[a / b / c / d / e / f / g / gif / h / hr / k / m / o / p / r / s / t / u / v / vg / vm / vmg / vr / vrpg / vst / w / wg] [i / ic] [r9k / s4s / vip / qa] [cm / hm / lgbt / y] [3 / aco / adv / an / bant / biz / cgl / ck / co / diy / fa / fit / gd / hc / his / int / jp / lit / mlp / mu / n / news / out / po / pol / pw / qst / sci / soc / sp / tg / toy / trv / tv / vp / vt / wsg / wsr / x / xs] [Settings] [Search] [Mobile] [Home]
Board
Settings Mobile Home
/e/ - Ecchi


Thread archived.
You cannot reply anymore.


[Advertise on 4chan]


>>2813593 hit the image limit
Please keep loli on >>>/b/, western styles on >>>/aco/, and vtubers on >>>/vt/
Non-Stable Diffusion (Bing/Dall-E/Midjourney) is OK but keep it /e/.

> Where do I start?
https://rentry.org/sdg-link

> News
https://www.sdcompendium.com

> Models and Mixes
>>>/t/1190826
https://rentry.org/sdmodels
https://rentry.org/hdgrecipes
https://huggingface.co/WarriorMama777/OrangeMixs/tree/main/Models
https://huggingface.co/andite/anything-v4.0
https://huggingface.co/AnonymousM/Based-mixes
https://huggingface.co/gsdf/Counterfeit-V3.0

> LoRAs
https://gitgud.io/gayshit/makesomefuckingporn#lora-list
https://rentry.org/hdglorarepo
https://rentry.org/trashcollects
https://rentry.org/zp7g6

> Upscaling
https://openmodeldb.info

> Recommended Extensions
multidiffusion-upscaler-for-automatic1111
a1111-sd-webui-tagcomplete
sd-dynamic-prompts
sd-webui-controlnet
https://github.com/Bing-su/adetailer
https://github.com/jexom/sd-webui-depth-lib

> Recommended models for /e/ content
AbyssOrangeMix3, Anything-V4.5, Based67, Counterfeit-V3.0

> ComfyUI resources:
https://github.com/comfyanonymous/ComfyUI
https://www.sdcompendium.com/doku.php?id=comfyui_0087
https://github.com/shiimizu/ComfyUI_smZNodes

> Resources
A1111 Wiki: https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features
Old guide: https://rentry.org/sd-mashup
Tags: https://danbooru.donmai.us/wiki_pages/tag_groups
LoRa Training guides: https://rentry.org/59xed3 | https://rentry.org/lora_train | https://rentry.org/lora-linux-troubleshooting
advanced merging: https://rentry.org/BlockMergeExplained
Model similarity calculator: https://huggingface.co/JosephusCheung/ASimilarityCalculatior
Animation: https://rentry.org/AnimAnon | https://rentry.org/AnimAnon-Deforum | https://rentry.org/AnimAnon-AnimDiff
Regional Prompting: https://stable-diffusion-art.com/regional-prompter/

> Related
>>>/aco/asdg
>>>/aco/csdg
>>>/d/ddg
>>>/g/sdg
>>>/h/hdg
>>>/trash/sdg
>>>/vg/aids
>>>/vt/vtai
>>>/wsg/aicg
>>
Request anchor
>>
FAQ:

Noob guide based on questions I see a lot (upscaling, danbooru tags, xyz plots, | and [from:to:when] syntax)
https://youtu.be/Jya6qcokqZQ

> What's with catbox?
4chan strips metadata containing prompt info, but catbox preserves it. Prompt information can be loaded from the PNG Info tab of the WebUI.
https://catbox.moe/
For temporary storage and slightly higher size limit: https://litterbox.catbox.moe/
4chanx extension: https://gist.github.com/catboxanon/ca46eb79ce55e3216aecab49d5c7a3fb
Pro tip: Look at people's uploads to see if their filename contains a catbox link. If it does, you don't have to ask for catbox, it's already there.

