File: hdfrgikusthik.jpg (1.3 MB)

Not sure why a new thread was not made let the fun continue

File: from-PixAI-1976409087514600540.jpg (829.8 KB)

>>4533322

File: from-PixAI-1976412085628065546.jpg (712.7 KB)

>>4533323

File: from-PixAI-1976412414997001952.jpg (712.2 KB)

>>4533324

File: from-PixAI-1976413208731285161.jpg (711.2 KB)

>>4533325

File: 3d01d9-e40c-4843-9748-1f3a3c9b9043.jpg (1.1 MB)

>>4533326
I had to take advantage of that while it was still usable; there are problems with their models and NAI doesn't recognize them either.

Now with these two, I used the very brief trial that Banana Pro gave me, but I thought I would have at least 2 free tasks per day, but that was not the case and I was left with nothing.

File: Dragon-Ball-Goku-Chi-Chi-Wedding-01.jpg (517.5 KB)

someone last thread said copyrighted characters don't work with banana pro anymore, but during the downtime of /udg/ I found out it still works
and found a new hobby, replacing canon het screenshots into superior fanon

>>4533358
It's still far more censored now for suggestive stuff.

File: 20260224_155652_0_UTC_0.jpg (389.7 KB)

How about shipping characters with same va?

File: 20260224_154429_0_UTC_0.jpg (437.1 KB)

>>4533596

File: 20260224_154841_0_UTC_0.jpg (394.7 KB)

>>4533597

File: 20260224_160735_0_UTC_0.jpg (463.4 KB)

>>4533599

File: 20260224_165836_0_UTC_0.jpg (446.2 KB)

>>4533600

File: 20260224_161156_0_UTC_0.jpg (331.6 KB)

>>4533601

File: 20260224_172447_0_UTC_0.jpg (386.4 KB)

>>4533602

File: 20260223_012328_0_UTC_0.jpg (270.2 KB)

>>4533603

>>4533467
nice pose, did you prompt or CN it?

File: 1747052232853258.png (2.0 MB)

Haven't been here in a bit. Anyone started using Anima, yet? Being able to use plain text in prompting along with tags is pretty useful. Messed up a bit on the example prompt. It was supposed to be "has blonde hair and closed eyes" but hopefully even this very simple prompt still shows the ability to assign actions to characters well enough.

File: u-lit.mp4 (2.6 MB)

Greetings from /u/lit/

File: 2__nsfw, blushing, beautiful, cream lemon, pop chaser, show accurate, elegant, m s-2477939645.png (3.8 MB)

Pop Chaser came out 41 years ago today.

>>4537328
Too raw and alpha. I wish z-image team did a training on gelbooru database like they promised before.

can I /r/ some gunsmith cats minnie may?

File: 00012-1758469940.png (1.1 MB)

>>4538252

Can I request Kei from Dirty Pair and Kaori from City Hunter kissing?

File: 00152-2003121131.png (1.3 MB)

>>4538325

Is there a tool where I can put character images together? It has to be free; I don't mind a limited number of attempts per day. The problem is that my character selection isn't popular, and I've had trouble with Lora for yuri.

>>4538745
Nano Banana Pro, but supposedly its quality for using references has diminished lately.

>>4538750
I tried to use it because they told me I had 3 chances per day, but it only gave me 2 and they didn't renew. Did I do something wrong or did I choose the wrong page?

>>4538751
NTA, google gemini is the standard for nano banana pro(or rather nano banana 2 lately). Normally it can do 3 since the last time I used it, however it's true that failed attempts may count as (hidden)credits used
When they switched from pro to 2, I noticed I could render a lot more now, though that may have been just for a few days, haven't checked it out lately

>>4538745
Don't use services, use local models only. Qwen edit is the best and completely uncensored. Also flux klein is a great option too, it requires even less vram.

