Reposan a question from last thread that didn't get answered. Can I get a recc on decent, fast LLM models good for RP? I have no idea what to download and for what purpose. There's a enormous number of models and little in the way of documentation about them.

OP post is probably not great. Need to add guide for oogabooga & silly tavern for running LLMs locally, but I only see those guides on jewtube, not written. Renty's silly tavern guide did not appear to be for running locally. I reintroduced Request & Delivery anchors like back in the days as there are people who are better at these things & it's also nice to get ideas from others. Anyways, I played around with Ashley & style LoRAs so I'll dump some stuff. >>1020471 I liked using LLaMA2-13B-Tiefighter, but there's likely better stuff by now. Dunno.

Was hunting for a Budd Root style LoRA, but only found this Cavewoman character from that artist. Rather nice regardless.

>>1020469 Food inspired by your favorite vidya character

>>1020487 them titties are too small if it's trying to impersonate budd.

>>1020547 I tried to match size to another image generated using that LoRA & they didn't look small to me, but I've been generating a lot of loli so my perspective is probably skewed. I wanted to try figuring out how to gen multiple characters with regional prompter, but even with it installed & enabled it wouldn't appear as a drop-down menu like it's supposed to (ADetailer was installed the same way & appeared). In the end I wound up using the old ways with Photoshop & inpainting to get Hex Maniac & Gengar on the same image. Very time-consuming. I'm sure if the extensions to do it in the web UI worked it'd be just as much of a time sink regardless.

>>1020622 >>1020468 big pokemon tits

Was making a LoRA. Any other tag suggestions for this girl? >Elie_Lunar, red hair, ponytail, sidelocks, cape, yellow cape, jacket, collared jacket, raglan sleeves, dress, red dress, pantyhose, white pantyhose, boots, red boots,

What model for textgen do anons use? I'm using nous-hermes-2-mixtral-8x7b-sft.Q4_0 with Kobold, and it seems to have a strong habit for verbose run-on sentences that change topics wildly with a tendency for exponential increase in grandiosity and emotion.

>>1020469 hot looking babes with sexy dressing and big boobers.

>>1020686 female, girl, 1girl, cute, black eyes, short hair, long legs, smile, light smile

Used Photoshop & Inpainting to get things looking okay, then multiple SD Upscale images at different denoise settings blended together with Photoshop. With SD Upscale you can get better details at a higher denoise setting, but it always breaks anatomy so you have to do low denoise upscales too, then blend all the upscaled images together in Photoshop so you can get good details in most areas while not breaking anatomy in other areas. If there's one minor thing you want to improve you can crop out a 512x512 section of the large upscaled image, throw that into inpainting where you can be super-focused on generating one thing like eyes or fingers as everything else is cropped out, afterwards you just slap the improved 512x512 portion back into the upscaled image where you cropped it from. TL;DR AutismMix is a good name for the checkpoint I'm using since really pushing for good results is an autistic & time consuming endeavor.

Where last bread?

>>1021384 Read the OP: >>1020468 >Previous threads are moved to >>>/ais/ Previous thread: >>>/ais/4017 Previous previous thread: >>>/ais/3494

Also can anyone delete the background from >>1020686 ? Every method I've tried has proven broken.

>>1020468 ATTN: Please edit the OP post Remove everything after the divider & paste this instead (as it includes everything): Resources: https://pastebin.com/fLMeAMb1 Previous Thread: https://archive.is/4Ndbd >>1021402 After looking at previous threads, current OP is missing a lot of stuff right after the post cutoff as the post was copied without being expanded & the second long-ass post wasn't copy-pasted at all. Honestly, the OP posts have gotten way too long. To the point where you have two massive posts that have to be expanded, then a third small post after that. Putting ALL AI stuff in the same thread is convenient, but the OP post is insanely huge. It's at a point that you may as well just link ONE resource list so the OP post can be ONE post that is far quicker to make, less intimidating so anyone can do it & it doesn't become a game of waiting until someone else does it. If you don't like pastebin then suggest an alternative to de-clutter OP as I can't think of one.

>>1020490 >>1020470 Watermelon cake for THE STRONGEST 2hu.

>>1021417 That's more of a Photoshop request, but sure why not. >>1020470 Tried messing with this using IMG2IMG for fun, but really need a trained LoRA to keep those zig-zag patterns on everything.