> How do I fix bad hands?
Try the sd-webui-depth-lib (needs sd-webui-controlnet) and this inpainting guide:
https://rentry.org/inpainting-guide-SD
Additional hands library: https://civitai.com/models/67174/900-hands-library-for-depth-library-or-controlnet
Depth lib inpainting tutorials:
https://files.catbox.moe/8r4y83.webm
https://files.catbox.moe/j46t3b.webm
There are also embeddings in the negative prompt that attempt to address this. I personally don't like the approach because it can change the style too much, but some people swear by them.
https://huggingface.co/zylux/orangechillmix/blob/main/badhandsv5-neg.pt

> I can't make large images, I'm running out of VRAM
Try to generate at a base resolution within a 768x768 box and upscale after that.
If you're on a card with 8GB or less VRAM, use --medvram, which saves VRAM but takes more time.
Keep in mind that highres fix is very VRAM hungry. Don't use it if you're running out.
The ultimate upscale and multidifussion extensions upscale using tiles, allowing you to upscale images in pieces, taking only the VRAM necessary for the tile size you choose. The tradeoffs are tiling artifacts (it's stitching photos together), and it takes more time.
https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Troubleshooting#low-vram-video-cards
>>
File: 2813593-part1.jpg (1.97 MB, 3000x2552)
1.97 MB
1.97 MB JPG
Previous thread highlights
Mar 23 - May 01: https://files.catbox.moe/6kbf5g.zip
May 01 - May 28: https://files.catbox.moe/foykah.zip
May 28 - Jun 17: https://files.catbox.moe/2ahwt8.zip
Jun 17 - Jul 22: https://files.catbox.moe/qkprij.zip
Jul 22 - Aug 17: https://files.catbox.moe/8m4chv.zip
Aug 17 - Sep 10: https://files.catbox.moe/5wj806.zip
Sep 10 - Oct 03: https://files.catbox.moe/t1y1t6.zip