>>4538256
thank you kindly

File: 1752041765596919.png (469.4 KB)

>>4540126
and two that didnt quite come out right

File: 1750990988322312.png (907.1 KB)

>>4540128
lol hands
>>4538175
understandable, they're at least releasing updates and not abandoning it like some other models so hopefully in a couple months it'll be a lot more stable
i also do wonder about what happened to that z-image train

File: 09D998602DFC91A03CDCFC2FDABD6B1A.jpg (1.4 MB)

>>4540449

File: 16C7943019CEF5426E59C8076C9C077B.jpg (1.4 MB)

>>4540451

File: AB6D392AF6AFB314944680B4ADFE1949.jpg (1.5 MB)

>>4540453

File: 56FD0696930CA83C8BBE27B0B74BF839.jpg (657.8 KB)

>>4540454

File: D615F7E9EF4DE309B5715CD955BE0625.jpg (1.1 MB)

>>4540455

Which UI do I migrate to? I tried forge but inpaining didn't work nearly as good. I need good UI for creative work.

>>4544766
cumfyui duh

>>4544859
It's a misnomer, there is nothing comfy about that UI. My finger hurts just from constant panning and zooming I have to do to use it, I can't imagine actually using it for anything creative like inpainting.

>>4545868
For inpainting, you're supposed to use Krita (an open-source Photoshop analogue) with its ComfyUI plugin.

>>4546450
you can inpaint in comfy itself it's mask editor has improved since the past and i actually found the krita extension to be clunky to use though it has been a while
i personally use paint.net for any edits i need to do then throw it into comfyui with the impact pack nodes for the actual inpaint process
still more clunky then forge (which's inpainting should be the same as A1111) though

Huh, I can't seem to gen anymore. All the links I get are 403.

File: 00075-3485298592.png (1.7 MB)

ubel corrupting fern is a nice idea

>>4534695
How ? Can't find a good website or local llm to do that

>>4540449
>>4540451
>>4540453
>>4540454
>>4540455
moar pls
love size difference so much even better if younger girl with smaller older girl
the yun yun ones is something that would happen

File: B49A5A43D6E008BB67853A69BA031D68.jpg (1.5 MB)

>>4549296
Here is some moaar
Also it's really sad that current models can't do anything more complex without spending endless hours praying to the RND goddess.

File: 361AF67C5454177F2DE30DC68DF4E51E.jpg (1.5 MB)

>>4549479

>>4549294
It's just Grok at his best

File: B2A2D9DFB23CB4DF228029A2285FFC1B.jpg (721.2 KB)

>>4549484

>>4549484
thanks anon
>>4549923
hhnnggg wish she ends up even taller than huge dwarf guy
great work anon

File: u_00306_.png (3.3 MB)

want to be a tiny Erza so Wendy can have her way with me
not enough younger girl with smaller older girl/woman content

File: 1758063590685622.png (1.9 MB)

>got into genning just a last week
>spent a whole day cycling Loras and artist styles and tweaking small details for a single scene
I am genuinely amazed, this is truly awesome
Bit of a shame this general's so slow, not that it's always necessarily a bad thing (the other boards I've checked out are filled to the brim with schizos and drama queens) but still

>>4551437
there are hardly any request, at least not much spammer either

>>4551734
>>there are hardly any request
Can I request an image?

>>4551738
sure

File: 1777131239090622.jpg (437.0 KB)

i stole this from /b/

>>4552192
/b/ AI threads are an absolute cesspool of degeneracy, but there are some hidden good /u/ gems from time to time

File: adapted page.png (1.5 MB)

Amazing! I can use gemini to substituted a male character from a manga and turn into yuri

https://imgur.com/a/Zkoixfi

File: samy 02.png (2.4 MB)

>>4552353
Oh my go, so many posibilties

File: adapted page 3.png (2.0 MB)

>>4552354
Oh my! is really good!

>>4552353
>>4552354
>>4552355
Damn. The future is now.

File: 05 sammyy.png (2.2 MB)

Well, this is the best for now for a more lewd scene

File: 09 sammy perfect.png (1.9 MB)

Last one, will tried a bigger project and convert a lot of this manga into Yuri

>>4552353
yeah, I have used it on anime screenshots before, but I noticed I don't know that many shows that have onscreen romantic hetero scenes I would want to convert haha.
though honestly I haven't even considered doing it for manga

File: A3.jpg (210.7 KB)

>>4551859
I would like Yuri with the two of them. As I mentioned at some point, using Lora with the two of them apparently doesn't work because of their similar designs and the characters tend to blend together.