>>1021641 Prompt/model/lora?

>>1021671 Some things were added later with Photoshop & Inpainting so were not in the prompt until I was adding them. I've excluded them for brevity as you're probably not gonna get that stuff normally. >Positive Prompt: ((score_9), score_8_up, score_7_up), score_6_up, score_5_up, score_4_up, 2 3 upper body, looking down, sitting at table, large plate on table with big cake, watermelon themed cake, 1girl, loli, detailed eyes, big head, detailed dark shadows, <lora:zy_Detailed_Backgrounds_v1:0.5>, detailed dining room background, winter, window, [pine trees, cloud], <lora:smr03_pony:0.7>, smr03, <lora:Cirno:0.7>, blue hair, ice wings, short sleeves, blue dress, short hair, hair bow, blue bow, puffy sleeves, white shirt, closed smile, <lora:Eyes_High_Definition:0.4>, eyeshd, <Negative Prompt: EasynegativeV2, PonyNegative, bad quality, bad_prompt_version2, score_6, score_5, score_4, watermark, mutation, muscular, lowres, low quality, extra limbs, text, signature, artist name, bad anatomy, poorly drawn, malformed, deformed, blurry, out of focus, noise, dust, artifacts, 3d render, (2girls, group, multiple_girls), depth of field, bokeh, (small head), bare arms, wings, teeth, nail polish, heart pupils, frilly collar, Model is AutismMix Confetti: https://civitai.com/models/288584?modelVersionId=324524 <lora:smr03_pony:0.7> is Samara03 Style LoRA: https://civitai.com/models/137595/samara03-style-pony15 <lora:Cirno:0.7> is Cirno - Touhou Project LoRA: https://civitai.com/models/514610/cirno-touhou-project-commission <lora:zy_Detailed_Backgrounds_v1:0.5> is Background Detail Enhancer LoRA: https://civitai.com/models/633524/background-detail-enhancer <lora:Eyes_High_Definition:0.4> is Eyes High Definition LoRA: https://civitai.com/models/670378/eyes-high-definition PonyNegative: https://civitai.com/models/332646/pony-pdxl-negative-embeddings EasynegativeV2: https://civitai.com/models/100191/ti-easynegativev2-textual-inversion-embedding bad_prompt_version2: https://civitai.com/models/55700/badprompt-negative-embedding Would likely be fine with just PonyNegative. The other negative embeddings are old. Regardless, I use too many LoRA & my prompts are probably too long as I'm nearly at the edge of breaking things sometimes.

>>1021665 Thanks. That one was a roadblock on making a LoRA for her.

And here's that LoRA I was making! https://civitai.com/models/799402/elie-ellie-lunar-magic-school

Neat, I was playing with a Midna LoRA. Wrangled the prompt for a while since it kept breaking. Eventually gave up & used a previous prompt I'd saved. Was easier to start from there than the broken shit I had going on. Also here's an earlier May K pic I didn't post as I was still trying to figure out the style I wanted for all the sisters when I did this here: >>>/ais/4463

Anyone know anything about upscaling video game textures? I have seen a few models on https://openmodeldb.info/?t=game-textures but I feel like that can't be the only place to find upscale models.

>>1022100 I don't remember where I got mine years ago, but I remember it had a crappy wikipedia layout. Maybe it was the site you linked & it had updated since. That site seems a lot better since it has filters & categories. I recall a manga upscaler that looked neat, but it didn't work for me. I got it working & tried to upscale an image that I can only find in a low resolution. I photoshopped the image a bit then put it through again to get halftone shading. Kinda hit & miss across the image, but certainly better than the low resolution source. I suspect it needs a cleaner image to do the crazy clean halftones I saw in demos.

>>1021959 Her head, hair, and helmet, and body art's good. Her body shape isn't impish enough.

>>1022100 Unless there's new development, AI upscaling video game textures looks shitty. Do them by hand, you'll need to seam by hand anyway.

>>1022202 It's hit & miss. >>1020469 More spooktober stuff. Doesn't have to be lewds.

Is there any hope of this ever not requiring a high-end GPU to run?

>>1022349 There's hope if you pay for cloud computing.

>>1020764 Midna mood.