Previous thread catboxes (all catbox images scraped from the archives):
12-20-22: https://files.catbox.moe/9db5fc.zip
01-03-23: https://files.catbox.moe/tquitr.zip
01-12-23: https://files.catbox.moe/y5pema.zip
01-26-23: https://files.catbox.moe/44hi5e.zip
02-13-23: https://files.catbox.moe/a1zfgl.zip
03-03-23: https://files.catbox.moe/tbxb20.zip
03-26-23: https://files.catbox.moe/3alkfb.zip
04-09-23: https://files.catbox.moe/og6ffw.zip
04-20-23: https://files.catbox.moe/j86g5k.zip
05-01-23: https://files.catbox.moe/okbfdl.zip
05-11-23: https://files.catbox.moe/dhayxj.zip
05-28-23: https://files.catbox.moe/zphj2u.zip
06-07-23: https://files.catbox.moe/t10yt8.zip
06-17-23: https://files.catbox.moe/8do6za.zip
06-25-23: https://files.catbox.moe/w02b88.zip
07-08-23: https://files.catbox.moe/u34buy.zip
07-22-23-1: https://files.catbox.moe/432nug.zip
07-22-23-2: https://files.catbox.moe/5g6vq0.zip
07-22-23-3: https://files.catbox.moe/72r8oo.zip
08-04-23: https://files.catbox.moe/mu10y5.zip
08-17-23: https://files.catbox.moe/1e64oy.zip
08-27-23: https://files.catbox.moe/17k3k1.zip
09-10-23: https://files.catbox.moe/uivxkw.zip
09-20-23: https://files.catbox.moe/znyect.zip
10-04-23: https://files.catbox.moe/e6ak7w.zip
10-14-23: https://files.catbox.moe/yzovui.zip
>>
File: 2813593-part2.jpg (1.56 MB, 3000x2768)
1.56 MB
1.56 MB JPG
>>
File: 2813593-part3.jpg (1.78 MB, 3000x3000)
1.78 MB
1.78 MB JPG
>>
File: 2813593-part4.jpg (1.56 MB, 3000x2560)
1.56 MB
1.56 MB JPG
>>
File: 2813593-part5.jpg (1.85 MB, 3000x3000)
1.85 MB
1.85 MB JPG
>>
File: 2813593-part6.jpg (1.54 MB, 3000x2548)
1.54 MB
1.54 MB JPG
>>
File: 2813593-part7.jpg (1.85 MB, 3000x3000)
1.85 MB
1.85 MB JPG
>>
File: 2813593-part8.jpg (1.9 MB, 2636x3000)
1.9 MB
1.9 MB JPG
>>
File: 2813593-part9.jpg (2 MB, 2944x3000)
2 MB
2 MB JPG
>>
Survey time. What models are you using these days (for /e/ related stuff)?
>>
>>2815836
Wow my shizuku made it into the collage. I'd make more but my fucking linux install died for the second time this week. Sometimes my automatic1111 would get stuck loading a new checkpoint. It froze the computer, I reset, then linux is gone from options at the bios boot menu. Can't get it back, so I have to reinstall the entire OS again for the second time this week. Good thing I back up my creations to a different drive after every session.
>>
Note to Nvidiafags: Driver version 546.01 makes the vram overflow optional, so if you were stuck on an old version for ai generation, you can update now.
>>
File: bikini-ClaraPlaya.jpg (1.62 MB, 3072x4608)
1.62 MB
1.62 MB JPG
>>2815824
More Kuroki Rei please.
>>
File: bikini-PlayaClara.jpg (1.56 MB, 3072x4608)
1.56 MB
1.56 MB JPG
>>
File: catbox_gnwl01.png (933 KB, 768x1152)
933 KB
933 KB PNG
>>2815834
Thank u for putting the Opal's together :D, love seeing her next to all those other amazing gens
>>
>>2815837
meinahentaiv4 and based67
>>
>>2815824
Animation I'd like to see someone take a shot at adding full detail to (and make it less western looking). Characters are Homura and Madoka. Too many loras for them to list; kind of up to whatever someone wants to go with.
>>
>>2815850
link lora then
>>
File: 338059380.png (1.86 MB, 1536x1920)
1.86 MB
1.86 MB PNG
>>
File: 436619264.png (1.55 MB, 1024x1280)
1.55 MB
1.55 MB PNG
>>
File: 3596556836.png (2.83 MB, 1920x1536)
2.83 MB
2.83 MB PNG
>>
File: 00005-1120194114.png (2.84 MB, 1280x1920)
2.84 MB
2.84 MB PNG
Do we have a theme for november?
>>
>>2815875
squirrel girls for no nut november
>>
File: 680084023.png (2.22 MB, 1152x1440)
2.22 MB
2.22 MB PNG
>>2815875
also maple leaves
>>
File: 3470581303.png (2.68 MB, 1536x1920)
2.68 MB
2.68 MB PNG
>>
File: 00058-329681756.png (1.84 MB, 1024x1536)
1.84 MB
1.84 MB PNG
>>2815837
Store Bought Gyoza for the most part.
>>
>>2815848
>reinstall the entire OS again
Alright, I reinstalled but prior to that I saved the entire stable-diffusion-webui folder to a different drive, then put it back on the linux install after. I can't exactly reproduce y old images, they're all very close, but slightly different even though the SD stuff is the same as from the old install. Am I overlooking something?

Sorry to ask for tech support, I'll be back to posting images as soon as I know I have reproducibility.
>>
>>2815883
I've heard of differences from machine to machine, but this is the first I've heard of problems reproducing on the same machine. Still, it's a new setup so don't be too worried about not being able to exactly reproduce something.
My understanding is that the way the GPU produces the seed image can vary slightly from machine to machine, but if you're on the same hardware that challenges my understanding of the problem.
>>
File: 00867.jpg (805 KB, 2560x3840)
805 KB
805 KB JPG
>>2815875
>>
how do you figure this shit out? I've wrote yoimiya a dozen different ways in the prompt and tried a dozen different models not a single one made a yoi anything, counterfeit, divineelegance, reproduction, bluepencil, nothing worked.
>>
>>2815885
It's weird. I did the load data from image and made sure it's all the same, but the left is the image I had before I had to reinstall and the right is on the newest install. The install just refers to the OS, the stable-diffusion folder is the same, I just sync the entire thing to a different drive after every session so when this happens, I can just put it back.

