i absolutely love her. There is barely any scene showing her body, ass or legs.
(358.63 KB 457x720 20241124-125628.png)


(486.43 KB 1016x987 20241124-124430.png)

Any suggestions for this hairstyle beyond "white hair, short ponytail"? The character has two hairstyles so I need some kind of hair tag that's visible from straight ahead (like pic 1) where the ponytail isn't taggable.
>>1043836 Half bang with ponytail?
>>1043837 Not a tag.
>>1043837 >Half bang with ponytail? Don't mind if I do!
(2.02 MB 2880x1616 Vivian, Gilda & Erin.jpg)

Stayed awake far too long trying to finish this.
>>1039392 I humbly ask somebody to gen non-human femboys, entirely because I'm curious how that vague request will be interpreted.
Which online AI chatbot should I use for casual conversation?
>>1043999 Also excellent
>>1043999 >Not Anthro Wot are you GAY?!
>>1043836 Found the right tag: "wispy bangs". It's about as low usage as a tag can be on boorus and still do anything, but it does something (I guess the fact that it shows up in real world fashion talk that was likely scraped by base SDXL helps) which is what I needed.
>>1044047 oh i get how tags work now. I'm a goddam fucking retarded ass nigger. I'm very sorry.
I take all the pics here are AI made right?
>>1044051 The majority are, but various reaction images, example/source images, workflow images, and odd logo for AI things are present in the thread.
>>1044052 I could deal with the whole realistic anime goyslop but seeing all the different styles of bot techniques and styles I think I want to kill myself, to be honest, family member.
>>1044053 Are you an aspiring artist?
>>1044064 He's an aspiring autist.
>>1044053 Are you the fag who complained about about some high quality pic made by a real artist being AI slop?
>>1044064 I'm a second rate drawfag. >>1044083 Not me that sounds gay.
>>1044103 Just add AI to your workflow. It can be used as little or as much as you want and it can help skip a lot of the tedium. For example you can use AI just to color your lineart, or just to add finishes, or just to generate the background, etc. It's very versatile.
>>1044107 You know what fuck it. I'll try the forbidden fruit.
Ok huh. Can someone explain me how does it work in potato terms, because I'm pretty fucking stupid.
>>1044116 >Potato terms There are none. It's a super autism hole. Actually doing things right takes time and effort, just far less than learning to draw.
>>1044116 Just delete System32. It contains advanced Windows code keeping your computer from becoming sentient.
>>1044118 >computer becomes sentient >immediately kills itself Heh
>>1044116 Check the OP pastebin, it has links to guides.
(1.91 MB 2160x3840 Vivian Deep Water Vibe.jpg)

(1.12 MB 1800x2696 Chel (Below).jpg)

Making some interesting poses using reference images with MistoLine. >>1043410 >>1039393 Here's another Chel then.
(536.04 KB 640x480 64-1.png)

>Don't use AI text stories for several months at a time >Wonder why I stopped >Try it again for the umpteenth time >Immediately encounter the issue >Constantly the AI will generate text from the first person perspective instead second person, which is the perspective the whole story has been told from the entire time This shit makes me want to take a hammer to my computer. Why the fuck can't it do this one simple thing?
>>1044146 >spoiler the taint and tip <huge voluptuous balls on full display
>>1044166 The fag thinks balls don't count and just smugposts at anyone that says otherwise. This is even more retarded than areola autists saying it's not part of the nipple, so it doesn't count. The anus is also on display, and the tip censorship makes me think this guy subscribes to the Japanese idea of what "effective" censorship is.
>>1044163 Oh, and this wasn't always the case, but it seems now that no matter what I do with whatever settings, the AI will always have overly flowery language and run-on sentences that lose direction.
>>1044145 That Vivian is very soothing, her hair looks really nice against that blue water too.
>>1044111 >semi-canon Birdo More funny than anything. >>1044146 >generates the pokeboy anyway after >>1043999 Autism works in mysteries ways
(230.58 KB 1300x700 Spot the difference.jpg)

