/co/ - Comics & Cartoons

Where cartoons and comics collide!

Index Catalog Archive Bottom Refresh
Name
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.

US Election Thread

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

Affiliated boards /ac/

AI Art General Anonymous 03/17/2023 (Fri) 16:25:51 No. 33086
Whether you like it or not, AI is here to stay. Post /co/-related AI artwork and experiments here. Here's some guides to installing Stable Diffusion (if you have a NVIDIA GPU with 2GB+ VRAM). >Installing AUTOMATIC1111, the most feature-rich and commonly-used UI: https://rentry.org/voldy >Different UI with 1-click installation: https://github.com/cmdr2/stable-diffusion-ui >Installing various UIs in Docker: https://github.com/AbdBarho/stable-diffusion-webui-docker >AMD isn't well-supported. If you're running Linux there's a way to install AUTOMATIC1111 but otherwise features are very limited: Native: https://rentry.org/sd-nativeisekaitoo Docker: https://rentry.org/sdamd Onnx: https://rentry.org/ayymd-stable-diffustion-v1_4-guide >Models, textual inversion & embeddings https://civitai.com/ https://huggingface.co/ https://rentry.org/hdgrecipes https://rentry.org/embeddings To try it out without installing anything you can use a web service, though they are lacking in features. >Stable Horde is a free network of people donating their GPU time, how long it takes depends on how many people are using it. It supports negative prompts, seperate the positive and negative prompts with "###": https://aqualxx.github.io/stable-ui/ >Dreamstudio requires making an account and gives you around 200 free images before asking you to pay: https://beta.dreamstudio.ai/ Img2img: https://huggingface.co/spaces/huggingface/diffuse-the-rest | https://dezgo.com/image2image Ippainting: https://huggingface.co/spaces/fffiloni/stable-diffusion-inpainting | https://inpainter.vercel.app/paint >The most notable non-Stable Diffusion generator is Midjourney, which tends to be nicer-looking and doesn't require as much fiddling with prompts but can have a samey style. However the only way to use it is through a Discord bot. https://www.midjourney.com/home/ >If you're okay with more setup but don't have the hardware you can use a cloud-hosted install: Paperspace: https://rentry.org/865dy Colab: https://colab.research.google.com/drive/1kw3egmSn-KgWsikYvOMjJkVDsPLjEMzl >Various other guides: NovelAi: https://rentry.org/sdg_FAQ Dreambooth: https://github.com/ShivamShrirao/diffusers/tree/main/examples/dreambooth Inpainting/Outpainting: https://rentry.org/drfar Upscaling images: https://rentry.org/sdupscale Textual inversion: https://rentry.org/textard >Resources Search images and get ideas for prompts, can search by image to see similar images: https://lexica.art/ Index of various resources: https://pharmapsychotic.com/tools.html Artist styles: https://rentry.org/artists_sd-v1-4 | https://www.urania.ai/top-sd-artists | https://rentry.org/anime_and_titties | https://sgreens.notion.site/sgreens/4ca6f4e229e24da6845b6d49e6b08ae7 | https://proximacentaurib.notion.site/e28a4f8d97724f14a784a538b8589e7d Compiled list of various models, regularly updated: https://rentry.org/sdmodels (Check here before asking "where do I find x model!") Copypasta OP: https://rentry.org/AI-Art-Copypata
>>33086 No. Fuck off.
Yes. Fuck on.
(12.55 KB 255x240 snibbenings.jpg)

Wow, it's about fucking time we have an AI art thread here. Anyone used Blenders plug-in yet? I'm using a measly 1080ti so I don't know if I should bother installing these programs standalone, but it sounds fun! Might inspire me to drawfag too
(43.42 KB 644x431 Smug Venture.jpg)

>>33087 It's not like the Drawfag threads are dead because the artists struck gold back at their echochambers.
>>33086 “Evil cannot create anything new, they can only corrupt and ruin good forces have invented or made -JRR Tolkien” -Anonymous
>>33128 I'm doubtful it will ever be perfect. There's of course AI art commonly screwing up hands and feet, but other than that it seems to have difficulty with varied poses and angles. A lot of AI art you can clearly see it filling details with things that don't make any sense like pieces of clothing that should fall apart if they actually existed, objects merging into other objects, lighting/shading being off, or random things added that give the appearance of complexity akin to greebles. A lot of people seem to make the mistake of ascribing AI ability and anthropomorphism (such as that guy who claimed Google was sentient or the various people who think the same of ChatGPT) it doesn't actually have. Ultimately the sort of AI art programs and chatbots we have now aren't much different than other algorithms in use for more than a decade. All it's doing is processing data with no internal understanding of what it's trained with or what it produces which shows if paying attention. The "good" AI art actually has a human doing the editing afterwards to fix the random bits. Humans have always been really bad at predicting technological and scientific progress. Going by predictions in both fiction and by actual engineers and scientists made decades ago or more we should have already had flying cars, sapient robots, interplanetary or interstellar travel, automation sufficient to make the majority of work unnecessary, etcetera. The AI algorithims we have now are no different.
(203.75 KB 320x601 09499-1315644395-_chel_1.png)

(454.91 KB 512x768 234315.png)

(448.93 KB 512x768 234322.png)

(472.93 KB 512x768 234323.png)