It must be something weird, would one of the OS packages changing affect things?
>>
File: 00011-2815602553.png (1.67 MB, 1000x1792)
1.67 MB
1.67 MB PNG
>>2815892
lookup the term Lora
it's a model you can train on a specific character that you call for in a prompt

download the lora you want and place it where you have your stable diffusion folder: >stablediffusion>models>Lora

you can then call it in prompts
looks like this <lora: name of lora:1.0>

here's the catbox for this gen:
https://files.catbox.moe/rbmbjv.png
>>
File: 00865.jpg (639 KB, 2560x3840)
639 KB
639 KB JPG
>>
File: PriestessUndressing.png (1.94 MB, 1024x1536)
1.94 MB
1.94 MB PNG
>>2815824
Requesting for more not!Priestess please.
>>
>>2815866
Don't think it exists.
>>
Was it worth it?
>>
File: 390485739048763.png (1.51 MB, 1024x1536)
1.51 MB
1.51 MB PNG
>>
File: 0394859034863.png (2.19 MB, 1664x1280)
2.19 MB
2.19 MB PNG
>>2815706
https://files.catbox.moe/lrauqt.png
https://files.catbox.moe/t2eq62.png
>>
>>2815893
Don't know if you do this, but there is an annoying bug when you switch models in the same session trash is not completely collected from memory and the results are not true to what is supposed to be loaded now. I am not a programmer and don't care if that is the right wording. It is impossible to remake images from memory mixed in such a manner, so I have to make sure to restart the UI everytime I switch models.
>>
>>2815823
Where can I get a 'Stable Diffusion' installer package?
When I searched Google it gave me 'Easy Diffusion' and I'm guessing the two programs aren't actually the same thing?
>>
>>2815953
>a 'Stable Diffusion' installer package
Does not exist. Read the OP.
>>
>>2815849
oh cool, they added it to the driver control panel and it can be set for any program.
took them long enough.
>>
>>2815937
Hmm I definitely noticed this sometimes. If I couldn’t recreate an image restarting helped. I don’t think it is the problem this time. Think I’ll just do another system reinstall and see if that helps. If not then oh well.
>>
File: catbox_dv7a64.png (1.95 MB, 1152x1728)
1.95 MB
1.95 MB PNG
>>2815823
>>2815827
>>2815814

Last thread was right on the average at 10 days.