>>1022161 Sounds neat. Could you do me a favor and either link it here, or try and upscale some pages from Candy Candy? The only scanlated version I could find looks like was last uploaded via dial-up. >>1022100 I use waifu2x generally but some pngs get fucked beyond repair if they have a lot of transparent areas.

>>1022349 Only in the sense that GPUs should theoretically keep progressing and eventually the current stuff will function on what in X years will be considered a low end GPU instead.

>>1022432 There's a lot of models on the page this anon linked: >>1022100 eula digimanga bw v1: https://openmodeldb.info/models/4x-eula-digimanga-bw-v1 <I used this older one because it worked on my Forge install. It attempts to clean lines & halftones, but I think if your source is really low resolution it'll struggle. eula digimanga bw v2 nc1: https://openmodeldb.info/models/4x-eula-digimanga-bw-v2-nc1 <This version 2 of digimanga is broken for me & unfortunately does nothing. eula digimanga MiA 65k: https://openmodeldb.info/models/4x-eula-digimanga-MiA-65k <Looks good & worked for me, but it is tailored for Made In Abyss manga or similar style. I only looked at ESRGAN upscalers because I know they can work with my install. There's other stuff I didn't try that's probably better. Just have to experiment more: https://openmodeldb.info/?t=manga >I use waifu2x generally but some pngs get fucked beyond repair if they have a lot of transparent areas I never tried doing transparency with SD, but I think I saw someone doing it with Comfy UI. Comfy is slower than Forge though from what I've heard. >>1022349 >tfw I had to sell my 4090 so I'm stuck using a 3080 Ti for Stable Diffusion 4090 was noticeably faster & so much VRAM. I miss the speed, but Forge is optimized a lot so it's pretty quick when it's not stuck dicking with memory management. >>1022437 True, but AI keeps progressing as well & may have higher requirements in future. Who knows. The main roadblock is private entities keeping things in-house so you don't have a major leap for locally run AI until something leaks like NAI did.

Heads up if you use the chink AI video maker! The moment you enter that site you will be automatically redirected to an english version of it, and that one requires you to sign in a (((google account))) to even make videos. There's a workaround I did where I refreshed the page & then quickly stopped it before the redirection. You will still be able to prompt your own videos & download them, but be warned that as soon as you leave the video window you will be dragged back into the english version.

>>1022466 Why not just use a VPN set to be in china?

Or just make a burner gmail?

>>1022477 >Why not just use a VPN set to be in china? But then you'll get a ding to your social credit score for making questionable loli content.

>>1020469 Requesting a regional prompting guide.

>>1022490 >>1020470 >regional prompting guide Saw one here: https://civitai.com/models/339604/how-to-generate-multiple-different-characters-mix-characters-andor-minimize-color-contamination-or-regional-prompt-adetailer-and-inpaint-or-my-workflow >>1022479 >make a burner gmail? How can you do that without a phone number? I've tried using temporary numbers to keep the account anon, but jewgle blocks using those numbers & won't create the account. Would be very useful to have an anon google account for downloading pirated games from gdrive & also since jewgle keeps trying to force a sign into youtube on my VPN & won't play videos. I've been using FreeTube, but I get the same sign-in message triggered on many VPN gateways,

Posted a new LoRA. https://civitai.com/models/822049/pratty-summon-night-swordcraft-story?modelVersionId=919243

>>1022497 I was able to make a google account without a phone number around December last year. If I had to take a guess as to why, it would be that people usually get new tech gifts for the holidays and it's better to get more people in the ecosystem even if it's missing what would be normally compulsory data.

>>1022497 I tried the examples from this guide for my last post and was hoping there was some other guide that was retard friendly floating around. Thanks anyway.

>>1022555 Ah. Guess I'll try around then. >>1022613 Farther than I got since Regional Prompter will install, but won't appear in Forge for me. Good news, everyone! I lamented in previous thread that there was no Pony LoRA for Kiki from Kiki's Delivery Service. Only 2 I found were from a Japanese McDonalds commercial redesign, not original design. I even found Pony LoRA's for other characters from Kiki's own movie. Well since then someone made one. Kiki LoRA for Pony: https://civitai.com/models/800687/kikis-delivery-service-kiki-pony Can't seem to grab tags from training data so just know that you at least need majokiki in the prompt to trigger it. Other helpful tags: dark brown hair, short hair, brown eyes, hairband, red hair bow, dark blue dress, baggy clothes, long sleeves,

>>1022750 Funny pumpkin on the left is me.