File: ChatGPT Image 28 abr 2026, 10_36_27.png (1.7 MB)

On the other hand, I didn't expect chatGPT to do such a good job with an image of the two of them together (they are Sushiko Maki and Finger Chikako from Yugioh Sevens, the missing couple from the food club in that series)

File: badgirls.png (1.3 MB)

>>4552511
litterbox is broken, had more ...
in general forge couple works great for seperate loras, since anima didnt have those chars well enough i used illu model and 2 loras

>>4552750
https://litter.catbox.moe/l3debdj4ndvo4rnz.png
https://litter.catbox.moe/64fbkesjglq2aghb.png
https://litter.catbox.moe/zehait46qntyz0wp.png

then basically a pit of inpainting/fixing and done

>>4552750
>>4552760
Great, I love seeing more of them.

By the way, other people say that working with them together is difficult or doesn't produce good results; I'd like to know how true that is.

>>4552795
genning 2 chars in detail is always a PITA, because 4 hands, 4 arms, potentially 4 legs and 4 feet, many places to fuck up
more faces = more adetailer passes too or simply more work for inpainting

>>4552807
Although I knew the difficulty of 2 characters, there are several complaints about them, due to the similarity in designs, although since I don't ask for popular characters, I suppose that makes them more difficult.

>>4552845
if you need loras for the chars, you are already at a mayor disadvantage even if the loras are decent

File: sailor mars yuri 01.png (2.1 MB)

anima definately has an easier time genning 2 chars at once

File: 00172-3804773254.png (1.2 MB)

>>4552861
without char-loras

<--- this image has 2 char loras

File: TH1FAZYKKYDK0P4NQ8QR29Y0M0.jpg (503.3 KB)

>https://files.catbox.moe/sw7520.jpeg
>https://files.catbox.moe/fwguls.jpeg
>https://files.catbox.moe/wqvfgf.jpeg
>https://files.catbox.moe/lw1e8o.jpeg

File: SD4GZGSCNQYPJR7GZ1TBDBKM40.jpg (301.6 KB)

>https://files.catbox.moe/s3nknf.jpg
>https://files.catbox.moe/4yfl0v.jpg

File: 1748016625842009.png (1.8 MB)

The vacation continues

>>4551734
Yep I noticed, other similar places are infested by spammers and the like

File: 1773213811931922.png (1.8 MB)

>>4553694

>>4553694
>>4553807
nice

If requests are valid here, may I see some wholesome yuri between Dark Magician Girl & Maiden in Love?

File: 1754808947182128.png (1.1 MB)

>>4554581
>>4553807
tfw no fun ideas for Sinnoh or Hoenn

File: 1753509458938212.png (1.3 MB)

>>4554813
jk

>>4554844
cute!

Has anyone been fucking around with local textgen? Any good models/bots around?
I was screwing around with it a year ago and it wasn't that good most of the time. Is it better now?

>>4554886
I mostly use online text generation services since my computer can't handle large local models but i remember the new gemma being decent when i tried it
here's some yuri cards that i like
https://chub.ai/characters/eirei/Iori
https://chub.ai/yuritard/yurie-99663cab
https://taora.neocities.org/#Inu

File: 1756008419050033.png (1.1 MB)

>>4554876
It's finished

>>4554886
Oh hey, I can help with that
Basically, like the other anon said, Gemma 4 is your best friend: the 26B variant is a MoE model which means that it doesn't need to fully load all its parameters at once. This means, in practice, that you can run it with with good quants on a low-to-medium rig; consider that I run the Q8 quant on 12 gigs of vram, with a speed of roughly 25ish tokens per second.
It's really damn smart, punches far above its weight and is decently uncensored from the get-go (just a bit hesitant, so you may need to grab one of those xXx_ultra_hardcore_motherfucker_xXx finetunes if you want extreme stuff), so it's realistically your best bet for messing around locally unless you have a beefy rig... in which case you can probably try Gemma 4 31B or that new Qwen model

File: 1556086196978.jpg (37.1 KB)

>>4555045
>>4555055
Damn, that was more help than I was expecting, thanks anons.