Here's the scrape:
https://files.catbox.moe/5ye11b.zip
>>
>>2815953
You can use Easy Diffusion, that's an option, but I recommend following the guide in the OP.
>>2815958
Thank you for your service anon.
>>
File: catbox_ds1soo.png (1.72 MB, 1152x1728)
1.72 MB
1.72 MB PNG
Foxxy Thicc
>>
File: catbox_aorig6.png (1.83 MB, 1152x1728)
1.83 MB
1.83 MB PNG
hose time
>>
File: 101023-1833-Rm2.png (1.92 MB, 1024x1536)
1.92 MB
1.92 MB PNG
>>
File: 00076-3930753382.png (1.09 MB, 1024x1536)
1.09 MB
1.09 MB PNG
>>
File: test.jpg (737 KB, 2048x2048)
737 KB
737 KB JPG
>>
If I draw some colored blobs in paint and then run it through img2img + controlnet (canny?) can SD transform it into a good picture? I won't be home until sunday but I wanted to test that kind of stuff when I get back so maybe I can already draw some drafts on my phone
>>
>>2815970
kinda. I've seen that work to an extent
>>
>>2815970
yes it works. you might have to fiddle around with the settings.
>>
>>2815974
>>2815971
Thanks bros, at least I'll have something to keep me busy during these days.
>>
>>2815910
is it supposed to be the goblin slayer priestess?
>>
>>2815913
its fucking OVER then
>>
File: 00088-2295547099.jpg (504 KB, 1228x1843)
504 KB
504 KB JPG
Do you guys find it easier or harder to coom with material you've generated yourself vs real art? To me I just see it like an extension of masturbation, you know? Like instead of imagining something to fap to, I get my pc to imagine for me. Thoughts?
>>
>>2815976
You can even make paint level edits to pics on your phone and have SD go wild on it. Like get a sfw image and draw tits on it. Actually works.
>>
>>2815932
catbox?
>>
File: 00008-407074283.png (1.89 MB, 1024x1536)
1.89 MB
1.89 MB PNG
>>2815987
At first yes but it gets boring after I realize I could have my fetishes in the palm of my hands
>>
>>2815987
My fap sessions are now like 2 hours long because I keep trying to fine tune the perfect pics as well as create variants akin to Artist CG sets that you see on the panda, and for some reason I always need new content when it's AI.
>>
File: catbox_vaxnzm.png (1.56 MB, 1024x1536)
1.56 MB
1.56 MB PNG
>>
File: catbox_wcrwz0.png (1.48 MB, 1024x1536)
1.48 MB
1.48 MB PNG
>>
File: 3563941374.png (3.35 MB, 1536x1920)
3.35 MB
3.35 MB PNG
Nijika my beloved
>>
>>2815989
This opened my eyes to a lot of possibilities, thanks anon
>>
>>2816012
Cute, catbox please?
>>
>>2815824
Requesting lewds inspired in dark fairy tales (Hansel and Gretel, Red hood, Cindrerella, that sort of stuff)
>>
File: PriestessTesting_c.png (2.28 MB, 1024x1536)
2.28 MB
2.28 MB PNG
>>2815977
Preferably but its OK as long as she looks like her.
>>
File: 1697350451802074.png (2.9 MB, 1920x2244)
2.9 MB
2.9 MB PNG
Is it possible to convert this scene with Rias from Highschool Dxd Hero to the artstyle from the first 3 seasons? (Example: https://civitai.com/models/17257/dxd-all-girls-gasper-rias-sona-yasaka-venelana-akeno-asia-tsubaki-xenovia-grayfia-kunou-gasper-rossweisse-irina-kiryuu-koneko-kuroka-serafall-ophis-ravel)
>>
>>2816025
https://files.catbox.moe/sbrq29.png