>>1022831 Someone turn it into an UOH

>>1022437 That just sounds depressing.

>>1022431 You should post your Midnas in Midna's thread too. >>799542

>>1022833 I had it as an UOH while inpainting, but it looked crappy so I changed it back. Here's something more UOH worthy. Kiki lifting her dress while I try to get Stable Diffusion to match her bloomers to the source material

>>1020622 What UI are you using? A1111? Comfy? Don't give up on Regional Promoter, it makes a big difference.

What should I tag her main garment as? Can't call it a dress because that would destroy the alt costume which is most definitely a dress. Also what kind of hat is in the outfit of pic 2? Razzy_SCS, dark-skinned female, yellow bandana, short hair, bangs, yellow ???, off shoulder, long sleeves, black tanktop, belt, buckle, bike shorts, shorts under dress, gloves, black socks, boots, Dress: ???, Yellow dress, sailor collar,

Also might as well ask for further tags for all the characters I'm prepping >Rifmonic_scs, cabbie hat, earflap hat, pink hat, twin braids, bangs, pink jacket, open jacket, fur-trimmed jacket, long sleeves, neck ribbon, black shirt, belt, skirt, white skirt, bag, sheath, weapon on back, black socks, pink shoes >Murno_SCS, blonde hair, hair ornament, forehead, halterneck, white dress, deatched sleeves, layered sleeves, long sleeves, black skirt, white garter straps, garter straps, black thighhighs, shoes thighhighs, white shoes, >Sanary_SCS, red hair, ponytail, neck ribbon, gray jacket, belt, sheath, weapon on back, black skirt, white boots >Rufeel_SCS, monster girl, ??? hat, animal ears, aqua hair, pom pom (clothing), strapless shirt, green shirt, puffy shorts, elbow gloves, fingerless gloves, tail, slippers >I'd make Lynn/Rinri too but I don't have remotely enough images >>1022903 Have you tried this LoRA? https://civitai.com/models/576402/bloomerssdxlpony?modelVersionId=642664 If it's not what you want, someone on CivitAI is taking free clothing requests and doing them fairly quick (I suspect this user is trying to get to #1 on the clothing leaderboard). I wouldn't mention Kiki, but "short bloomers"/pumpkin pants/パンプキンパンツ with appropriate example images from an image search might get you something. https://civitai.com/articles/7712/requestclothing-lora-requests

>>1022431 What's wrong with her legs, why are her legs so lumpy and fat? That Midna needs cellulite treatment.

>>1022956 In before someone posts Dagoth Ur's explanation.

>>1022976 If you're asking for it, I don't have it.

>>1022910 I'm using Forge. Regional Prompter installs & enables, but doesn't appear in the UI. I know the Regional Prompter files existed in the extensions folder as well, because I manually removed them when it didn't work, Multiple characters is still possible with a stupid amount of hours put into editing & inpainting. >>1020764 >>1020470 Okay.

>>1023135 I've been finally been blessed by the gods.

>>1022910 >>1023135 After some research I've found that Regional Prompter simply won't work with Forge. Even tried editing the python script with advice I found, but it always has errors & won't work on Forge at all. However, there's an alternative called Forge Couple: https://github.com/Haoming02/sd-forge-couple I installed that. It shows up in the interface & doesn't throw errors so far. I think it can only do two regions, but it's the same concept of separate prompts in the same image for different characters. I dunno if I can figure it out, but I can try it.

>>1023334 I'd say it's worth installing A1111 for it, I don't think the Forge improvements are that big of a deal, but being able to use regional prompter is. Even if you're only using two people, more regions helps more finely tune a scene. I don't think you actually need to move all your models/loras over, just set a symlink.

>>1022913 Training started. Even first epoch is pretty good. Third is even better.

Can I get any suggestions on LLMs to do kinkier stuff? A lot of them flounder around and don't know what to do for a lot of things.

>>1023135 Why is lesbianism so hot?

>>1023380 And published https://civitai.com/models/825000?modelVersionId=922566 >>1023431 Because yuri is the purest form of love.