>>1044169 Areola autism was related to 1 post singled out for a supposed violation which could be easily found throughout the thread. And if vols are cool with balls/anus unspoilered, but not the edge of a female's areola I'd just assume we're policed by sodomites. And even if meant jokingly, the bandaid-censor was also joking yet the post was deleted. People mostly use this AI to make porn so this thread may well be pushed to /h/ eventually since it's always littered with spoilered nudes. Regardless, ON TOPIC go on civit.ai & you'll see popular female characters are flooded with endless futanari pics while genderswapped males or Rule63 is a drop in the ocean by comparison. The last big Rule63 was Bowsette & some offshoots. Haven't seen it blow up quite like that in ages. Not much into genderswap so I guess I can't think of many examples. >>1044163 >AI chat bot changes perspective Yeah, that's aggravating. Seen it before, yet it seemed rare. Could also just be character card related. Some seem to have a broader scope of improvisation, while others are inflexible. For example, if you take a character away from a place they hate, yet they keep trying to force that place back into the story because it's in their card. They can't forge a new path anywhere without the user writing stuff into their lorebook. Even then, they can be inflexible with doing episodic content divorced from the main story, since they're too focused on one thing in the lorebook.
>>1044186 >Areola autism was related to 1 post singled out for a supposed violation which could be easily found throughout the thread. And if vols are cool with balls/anus unspoilered, but not the edge of a female's areola I'd just assume we're policed by sodomites Report the balls/anus post >>1044146 and see if it gets spoilered, that'll answer that assumption.
>>1044186 >this thread may well be pushed to /h/ eventually since it's always littered with spoilered nudes. No. >>>/h/ is under 6000 posts, are you /h/ BO or something? Don't do this or this thread dies.
>>1044181 Yeah, I can almost hear underwater sounds or chill music. Speaking of images with music. A gondola LoRA exists for SDXL, but doesn't seem to work for Pony. Also, this is useful for making hair flow like that: https://civitai.com/models/494841/pony-hair-flow
>>1043573 Hands on hips, usually
>>1044238 Nobody here plays games, boomers here just talk about politics surrounding it and complain how industry isn't catering to them. Palworld discussions stopped once the popularity around it decreased, otherwise it was 300+ posts on threads.
>>1044251 You fresh off the boat or something? The game is still in early access and people already finished most of the content available to them already, I don't see what Palworld has to do with "politics" for that matter either.
>>1044103 >I'm a second rate drawfag. So AI is taking away your desire for improvement? >>1044146 That's a juicy cock ngl
>>1044192 >are you /h/ BO or something? No, he's not, and the AI thread is my least favorite active thread.
(19.25 KB 200x149 200w.gif)

>>1044280 That's my thread nigga
>>1044238 I'll pick it up again if there's any meaningful update, but given the company's track record of publicly abandoning games in EA, I doubt it.
>>1044282 Congratulations. Not everyone likes incomplete deformed art. I've only known one local AIfag to regularly polish his work, and he's almost /loli/ exclusive.
>>1044285 Actually, now that I think about it, the Vivian AIfag makes two. But Uohtism is still more autistically thorough more often.
(51.53 KB 1024x762 EPFr8DAWkAcFG1P.jpeg.jpg)

(153.25 KB 850x1275 so sorry.jpg)

>>1044263 Well, when I said "non-human" I wasn't specifically thinking YIFFE. Like I said I was curious how it would be interpreted, and feral Pokémon seemed to be how.
>>1044284 They recently announced a huge island update for next month and a terraria crossover for 2025 so besides the pokemon lawsuit, the future for Palworld seems pretty bright
Doing some voice cloning, what's the best voice cloning AI right now?
I was doing ElevenLabs TTS years ago btw, I assume there's better TTS now?
>>1044315 The OP's "Resources" section links https://pastebin.com/fLMeAMb1 which has a "Voice Cloning" section, which says 11Labs is the best on the market, but may be outdated since this field moves fast. >11Labs, requires shekel donations to do anything good with it, free tier only gets bland voices but it's the best on the market https://elevenlabs.io/ >FakeYou, lots of models, most of them suck so voices may com e off stilted, however it's the only truly free one of the bunch, can upgrade for better load times https://fakeyou.com/ >UberDuck, used to be just like Fake You, now needs to sign up. Lets you sing and shit. https://www.uberduck.ai/ >OpenVoice, new kid on the block, does awful voice cloning, however it's about as fast as it gets when it comes to generating new voices and it's highly customizable, also free. https://huggingface.co/spaces/myshell-ai/OpenVoice https://github.com/myshell-ai/OpenVoice >RvC, the de facto standard for music cloning. There used to b ea google collab for it but they nuked it. It's the thing used to make all those Frank Sinatra covers. https://colab.research.google.com/github/ardha27/AI-Song-Cover-RVC/blob/main/RVC_TrainingV2.ipynb https://invidious.private.coffee/watch?v=hB7zFyP99CY
>>1044291 >bottom twink Venom
>>1044296 REAL FINAL UPDATE GUIZE! WE TOTALLY WON BE UPDATING THIS GAME FOR THE NEXT 30 YEARS
>>1044291 >>1044324 C-could you make him a little more shota?
>>1044327 Parker wouldn't oil drill Venom's asshole but that nigger Morales would do it. Find an alien freak and just fuck its ass cause he's a stupid feral nigger, fried chicken and muh dik is all he knows.
Made two more LoRAs to finish off the set of >>1042990 >>1043365 (and because I could get most of the screenshots I needed for them while getting those two) and be my last LoRAs for the year. That brings me to 53 LoRA(+5 retrains/V2s), which is a lot since I've only been doing this since June 27th. https://civitai.com/models/981682/helena-hegel-gundam-code-fairy-code-fairy https://civitai.com/models/985435/lilith-aiden-gundam-code-fairy Since I'm not going to be doing any new LoRA in December, I've put up poll on what people want converted to Illustrious. All I've found says that's just a matter of running the throwing the same training data at the trainer again with a different model selected (please tell me otherwise) https://civitai.com/articles/9197/december-hiatus-poll-for-what-to-convert-to-ilxl
(907.90 KB 711x1136 roughtweak.png)