>>2816061
ok i might bake some in a few
>>
>>2816065
>trained this lora on AnythingV4.5
ewww gross don't touch it
>>
>>2816074
Well it was just used as an example to be fair. There are at least other Loras which do the same job.
>>
>>2815987
>material you've generated yourself vs real art?
At the end of the day, they're both drawings. If people were drawing what i wanted to fap to, then it'd be the same but it's hard to come by LL girls with accidental thongslips.
>>
File: KurokiAI.png (2.88 MB, 1408x2048)
2.88 MB
2.88 MB PNG
>>2815850
>>2815978
The gens only need to resemble her. Pic and video ( >>2815913 ) related..
>>
File: 00005-2879212809.png (2.99 MB, 1280x1920)
2.99 MB
2.99 MB PNG
>>
>>
Tonight turned out to be a Ruby night for me. It's hard to get it to do these rally slight panty peeks.
>>
>>2815824
akane tendo from ranma½, goth, black eyes, black cropped shirt, black shorts, torn clothes, barefeet, split
>>
File: 16814928351.png (1.79 MB, 1152x1536)
1.79 MB
1.79 MB PNG
>>
File: 00144-843418190.png (781 KB, 768x960)
781 KB
781 KB PNG
>>
File: 00333-446690584.png (658 KB, 768x960)
658 KB
658 KB PNG
>>2816132
>>
File: 00447-1720256500.png (2.95 MB, 1536x2304)
2.95 MB
2.95 MB PNG
>>2816133
>>
File: alt19.png (861 KB, 2315x1762)
861 KB
861 KB PNG
>>2815824
woman with long hair wearing long sleeve top and thigh high stirrup stockings or legwarmers.
picture shows entire body
both hands visible/bare/uncovered/exposed.
area from armpits down to upper thighs uncovered/exposed
toes and heels exposed.
(sometimes called reverse bunny)
or -------------------------------------------------------------------------------
woman with long hair wearing only elbow length fingerless glove on left arm,
right hand bare/uncovered/exposed. both hands visible
picture shows entire body
>>
File: 00064-3905996287.png (704 KB, 1152x768)
704 KB
704 KB PNG
>>2816134
>>
File: 09845039874563.png (1.54 MB, 1024x1536)
1.54 MB
1.54 MB PNG
>>2816132
>>2816133
more of this
>>
File: 00069-4142921184.jpg (499 KB, 1228x1843)
499 KB
499 KB JPG
>>2815996
I've actually started pulling stuff from other e threads and seeing what img2img can do with them. Kept things fresh desu. Kinda fun too
>>
File: 00236-3978969417.jpg (899 KB, 1024x1600)
899 KB
899 KB JPG
>>
>>2815850
I only occasionally lurk these threads but when I do I always see your request. What anime is she from? I looked up the name and the results look nothing like the image you always post
>>
File: Kuroki'sGarden.png (983 KB, 704x1024)
983 KB
983 KB PNG
>>2816172
Kuroki Rei is from Vividred Operation. The pics posted are of Clara from Star Rail. They are posted to contribute something to the thread.
>>
File: catbox_dhnsbo.png (1.86 MB, 1152x1728)
1.86 MB
1.86 MB PNG
bride
>>
File: Nemona.png (3.08 MB, 1806x3072)
3.08 MB
3.08 MB PNG
Bigger resolution: https://files.catbox.moe/f6mrbo.png
>>
File: 00010-940229239.0.png (1.58 MB, 1024x1536)
1.58 MB
1.58 MB PNG
>>
File: catbox_xqbgcu.png (923 KB, 768x1152)
923 KB
923 KB PNG
>>2816190
November is Sweater Weather
>>
File: catbox_10ankw.png (2.1 MB, 1152x1728)
2.1 MB
2.1 MB PNG
>>2816191
>>
>>2815934
catbox?
>>
File: 21093-2241719018.png (2.03 MB, 1600x1280)
2.03 MB
2.03 MB PNG
>>
>>2815824
Requesting military stuff but with a fantasy twist. Like I don't know... a female soldier with a witch hat or a tactical knight or things like that
>>
File: F3arbvobMAAZLrf.jpg (800 KB, 2048x3072)
800 KB
800 KB JPG
>>2815824
Requesting someone fix her panties/skirt. They basically fuse together. The designs and colors on her panties are kind of irregular too (3 different shades of black, uneven frills).

And as one other minor fix- the strap on the left of her shirt shouldn't be white, and the fabric around it is kind of the same color as her skin. Character is Sakura Kyouko from Madoka.
>>
File: 1699018708217255-2.png (906 KB, 768x1152)
906 KB
906 KB PNG
Added boobie to some anon's gen, I don't remember which thread it was posted originally though.
>>
File: catbox_qp451w.png (1.63 MB, 1024x1536)
1.63 MB
1.63 MB PNG
>>
File: KantokuIA.png (2.4 MB, 1280x1920)
2.4 MB
2.4 MB PNG
Looks real good. Thanks for this, Kantoku Anon.
>>
File: catbox_iypgm7.png (1.81 MB, 1152x1728)
1.81 MB
1.81 MB PNG
Definitely in my top 10 gens ever.
>>
>>2815824
Re-request for more gens of Julia from Fire Emblem.
>>
File: IMG_4471.jpg (145 KB, 980x980)
145 KB
145 KB JPG
Any models for Sian?
>>
>>2816171
catbox? nice style
>>
File: tmp4yui5xm6.png (1.85 MB, 1280x1536)
1.85 MB
1.85 MB PNG
>>
File: 00004-338982549.png (3.47 MB, 1280x1920)
3.47 MB
3.47 MB PNG
Went back to my mad hatter and see if I could make her tits lactated. I manage to do it but I had to edit multiple gen together to make it work.