>>1023369 I tried Forge Couple extension. Helps get a better start from TXT2IMG as I don't have to edit & inpaint the second character from something else. I started with both characters, yet still sunk hours into editing & inpainting regardless. I don't want to use A111 since Forge gens quicker & since I'm generating tons of images for nearly endless autistic changes any extra time spent waiting adds up. I can see how more regions would be useful to cover more than one area of where a character is in the composition.

It's spooky season. >>1020622 >>1023528 Great work on these Hex maniacs, they look really cool.

>>1023001 I wanna hang out with Dagoth as a friend

>>1020469 Postal Dude celebrating Halloween

>>1020469 Lots of smug Erin stouts please.

>>1024055 Who's Erin anyways?

>>1024179 >Being this new

>>1024013 Those are some cool spooks. One degenerate thought led to another until I made this. Couldn't find LoRA for Chu Chus, but found Dragon Quest slime. Stayed up too late working on it. Head hurts.

>>1024256 Every day we stray further from God's light.

>>1024318 Where do you think you are?

>>1024383 On /v/ - Fitness and Bible Study, of course.

>>1020468 >Starring Tom Cruise and Chris Refield >Alec Baldwin as Barry Burton >And Ben Stiller as Albert Wesker

Have an egg.

Any tag suggestions for the clothing? I'm sure there's more than just >basketball jersey, basketball uniform, sportswear, sleeveless, white shirt, short sleeves, short sleeves under sleeveless, number print, shorts, pink shorts but I know nothing about sports clothes.

>>1024590 >but I know nothing about sports clothes. You could use a sportswear catalogue or store to use their own terminology

>>1024614 Doesn't work on non-natural language models. Need established booru tags to be effective.

>>1024625 Can you save all booru tags then compare to terminology in a sportswear catalogue or glossary?

Since I may not be able to post for a few days, I've finished three more LoRA I've been working on https://civitai.com/models/833150/rufeel-summon-night-swordcraft-story-3 https://civitai.com/models/833340/mana-umihara-gotcha-force?modelVersionId=932305 https://civitai.com/models/833973/rin-nishikiori-orochi-gotcha-force Use them well. Use them for good something funny. >>1024632 Completely over complicating it. >>1024590 Sound up working fine, despite the lack of training data of her in that outfit. Her number isn't consistent, but that's to be expected.

>>1024766 GEE BILLI, TWO BASKETBALLS?

>>1024827 She learned the forbidden double dribbling technique from Barkley.

>>1024179 A white version of Korra. Some leftist tranny from the Escapist used to make Dobson tier strawman comics using this character but then Eltonel culturally appropriated her.

>>1024055 some minute generations. Need to figure out proper clothing.

>>1024955 Pretty hot. Now do the self destructed outfit version.

>>1024869 I WANNA FUG ERIN. That is all.

>>1024827 Just get AI to give her 4 hands

I want to make a Lora, but it sounds like more trouble than it's worth. Does every training image need a .txt file describing it? >>1024959 Yes mind master.

>>1024979 Yuri is master

>>1024979 Yes, but there's software to automate making the text files. It's really just a matter of tagging everything (autotagger helps for poses, but for a character you need consistent tagging). For characters with only one or two outfits its just a matter of copy-pasting in the applicable tags from a list you make ahead of time. The biggest time consumption for characters is data gathering (can be quick if pixiv and your favored booru site have enough properly catalog, or slow if you're doing things like getting game screenshots yourself) and data cleaning (can be uneeded, easy because you're just cropping ground shots to a single character, or annoying as you're trying to remove text and cut out characters from complex backgrounds). Handtagging for a style is the really annoying one, since you want far more pics (while characters get diminishing returns past ~30 pics and would benefit more from swapping out low quality pics than adding more, styles want as many pics as they can get with maybe 500+ the point of diminishing returns) and, while normally the one you can get away with just autotagger, weirder styles both confound them completely and many people want style LoRAs that can produce characters and/or items as well as the style.

>>1024979 Very good! Is it possible to get an angle showing her ass in that outfit?

I'm loving flux

>>1025142 Lewd when? System reqs compared to pony? How well does it work?