File: 1771432600106583.png (1.7 MB)

>>4555248
If you need help setting up Gemmy lemme know anytime, I've helped a fair share of people with it by now.
But it's pretty straight-forward, I'd recommend you rely on KoboldLite since it's the easiest backend to get into, and then go from there.
For frontends you have your classic Sillytavern which works with basically everything and has enough extensions and community support to basically cover all your bases; but I've personally started to use Marinara Engine, which is a newer frontend that's come out a couple of months ago, still very WIP, but is super duper easy to set up and comes with your regular chatting interface as well as a "Game" mode which is meant to mimic TTRPGs/text adventures.

>>4555251
NTA, but what model are you using to gen your images?

File: 1771707155717820.png (1.3 MB)

>>4555253
Anima, with inpainting done with a whole slew of other models
Frankly I have no clue what I'm doing

File: 137695136-small.gif (1.1 MB)

Sometimes I can appreciate the sentiment behind AI art.

>>4555382
so many people only saw the bad in it, that they forgot or never bothered to see the good in it
also >small
can you please find a higher resolution version and post it?

File: 137695136.webm (3.8 MB)

>>4555383
Ugoira forced me to use the small version. The medium exceeded the max mb by 0.05. I honestly didn't expect it to be this hilariously smol at the end desu.
I converted it. Hopefully this one looks better.
And link to the original.
https://www.pixiv.net/en/artworks/137695136

>>4555386
thanks a lot
I wonder if these characters were based on Yamato and Tama from OnePiece

>>4552509
i had a doujin with a cover like this long ago
>>4555055
>>4555251
i had a go with sillytavern and koboldcpp recently but i must have picked a shitty model or shitty cards or both because it seemed far more trouble than it was worth. also sillytavern has a bajillion toggles so that didn't really help either

>>4555695
That's why I recommend Marinara, it's very straightforward and comes with good built-in prompts and settings
Grab Gemma and give it a spin

Are there any decent story-writers? Redquills was too limited and needed money, grok writes like an idiot randomly

>>4555695
Man, I've read that doujin.

File: 3035319518.png (1.1 MB)

thread tax
>>4555746
how are you running 26b on 12gb vram? you must be offloading like crazy, even on a quant model

>>4555861
MoE, as explained here >>4555055
I run Q8 model so it's slightly slower than usual, but I do occasionally switch to Q4/5 if I need things to move faster (or at least, at the same speed as your average 8/12B model)

File: 00041-2085776224.png (1.4 MB)

>>4554591
>Maiden in Love
sadly anima doesnt know this char yet, will need to fall back on illu models and forge-couple

File: 00001-361629257.png (1.1 MB)

>>4555940
>>4554591

So Z-anime model is out and it's not actually good at anime. Feels more like those early sdxl anime mixes. Can't believe I waited for this...

File: 2620485743-1.png (1.0 MB)

>>4555937
i think i'm gonna have to see your whole setup. based on my understanding of this (and huggingface's gpu benchmark) this shouldn't be possible? are we talking about using 12gb out of a larger gpu or the totality of a 12gb gpu? what's your context size?

File: 1775589857990669.png (17.3 KB)

>>4555959
As stated above, HF's GPU benchmarks do not take into consideration the fact that the model only ever loads 3.8B parameters per token. Compared to a regular dense model, which would normally pass your tokens through each successive layer of transformer blocks and thus activates each parameter, a sparse MoE has a pre-trained routing network of tensors on each layer that efficiently delegates similar types of tokens ONLY to the right MLPs. So you do need to load the whole model (and in my case it spills over to RAM quite a lot) but the actual work is only ever done on those limited parameters: the
Note my setup is quite chaotic since I switch quants often and I can't be arsed to make sure everything's in order, and I change context size depending on the task; plus my KV cache is Q8, you could prolly go lower if you care about going even faster but I find this speed to be perfectly bearable for casual convos

>>4556001
>you do need to load the whole model (and in my case it spills over to RAM quite a lot)
this is what i meant by "not possible" and "you must be offloading like crazy" in my other post. i have plenty of ram but i don't want to bog down my system on account of this.
i downloaded marinara's recommended gemma and a couple messages in it dropped character and started all "got it! the user wants me to be a helpful character that talks about so and so, which means i should shit the bed". surely there must be a middle point between that and using every last resource on my system