Also, I think I did this anon >>2815824 request.
>>
>>2816289
I mean this anon >>2816026
>>
File: 00184-709348370.png (754 KB, 768x960)
754 KB
754 KB PNG
>>2816145
Lora is a real roll of the dice.
>>
File: 00203-1149839434.png (788 KB, 768x960)
788 KB
788 KB PNG
>>2816291
>>
File: 00218-593180301.png (806 KB, 768x960)
806 KB
806 KB PNG
>>2816293
>>
File: 0666_4w.webm (3.52 MB, 640x640)
3.52 MB
3.52 MB WEBM
>>2816294
>>2816291
>>2816191
>>2816171
>>2816178

i like those nice lightings & pose
>>
File: 00264-2674681333.png (892 KB, 768x1152)
892 KB
892 KB PNG
>>
File: 00034-1251352555.png (983 KB, 896x896)
983 KB
983 KB PNG
>>
File: 00041-2282711746.png (1.09 MB, 968x968)
1.09 MB
1.09 MB PNG
>>2816302
>>
File: 00035-4082858174.png (1.03 MB, 896x896)
1.03 MB
1.03 MB PNG
>>2816303
>>
File: 00033-3283958595.jpg (119 KB, 1136x1632)
119 KB
119 KB JPG
>>
File: 70334-tmp.png (2.29 MB, 1152x1536)
2.29 MB
2.29 MB PNG
Late night sleepy maid
>>
>>2816294
catbox?
>>
File: 00000-1329541434.png (1014 KB, 768x1152)
1014 KB
1014 KB PNG
>>2816340
https://files.catbox.moe/ia1fn2.png
>>
>>2816341
where do I get the assup lora? couldn't find it in the usual places..
>>
>>2816354
>couldn't find it in the usual places
?
https://civitai.com/models/186916/ms-real-lite-ass-up-top-down-bottom-up-lora
>>
Why are so many of them fat as fuck with large drooping tits?
Why does art have to represent the world we live in.
Love the skinny/petite ones...
>>
>>2816355
Thanks. There isn't really a practical way to go from the information in the catbox to the lora on civit since the names and hash don't match.

Also: >Do you want to support me? Consider being a patron on Patreon to vote on train polls and access stuff early.

>Lite models are less trained versions of the Full models but yet usable ones. Full models will be on Patreon and after 1-2 week span I'll release Full models on our Discord server.

lmao
>>
File: 00100-954205083.jpg (190 KB, 1128x1680)
190 KB
190 KB JPG
imagine being a cringelord who has a patreon
>>
>>2816360
Imagine not being one, free money
>>
>>2816356
probably cause the people behind them don't share your opinion.
>>
>>2816367
If you need to do requests instead of what you like then it becomes a job, the total oposite to "free money".
I dont think anyone would get into your patreon just to see what YOU want to make and what you want to make alone, to get subscriber you need to come with actual plans that makes you get patrons that includes request like it or not

Its perfectly fair of course, but the "I do what I want and get free money back" is just an illusion. IF you want money you have to commit to the bussiness model or you get jack shit.
>>
>>2816374
I made AI commissions for some money and I quickly began hating it, so ur barking up the wrong tree.
Maybe some people like it though, like that guy genning elves for months on /h/. Also no, ur entirely wrong - fanbox and patreon are places you sub to see the author's content, not to request things.
>>
>>2816360
>>2816374