>>1020469 If anyone can pull off the regional prompting or image 2 image stuff for it, I'd like to see a shocked Rifmonica simultaneously getting a kiss on the cheek from both Murno and Rufeel and being part of a "girl sandwich" (as tag calls it). LoRAs for characters https://civitai.com/models/829694/rifmonica-rif-summon-night-swordcraft-story-3 https://civitai.com/models/830658/murno-summon-night-swordcraft-story-3 https://civitai.com/models/833150/rufeel-summon-night-swordcraft-story-3

Different style with fluffytart.

>>1025170 I love you and i love AI. What a time to be alive.

>>1025170 I fucking love technology.

>>1025170 While not video games related I'd love to see similar angels with Chel from El Dorado or Midna.

>>1025179 Midna is videogames. You could dress Chel up in vidya outfits.

>>1025208 >>1025209 hah neat but I wouldn't mind variety in the poses. A few backshots a few frontal of her smiling smugly as usual her thick smug lips and giant hips cause a conundrum in any man.

Back 2B.

>>1025172 >>1025174 かがくのちからってすげ！

>>1024013 Wanted to make a spooky pic in a neat style, but I wound up making American' McGee's Alice in the style of Angel's Egg.

>>1025222 >>1025228 >>1025232 Nice chels. Her in 2B's outfit works since she has the ass, hips & thighs to pull it off. Dunno what other girl to suggest. Maybe some more dynamic poses but to keep vidya do Midna in human form.

>>1025145 Don't really know much about system reqs but I can run FLUX on a GTX1060 (6GB) latop.

I may try my hand at some AI gen stuff but I've mostly put off on it due to laziness. I got 12 GB of vram wot can I dew with that?

>>1025142 sexoooo

>>1025325 Can you generate decent nsfw? How much time usually it takes to generate something?

>>1025462 >Decent NSFW I guess so, haven't really tried that >How long For me, a single image at 8 steps. It takes around 3 - 3:30 mintues, but it takes a lot longer to load up with LoRAs.

>>1025471 In his house at R'lyeh dead Cthulhu waits masturbating.

Any tag suggestions for these two lesbians? Wanted to try a two characters in one LoRA and am thus avoiding overlapping tags when possible. >Virginia: Blue eyes, Virgina_WA, brown hair, hair intakes, asymmetrical hair, braid, single braid, bangs, red headband, hairband, bowtie, red bowtie, white blouse, blouse, purple coat, coat, juliet sleeves, long sleeves, sleeve garter, wide sleeves, gloves, belt, longskirt, purple skirt, frilled skirt, holster, white holster, pantyhose, black pantyhose, fold-over boots, fringe trim >Maya: Blue eyes, Maya_WA, blonde hair, long hair, hair bow, blue hair bow, ascot, red ascot, orange dress, dress, long sleeves, shoulder holster, cross-laced clothes, brown gloves, long gloves, pantyhose, white pantyhose, cross-laced boots,

>>1025504 A third lesbian.

>>1025504 >Any tag suggestions for these two lesbians? yes make the tentacle monster >>1025471 rape all their holes at once

>>1025537 Why stop there? What's the maximum number of lesbians the LoRA can prompt into existence?

>>1025583 >Symphony of the Night Excellent taste.

>>1025583 >(chew-chew-chewchew-chew-chew the carpet) >(chew-chew-chewchew-chew-chew the carpet) >na na na na na na na na na na cuntamari dykeacy...

>>1025669 katamari damacy is for gamers with the biggest balls

>>1025672 I see what you did with those balls. No homo.

>>1020469 Captain Falcon with a Honda Civic

>>1025791 What real car looks closest to the Blue Falcon?

>>1025798 your mom.

>>1024980 Unrelated to the topic but I cannot believe that Brain Freeze still runs into copyright issues over the fucking floating brain clip from a movie from the FIFTIES. Copyright is beyond fucked and AI is the great equalizer, since no one really has a case against it (Nutendo DMCAing people who don't have the cash to fight back does not count).

>>1024869 Felt cute, erin time. All lewd, all smug. High quality (except the hands, and some background objects...)

>>1025672 >balls touching Gaaaaaaay

prompt and prompd should be used as rhyming with dreamt and dreamed, and count as the same thing as drawing from reference. If you "made" AI art you just reposted a reference piece as your own.

>>1025917 reference my dick faggot

>>1025936 >Erin will never reference your dick

>>1026031 >no full body

>8chan/v/ is sfw Where do I post my AI made hentai?