>>>/h/5957 >>1044285 >Not everyone likes incomplete deformed art It's so Splatover for me ....
>>1044370 Thanks for the attempt anon but he reads more like a male shortstack than a shota.
(1.05 MB 3000x3000 Texas Vivian.jpg)

(563.50 KB 1800x2160 Vivian Walk.jpg)

(993.88 KB 2880x1616 Vivian Semireal.jpg)

(2.67 MB 3840x2160 Vivian Photoreal.jpg)

>>1044286 Crashing the Vivian fanart market with no survivors. The range of what can be done with one character in stable diffusion is crazy.
>>1044590 That's a nice Mibibi anon.
can't believe how much a strap can change her default look.
>>1044771 Lucina?
(3.14 MB 2880x4848 Hermione Charmed 3-Panel.jpg)

(1.01 MB 2880x1616 Hermione Charmed 1.jpg)

(1.08 MB 2880x1616 Hermione Charmed 2.jpg)

(1.08 MB 2880x1616 Hermione Charmed 3.jpg)

Maho Shojo Alkemanubis Style LyCORIS: https://civitai.com/models/294142?modelVersionId=497224
>>1044827 You could probably use it to make Marth too with "genderswap"
>>1044601 That photorealistic Vivian is really good, the clothes and hair accessories actually look like something that can be worn. >>1044771 Some Lucina content is unexpected, but very much welcomed. The computer definitely took some creative liberties when it came to making that smartphone (?) and video game controller on her bed.
(1.05 MB 2880x2400 Bottomless Ed Pinup.jpg)

(1.07 MB 2880x1616 Inkling White-Inked.jpg)

(241.26 KB 519x390 00020-2979752607.png)

(1.65 MB 1416x1000 00012-2687301153.png)

(1.40 MB 1416x1000 00024-2979752615.png)

(341.59 KB 847x421 00025-2979752616.png)

(1.58 MB 1416x1000 00011-1032930776.png)

>>1045319 >Inkling Frickin' awesome.
(1.21 MB 1416x1000 00029-2979752621.png)

(1.38 MB 1416x1000 00028-2979752620.png)

(1.36 MB 1416x1000 00027-2979752618.png)

(1.46 MB 1416x1000 00026-2979752617.png)

(1.29 MB 1416x1000 00016-2979752602.png)

(1.85 MB 3840x2160 Vivian & Erin TRIBute.jpg)

Put off finishing this for a long time since in-painting some areas was giving me a lot of grief.
>>1045523 Any chance of a Viv and Gilda strip gaming picture?
(58.93 KB 1024x1024 image.webp)

(59.13 KB 1024x1024 image.webp)

(68.46 KB 1024x1024 image.webp)

(33.78 KB 1024x1024 image.webp)

(43.68 KB 1024x1024 image.webp)

nintendo power!!!
>>1045765 >vivian as a rogue so cute. It reminds of the group pic of all the v characters as dragon's crown classes, vivian as sorceress, gilda as a ranger, an v as a fighter. Can you do one for Futaba (persona 5) as a mage/sorceress in oblivion classes art?
>>1045765 Don't know how I missed the Oblivion class art LoRA being added. It was actually one of the things I considered trying to make were I not taking a break from LoRA making.
(233.87 KB 832x1216 43308408.jpeg)