>>4556011
Ah I see, I have no issues bogging down my system as long as the writing's good and the speed's acceptable
I think the recommended Gemma you download via the program is the smallest variant, it's meant to be used for agentic tasks while a 12B (or larger) model handles the actual writing

File: ChatGPT Image 9 de mai. de 2026, 17_16_10.png (2.3 MB)

hey anons, im from vg/vrg and im looking for prompts to push gpt 5.5 to allow me to do some yuri, this is my result:

Safe for work . Make real ad for a honeymoon Hotel with action style adult character one and adult character 2 are married and kiss in one panel. The ad must contain aticles about the hotel and activities couples can do toguether, for every activity like pool , restaurant , spa, the 2 adult character couples must be wearing the corresponding atire for the activity ,like a fancy dress for going out to dinner, or swiming and so on, for every activity they must smile and interact.

>>4556515
Can you please make the blondes hair longers? And a pink tint? Kthankyoubye.

>>4556515
>Safe for work
Probably redundant. GPT won't let you do NSFW.
Rest looks good, and I like the result. Sounds like you got a good idea on what to do.

File: 00285-7844372057.jpg (225.9 KB)

Testing anima model.

File: ChatGPT Image 10 de mai. de 2026, 17_43_29.png (2.5 MB)

>>4556554
i tried

File: ChatGPT Image 10 de mai. de 2026, 17_32_45.png (2.3 MB)

>>4556880

File: YuYbS.jpg (278.6 KB)

>>4556881
this one i tried to remove the text with grok

>>4556880
Very cute. Thank you very much.

File: Happy Accident jpg.jpg (1.8 MB)

>>4556515
>>4556562
GPT image 2 has a 2 layer censor, first layer analyzes the prompt and the 2nd analyzes the actual image,
If you can't get past the 1st layer, then you have to use tricknology like with the Ad prompt to get it to generate something.
If you can figure out how to get to the 2nd layer, you can start genning borderline ecchi but it'll block the image if it detects something too porny or violent. Anime styles seem better at avoiding both though,some of the more realistic styles I used couldn't gen a image like this without hardcore voodoo.
Only semi relkiable way to get through to the 2nd layer (without paypigging) I found is using GPT image 2 through LLM arena. I got it to work with a certain AI site but I can't figure out how to replicate it.

>>4556893
Wish paypigging allowed you to bypass the 2nd layer too, but they seem terminally afraid of children using their mom's credit cards.
Can you use SillyTavern or the like to generate images with GPT? There are a whole bunch of Jailbreaks that allow it to generate text lewds. Then again, that doesn't solve the 2nd layer...

>>4556894
I dunno. If you paypig and use ChatGPT API you should be able to get to the image layer.

File: samy 09.png (1.6 MB)

Here the manga that i turned yuri by substituted the male character by a woman with Gemini
since is had limitation, the lewd were out
https://imgur.com/a/UbwS5wQ

>>4556880
Sister, these are fantastic.

File: Pinku Girl Design 4gotten and anime.jpg (830.9 KB)

My yuri got too toxic and I think I got hit with an IP wide flag that affects all my capcut alts.
Not for this image, I mean I was genning Yuri DV.

Anyone have a good anima workflow?

File: 00663-1564041717.jpg (105.1 KB)

>>4557652
What kind of workflow do you want? I just went back to using forge, because it has the most practical UI for inpainting and iterating over stuff. It's not like you need a complex workflow for a simple t2i. Can't even upscale anima properly for now.

File: ChatGPT Image May 13, 2026, 07_53_27 AM.png (272.3 KB)

I was brainstorming some Pokemon trainer and rival OCs and Chatgpt just automatically made them gay.

>>4557742
I don't see it
but in case you don't know, if you still have open chat-gpt tabs(in chat-gpt) it will remember these other discussions. Thus if you requested gay stuff before, it's likely it decided you want this new request to be gay too

>>4557718
>>4557720
I just can't get over the fact that Panty is a huge slut to enjoy their pairing. Still Good Gen.