>>1026075 Just spoil it

>>1026075 You can post porn here. The only rule is you spoil it. You can spoil individual images even.

>>1026075 If you want to post porn, you have to buy a pass.

>>1026075 Are you from 4/v/? There aren't really SFW or NSFW boards here. The blue background is just an aesthetic thing and doesn't mean anything. Post lewds if you want, the only rule is to spoil it, and not to porn dump. Though threads like this are treated with more leniency in that regard.

>>1026086 >tfw can't ever fug a female baron

>>1025897 moar erin also a stray musashi, wonder how she got there (very lewd!!)

>>1026110 Nice.

I've been fucking around with AI music. This one has the second verse fucked up but I still like it.

I'm still figuring this shit out, but I feel like these look not too bad.

>>1026130 Three is pretty cute.

>>1026134 Cute and funny!

Posting the lewds to here >>>/h/5602

>>1026136 >>1026173 Okay but where are the loli nipples?

>>1026175 She's cute and funny, not... nice and pleasant?

>>1026175 Here.

(ó﹏ò｡)

Reimu and Rally had yuri babies or something

>>1026131 A few more of Hex dressed up as 2B

I want to sniff and smell those butts >>1026258 >>1026257 >>1026131 >>1026130 >>1025325 >>1025142 >>1023528

hey nigga's, my 'puter a toaster, could i request to see if that image gening thing is capable?, so, you remember that reverse bunny suit thing that sprouted recent-ish?(less than a decade ago), so here is my request: reverse tan, any girl you want, the reverse of any swimsuit/clothing you want

>>1026338 >>1026339 >>1026340 Nigger, what the fuck are you doing?

>>1026341 What happened?

>>1026341 Anon even retards have dicks... and so I shall grant his request.

>>1026341 trying to write well what i mean without taking many post from the thread limit, hence the deletion >>1026363 than you but i mean more like pic related, left=regular tanning, right="reverse tanning", and yes im fully aware that my doodle looks like a tanned... somewhat rotund(i don't draw much if a tall) girl and a cave-whaman or something

>>1026476 I see

>>1025818 The copyright kikes strikes once more

>>1026491 wow, the models are that receptive to specificity, huh, neat and thank you very much for taking your time on my dumbery, have a good day

Text prompts will not generate correctly with Texta, but it's not like comic sans has failed me before.

>>1026515 Pixie is loads better than this slut.

>>1026517 Disagree

>>1026491 >reverse tan Interesting.

>>1026532 hey bub, i think you got early onset dementia. Never said a fucking thing about flatties.

>>1026517 >>1026532 shut the fuck up it keeps fucking up hair colors, giving one big boobs, not giving both wings, etc. Honestly, the hands are the least of my concerns... I really don't want to spend 9999 years on inpainting this shit.

Can't believe these have not been posted here.

>>1026547 Forget about it. This is just for fun.

>>1026547 >I really don't want to spend 9999 years on inpainting this shit. You could learn to draw instead.

>>1026571 I just wanted a excuse to post a bunch of cute girls of a certain kind. I meant no bully. Also those are big lamias >>1026572 >9999 years of drawing At that point personal 2bs will be real.

I went down a rabbit hole of these film advertisement AI videos: someone on YouTube made a how-to video and there are so many of them (when you start to look for them). I don't really like AI. The barrier to entry is low, so there is a lot of shit. I sometimes question the amount of labor involved, so that when people call themselves "AI artists" I scoff (though, the troubles of people like >>1026547 and the effort of Boris Vallejo loli poster make me recognize that there can be much human labor, but it is a double thought). And AI in software is just a joke. I code because I enjoy coding. I do not enjoy peer reviewing other people's code. Why would I turn programming into nothing but peer reviewing other people's code? But, I do find myself looking at a lot of AI, and I think I know why. Postmodernism hates beauty. We indoctrinate most artists to idealize making a statue out of their own shit of themselves sucking their own cock. That's "art" to the postmodernist/feminist/marxist/college-educated/democrat world. But, we train AI to reproduce beauty, not marxist beauty, but kitsch beauty. Vulgar beauty. Beauty that hits you on a biological level. Real aesthetic. And that's where I think AI is going to stick around: AI continues to reproduce the beauty that "intellectual" world has rejected.

>>1026565 >first video Even in algorithmic content, niggers still look like they're thinking, "Crazy ass white people..."