(206.84 KB 832x1216 W4BAV3Y8VA1CBHS5EFQ35FZR80.jpeg)

(149.77 KB 832x1216 6FP3DSKQJYEC99S4H59KPBA540.jpeg)

(124.62 KB 832x1216 DNMMG9NM5N52T7E5KX5ZR88C80.jpeg)

>>1045905 forgot images
>>1045911 Sometimes i dont understand how Bethesda not banking on Dagoth's popularity. Some artists and AI wizards make some real banger content with him (not just fan arts, but videos and other media).
>>1045922 Because Bethesda is owned by a kike with zero ounces of fun in his system.
>>1045922 You know damn well if they bring him back they will fuck and retcon his whole persona.
>>1045927 I never said it will be a good thing, i said its just strange how they didnt milk him like they do with the Vault Boy.
>>1045922 What could they do with him though? He did appear in the only Elder Scrolls crossover thing already. He'd be a good pick for TES representation (alongside default Dragonborn) in a Microsoft crossover thing and that's in but MS seems too inept to make MicroKart.
>>1045546 >>1039393 Took all day. Made two versions. After AI showed me some poses I liked, I Photoshopped simple figures of those poses so I could re-use them on anything. Here's that figure image as well if you want to use it with MistoLine & regional prompting. I'd recommend "holding a controller" LoRA, but it always wants to draw top face of the controller in inpainting no matter how the controller is facing.
>>1046030 Hey that's pretty excellent. Given that most ai art I see is of a single character getting two doing something cohesive like that is quite impressive. Amazed you got Gilda's panties right.
(859.91 KB 1616x2880 Futaba (Oblivion Classes Art).jpg)

>>1045896 >>1039393 K >>1046036 Single character is easiest. For 2 characters, there are tools for Stable Diffusion to mark out specific areas & give a different prompt for those areas, also a global prompt that effects the entire image where you put background, art style & anything else the entire image should have. This is higher difficulty since you're writing multiple positive & negative prompts all at once & altering them all as you go. For specific things, I Photoshop them into the image, save the image, drop the image into Stable Diffusion, inpaint the object or detail that was added so the AI can blend it into the rest of the image. It doesn't always blend perfectly, but it can get it decent enough. The following had to be added to the image using Photoshop & in-painting: >pattern on Gilda's panties (AI made it a little messy during upscaling, but mostly intact so you can tell what it is) >Gilda's scarf >Gilda's skirt >Gilda's jacket on the floor >Gilda's training bra >DS4 controllers (because AI wouldn't draw them correctly, had to screenshot a 3D model at the angles I needed) >Vivian's ribbon (because her character LoRA doesn't have it) >Anon (generated separately with an "against glass" LoRA) >text on Anon's shirt & text bubble I tried to generate Anon behind a window so I could just put a whole new window into the main image, but it wouldn't do it so I had to Photoshop him behind the existing window. Tried to alter framed pictures on the walls as well, but couldn't get them to blend well enough. I've managed to do it before, getting the added images to look "splotchy" so they blend into the background, but the AI doesn't always want to co-operate, Post is long already, may as well point out where multiple prompts were used: >>1045523 >>1043996 >>1043607 >>1043282 >>1041720 >>1040997 >>1040599 >>1040381 >>1039512 >>>/ais/4630 >>>/ais/4829 >>>/ais/4892 >>>/ais/4982 >>>/ais/5016 >>>/ais/5018 >>>/ais/5020 I'm tired. G'night.
>>1046080 So what you're saying is that AI is a long, LONG way from me being able to say "draw this" and getting it.
>>1046089 It's certain things require it be told in a very particular way. You can say "draw this" but if you want the best results, you need to put in work.
(75.63 KB 1024x1024 image.webp)

(90.18 KB 1024x1024 image.webp)

(80.84 KB 1024x1024 image.webp)

(50.55 KB 1024x1024 image.webp)

(65.07 KB 1024x1024 image.webp)

ready for christmas?
>>1046384 I need a new PC
>>1046294 >>1039393 Sure. >>1046384 >minimum requirement >45GB or 60GB of VRAM It's like I'm reading a poorly-translated Chinese joke.


Forms
Delete
Report
Quick Reply