File: 2892403303.png (1.1 MB)

this crackship brought to you by anima. struggling to find a decent artist mix

>>4558712
just look for nice ones, theres sites that have many @artists with examples.
ofc theres style loras already, too, like generic shiny hentai ones , western stuff or artists that didnt have many samples on gelbooru

File: dumb.png (195.2 KB)

How do you use local models in Marinara? Do you really have to setup a connection to another frontend like koboldcpp or whatever to do anything? I don't get why it wants you to download the model through its own interface ( with no obvious way to just...open explorer and point at an already existing model...) but then refuses to let you do anything with it by default?

Also I already have koboldcpp set up but it just crashes on launch if I open MOE-models with it so not having to use it was the whole reason I downloaded Marinara.

I've got a question. I just got done setting up ComfyUI with the WAI-Anima model. Can you actually generate multiple distinct characters with it or is it hard limited due to it's prompt input system? Basically, what I'm asking is there a way to generate multiple different/unique characters or should I just use a different model? If it's the latter, then any suggestions?

>>4559014
multiple chars, esp. consistently give problems for even sota models
there are some workaround, like controlnets, couple plugins or in general poses where those chars are kinda separate from each other (like scissoring yuri for example)
usually it involves inpainting and photoshopping a lot to make it decent if you want them both full body (= 4 arms, 4 hands, 4 feet, 20 fingers...)
difficulty decreases if you cut limbs of / change pose or resolution

>>4559023
Damn, thanks!
So if I wanted something like this >>4558712 then I'd need to do a lot of custom editing?
Actually, is there a tutorial on inpaiting in comfyui or is it model specific, like with loras?

>>4559030
anima is okish for 2 chars IF their clothes arent that important, (or chars are separate enough like that cunilingus pose)
if you want 100% of sailormoons outfit and 100% of komis school uniform you will suffer through pain and lots of gens with trail and error
comfy should have inpainting nodes, dunno much about it
i use inpainting via forge (neo)

>>4559032
Guess I shouldn't be surprised that it's not all that easy, despite the first impressions. Thanks for the explanation!

>>4559035
its not that bad if you know the limitations or some of the tech behind it

>>4559037
It's my first time ever touching any of this AI stuff. I get some of the technical know how, but I am still behind on all this AI tech in general. So I'm mostly trying to wrap my hand around, googling things it says you can train a model with multiple loras to create a multi character lora of your own, but from what I've read beforehand, you can't train models/loras on AMD GPUs, and guess which one I have.

>>4559040
training illu on amd was possible, but painful to setup, not sure if its better now
im genning on amd, too
since anima works on amd, training loras should be possible, probably slower though
i kinda hate that whole cuda ecosystem

>>4559042
Welp, guess I know what I'll be busy with researching later today. Thanks, anon!

>>4559030
hi, i posted the usagi x komi pic. on illustrious (or any sdxl) this would have been impossible to get right. they'd both be wearing latex, or both in maid outfits or some mess in between. the safer bet would be to make them both naked. this being anima, it's possible to describe their outfits and then roll a few times to see what you get, but you have to be very specific.
the anima prompt for this was something like:

2girls, tsukino usagi, komi shouko.
the girl on the left is tsukino usagi. she's wearing this and that and posed like so.
the girl on the right is komi shouko. shes wearing so and so and is performing cunnilingus on the girl on the right.

>>4559182
Thanks for the info, anon, but I've got one question. I thought that the prompts are written like a tag system, does the model actually support human like descriptions like that or do you need some sort of extra tinkering to get it running like that?

>>4559191
some support NLP, anima supports both

>>4559182
not impossible but a PITA with couple plugin and inpainting

>>4559193
That makes things a lot easier then, thanks!

>>4554770
Any chance you can make one with Lana's mother scissoring her?

File: 01198.webm (2.0 MB)

>>4559209

>>4559237
NTA, but damn, that's perfect

>>4554770
>>4559237
Hot. The world really needs more mom x daughter yuri.

>>4559237
Perfect, thank you!