>>33086 Here's one I found. Something Unlimited is the trainer game based off of Bruce Timm's artstyle. Someone fed that artstyle through an AI to get some decent edits. https://civitai.com/models/18035/something-unlimited-style-lora https://imgur.com/a/Moieqgl More: https://f95zone.to/threads/something-unlimited-sprite-re-mix-and-fanart-thread.118041/post-10289359
>>33142 That's not Bruce Timm's artstyle. Also looks like shit.
>>33142 Looks less like Timm and more like Shadman
>>33156 >Shadman Needs eight more layers of whore makeup, piercings, and chromatic aberration.
>>33086 >Third pic Fourth one is a fucking genestealer.
>>33179 Avatar girls or Miss Heed?
>>33179 >Butch Hartman style girls If he'd just waited six more years, Randy Stair could have just used AI to generate as many school shooter Danny Phantom OCs as he wanted.
>>33190 Hey, those arn't half bad.
(38.83 KB 468x394 th-537364173.jpg)


(30.23 KB 474x445 th-1194456608.jpg)

>>33187 >If he'd just waited six more years, Randy Stair could have just used AI to generate as many school shooter Danny Phantom OCs as he wanted. "You willlllll reeee-mem-berrrr my naaaaaame!"
>>33222 He would've made a great sissy trap
>>33179 More girls in that Nickelodeon style that's a mix of Danny Phantom, Fairly Odd Parents, and some other shows I can't recall.
Do you have something in that 2003 Teen Titans style?
>>33179 >>33190 What AI are you using for those?
>>33245 Reminding you that Butch Hartman made Bunsen is a Beast if you still think he wasn't a two hit wonder. Any specific requests? >>33246 Unfortuantely no. This is the closest I could find, and even then it looks like it's just Starfire alone and not the artstyle. civitai /models/17357/starfire-teen-titans-anime-style >>33250 Stable Diffusion with a Butch Hartman and Dop LoRA at 0.5 strength each. Also using character LoRAs for Wendy, Dexter's Mom, Chel, and Frankie.
>>33251 >Any specific requests? Power Girl, Wonder Woman/Wonder Loli, Teen Titans' Raven, Starfire, Terra, Jinx, Cybersix, Elisa Maza, Disney princesses, Batgirl, and whoever else you can think of.
(268.45 KB 640x481 GeorgeLiquor1.jpg)


>>33251 If possible, I'd like to see AI generated art based on John Kricfalusi's style. I think it'll be difficult to replicate though.
(119.28 KB 1145x450 f48.jpg)

>>33251 Jucika? That Chel one is real good.
>>33271 Man, that strip is making me feel things.
>>33252 No character LoRAs on these so on-model accuracy is proportional to popularity. >>33261 Unfortunately, no. Been looking for a LoRA or even a dreambooth for a while, but his style seems unique enough that you can't get a LoRA/checkpoint/prompt mix. I think my GPU is good enough for LoRA training, but I'm still getting the point of control nets.
>>33275 They're all pretty nice, if in need of cleaning.
(126.76 KB 1362x916 0q5bg2yfz6p21.jpg)

Anything that isn't Butch Hartman? Anyone try to generate something in a less generic artstyle? Let me know when you can generate chowder-esque screenshots
>>33280 It's pretty slim pickings for western cartoon style LoRAs outside of porn artists. The only ones I've been able to find are BH, Disney/Pixar, Peanuts, Tim Burton, Tron Uprising of all things, Spider-verse, Rick and Morty, and nondescript mixes with names like, "modern American comics" and "cartoon fanart style". Surprised there isn't a modern adult animation model trained on Family Guy and its derivatives yet.
>>33282 The shading on that 2nd one is good but it's confused by the umbrella and fingers. 1st in peanuts still is nice. Wonder what Shultz would say about AI art.
>>33225 He was halfway there with the sissy aspect. Fucking faggot waifued a girl he wouldn't have been able to touch if she somehow DID come to life. Now THAT is beta.
(137.39 KB 1280x720 disneysirhiss.jpg)

>>33280 >that pic I rue and regret the day you were born.
(208.85 KB 523x472 peanutslinusdies.jpg)

>>33284 >Wonder what Shultz would say about AI art. Either "Good grief!" or "The greatest trick the Devil ever pulled was convincing the world he didn't exist."
(555.89 KB 961x609 George Floyd by pixar.jpg)

>>33086 Looks like the ai art is starting to ruffle the feathers of some Yidsney adults https://yewtu.be/watch?v=Impy4aQg9ps Better start archiving before they purge everything.
Any suggestions on how to selection images for a lora when my only source of images is comic books where most pictures of the character are group shots, obfuscated, or low distance detail shots? What should I do with speech bubbles (e.g., blank them out)?
>>33179 >any requests I know for a fact there's a Penny (Inspector Gadget) and Gwendolyn Tennyson resources. Make the two kiss, or just pose in cute pantsu if you can't manage to work an image with both.
>>37415 I'm no expert at all, but would your problem be solved by manually cutting out only the parts of the images you want? You could just cut out the character and leave out other characters and speech bubbles.
>>37480 Would if I could, but the group shots frequently have characters overlap
>>33179 JC Denton shakes hands with his mechanically augmented senior agent Inspector Gadget


Forms
Delete
Report
Quick Reply