>>1026622 I want to watch that movie.

>>1026622 > Boris Vallejo loli poster His handle on boorus is Uohtism.

>>1026622 You gotta think AI as good for three things, and only those things: As an automation tool that speeds up certain parts of the creative, brainstorming, editing or finalizing process of programming, art, music composition, research etc. In this sense stuff like inpainting or rvc-type text to speech can improve what you already do on your own, because whatever imperfections may be in the AI generated product you can at least recognize and edit them as you please. Some anon at the beginning of the Dall-e craze claimed he was swimming in commission work money because he could make the basic lineart he'd always do and use a neural network to add colors and shadows in a manner that was 90% satisfactory; As a lewd generator, especially when you're in need of very specific kinds of fetishes or poses that have very little fanart, while most works have something or other that doesn't match the original characters, the fact that the amount of animated and real pornography outnumbers so heavily the rest of the training sets for any tool means that results will be at worst passable and at best unrecognizable from the original; As a shitposting tool. I think I had more fun watching people force the AI to hallucinate or make absurd scenarios real than when they were actually trying to make good content. It taps into the opposite of uncanny valley type shit, you know it's bad or purposefully done in poor taste, but it hits that sweet spot where it can become recognizable if not iconic. The balenciaga memes, the fat guys commercials and all Presidential voices may be crude humor, but they work exactly because of how fast they can be churned out and how the results range from extremely accurate to extremely inaccurate with no in-between. "AI Artists" and "prompt engineers", conversely, fail at using the tools in a manner that is actually interesting. The Toys'R'Us commercial feels fake and on a string budget in a way crap like vid related doesn't, because there's no genuine attempt at making something that resonates with people, regardless of tone.

>>1026331 thank you based sniffer

New LoRA https://civitai.com/models/842107/virginia-maxwell-and-maya-schrodinger-wild-arms-3 I think I should have used apron and layered skirt on these two.

>>1025293 I like that background. Reminds me a bit of Silent Hill or maybe Bloodborne. At first glance it looked like Alice was made in the style of Kazuma Kaneko, since his characters tend to look a little pale at times. >>1026913 It's also nice that you can basically see what a character would look like if it was drawn by some specific artist. Theoretically at least. I don't think asking some artists like Kaneko or Yoshitaka Amano to draw a character in their style would be met with anything other than "No" or "Pay me loads of money", so it's nice that you can easily sate your curiosity. And you can make something in the style of dead artists that you like, such as Frank Frazetta for example.

>>1027277 Norman Rockwell is always a funny one to try.

Have you guys used fastflux.ai? It apparently runs Schnell but most of the stuff you can get for less than 10 seconds is actually pretty impressive.

Should I tag the lesbo in pic 1 as having "purple hair" or "black hair"? It's a different shade from the isekaied nihonjin (pic 2)

>>1026614 Me too.

Published another LoRA. Ask if you have any questions (at least for Pony) and I'll answer them if I can. I've read a lot on the subject and am over 25 deep in so I know a decent amount. https://civitai.com/models/855995/toris-summon-night-2-2?modelVersionId=957734 Also: Any tag suggestions for the girl in pic 4? I'm kind stumpped beyond "brown hair, long hair, dress, long sleeves, shoes" (Recommendations on how to easily get rid of those little speckles around her in GIMP also appreciated: I cut her out of a book scan I found, but the way the scan was makes it prone to these and I can't get rid of them with the fuzzy select tool, at least not without setting it to something I don't know how to)

>>1028156 any questions about making LoRAs

I'm too lazy to train a LoRA so I used existing things & inpainting to try to make Vita-tan.

>>1028183 Training a LoRA isn't that hard. Most of the difficulty is in these three steps >find 20-30 pics of character >do some basic cleaning cropping out other characters and getting rid of text >tag the pics like on a booru site Step 2 isn't even always needed if your training data doesn't need it.

>>1028183 Took long enough. She's pretty cute, as expected. Face is a bit on the round side though.

Started playing around with a single prompt, but later got an idea & used Forge Couple to do it with multiple character prompts. Tons of inpainting & edits as well. My idea: Tetra bathing on some island when she noticed Link watching, now she's angrily going to kick him hard in the face

>>1028545 Excellente!

>>1028736 Wild reference