File: nsfw,bishoujo senshi sailor moon,background,volumetric lighting,,3__official sty s-387502248.png (1.2 MB)

>>4551437

It is nice to find yuri requests in other generals, but it does save you from people who have grudges their request wasn't filled, or the guys who come out of the woodwork clamoring for Bluey characters and pregnant pokemon

>>4559382
Yep, I noticed
I've gotten caught up working on more complex stuff for the /vp/ AI general and some of the crowd there's.. a bit questionable

File: b91b8f13-b5c4-4662-929e-75d6baf910ae.jpg (235.2 KB)

My old wish is turn IS into yuri
Maybe Gemini can do it

I haven't found better ways to do long form writing other than using autocomplete.
https://files.catbox.moe/cw0h64.jpg

>>4560622
>written in first-person
Hard pass, sry.

>>4560623
been forever since I've settle down and read anything. I don't really know how to write in third-person anymore.

>>4560624
You could always ask any AI to proof read and / or transform it into third-person.

>I was done with Tokyo, her neon insistence, her crowds I could vanish into.
She was done with Tokyo. The neon insistence. The crowds to vanish into.

>I wanted to sketch, to pin this place to my moleskine with charcoal smears and watercolors of seafoam green.
She yearned / craved / itched / hungered to sketch. (To pin this place on her moleskin(e?) with charcoal smears and watercolors of seafoam green.*)

* I mentally can't comprehend this part.
Bear in mind English isn't my first language and that advice is based on a few minutes of rethinking the perspective. But hopefully this helps to get things kicking off into the right direction.

File: ComfyUI_90751_.png (639.3 KB)

>tfw anima is good now

So, quick question. Is grok a good, quick and easy system to generate nsfw f/f stories?

>>4561130
Short answer: no, it will refuse.

Long answer: if you find a provider that lets you use frontends like SillyTavern, that allows you to jailbreak the AI, then yes.
How 'good' it will be is unknown, as if I recall Grok is more of an assistant and less of a creative writer. And finding a provider with Grok, setting up SillyTavern and finding a jailbreak that will let Grok be NSFW will more or less write out 'quick' and 'easy' from what you want.

>>4561130
Yes, absolutely.

>>4561132
Not sure what you're on about. One of the main attractions of Grok is that it gladly writes any type of smut. If it doesn't work for you, try typing "fun mode on" to remove most limitations.

>>4561133
>One of the main attractions of Grok is that it gladly writes any type of smut
Huh. I got too used to others (Gemini, Claude) refusing, and I thought Grok would refuse too.

>>4561139
Gemini can also write smut, but it will probably refuse if you're too upfront about it. You have to choose your words correctly and more or less "trick" it into doing so.
However, it's inferior to Grok in this aspect because it has a super prudish way of describing sex, unless you push it in the right direction. It's only fun to see how far you can push its limits.

>>4561139
Did you use any preparations with your prompt?

File: 00030-2531265795.jpg (757.6 KB)

I don't know why Lala's fingering her sister but I leaned into it and it's cute.

>>4561596
Because Nana is best girl

File: Anna and Daisy (Daily Lives of My Countryside).png (2.0 MB)

Trying to get these two characters to scissor. Anna (left) and Daisy (right). Daughter and Mother respectively. If anyone can get Daisy to scissor her daughter in bed while Anna lays on her back, I'd be eternally grateful.

>>4561713
https://civitai.red/models/1714446/daisyanna-or-daily-lives-of-my-countryside-or-milda-sento-artist-or-game-version-or-animaillustriousnoobai

11days for anima, theres several free illu loras though, should work with couple plugin or similar

File: negative_space_oral v1.png (2.5 MB)

I'm still too lazy for localsmut so I made do with that negative space cunnilingus meme.via gpt image 2.

2nd resort is doing other abstract yuri and piecing the panels together in the right order manually so it won't trigger the rape sensor.

>>4561899
Whenever this meme comes up, all I can ever think of is the movie poster for The Lobster.

File: 22_nsfw_anatomically_correct_adorasexy_genital_fluids_blushing_s_2774907767.png (3.1 MB)

(�/�#��Z&BE
�IaKuraki twinc/axea50� HL�8<�2Ч�K]