Ai commisionning is not going to be a long career, look at bing images, once it has a nsfw version elsewhere, it's done
but i guess prompters still have 1-2 years
>>
File: 09823745068743856934.png (2.03 MB, 1664x1280)
2.03 MB
2.03 MB PNG
>>
File: catbox_ttlh8w.png (1.63 MB, 1024x1536)
1.63 MB
1.63 MB PNG
>>2816309
catbox?
>>
>>2816389
Nobody was making enough to quit their day jobs.
It usually takes artist years to generate that kind of following and the "1girl, solo" market was immediately saturated with significantly more supply than demand.
But people are lazy and stupid.
Look at food delivery for example.
If there are people that can't be bothered to get their own food and would rather pay way too much for someone else to bring it to them, then there are going to be people that will never care to learn what tools to use or how to prompt properly.
Food delivery as a main job is fucking stupid, but if you need a little extra cash and you're not doing anything on your day off anyway, it's an easy way to make a little extra.
Most traditional pixiv and patreon artists just make what they want and people subscribe regardless.
Some will go a year without updates and still retain hundreds of paypigs.
There are also tip jar type payments, and all it takes is one little whale to make it worth the little trouble it takes to set up an account.
The clock might be ticking for the casual early earners, but I would be surprised if there aren't already certs or courses on how to train and prompt.
>>
File: 00020-906504732.0.png (1.71 MB, 1024x1536)
1.71 MB
1.71 MB PNG
>>
File: Akko Kagari.png (3.32 MB, 2048x3072)
3.32 MB
3.32 MB PNG
Bigger resolution: https://files.catbox.moe/0x7wb9.png
>>
>>2816390
What ur config?
>>
SD appears to be adding this crazy contrast/saturation filter in the final step of every image I generate these days. I have no diea why. Is there a setting for it somewhere? Putting things like "saturation" and/or "contrast" into negatives doesn't seem to do anything.
>>
>>2816426
Sounds like the vae. You might want to try a different one or a model that doesn't have a baked-in vae.
>>
>>
>>2816427
I use the same vae I've always used and it was never a problem before. Maybe I'll try tinkering with the settings a bit.
>>
>>2816430
Maybe give it a no positive prompt test. If it's still coming out whack, you have something going on with your negative prompts (something like greyscale or monochrome can change the output quite a bit) or you're suffering from the A1111 memory leak issue and should reboot the webui.
>>
>>2816432
Thanks for the tip, but I think I learned what it is now! It's an effect called "burn". There is an extension to help deal with it. I'll try it out.
>>
File: 11301151.png (1.83 MB, 2507x3541)
1.83 MB
1.83 MB PNG
>>2815824
Please img2img pic related. Background optional tho a beach may be it. Expose her skin more if you can.
>>
File: 00053-2414106783.jpg (126 KB, 1056x1504)
126 KB
126 KB JPG
>>2816482
>>
File: 00048-604599442.png (1.85 MB, 1024x1536)
1.85 MB
1.85 MB PNG
>>
>>2816484
amazing transformation
>>
>>2816487
NICE HAT
>>
File: Hood 01 Sample.png (1.98 MB, 1217x1070)
1.98 MB
1.98 MB PNG
>>2816026

Larger file: https://files.catbox.moe/93z29j.png
>>
>>2816487
This is seriously impressive
>>
File: 70083-tmp.png (3.29 MB, 1440x1760)
3.29 MB
3.29 MB PNG
>>2816391
https://files.catbox.moe/7so7sk.png
>>
File: 983475894375.png (1.6 MB, 1024x1536)
1.6 MB
1.6 MB PNG
>>
File: 3489759384.png (1.51 MB, 1024x1536)
1.51 MB
1.51 MB PNG
>>
File: 32458973489752.png (1.35 MB, 1024x1536)
1.35 MB
1.35 MB PNG
>>
>>2816484
Nice. Thank you.
>>
File: 45348795638946.png (1.65 MB, 1024x1536)
1.65 MB
1.65 MB PNG
>>2816200
https://files.catbox.moe/aggnek.png
>>
File: 00068-760263841.png (2.83 MB, 1728x2304)
2.83 MB
2.83 MB PNG
>>
File: 00002-1822971303.jpg (852 KB, 3840x2560)
852 KB
852 KB JPG
Wanted to post the png file but it's 9mb.
>>
>>2816598
just use catbox
>>
>>2815824
Requesting: symmetrical docking
Challenge: asymmetrical docking
>>
>>2816598
4chan strips metadata anyway and for high color images, the naked eye can't tell the difference between png and jpg
>>
>>2816512
>>2816510
Sorry, but I won't gonna praise your inputs any more, Everything you post is so amazing that posting every time how amazing they are is just redundant
>>
File: 00004-3103805448.jpg (772 KB, 3840x2560)
772 KB
772 KB JPG
>>2816599
>>2816605
https://files.catbox.moe/phij9k.png

The best thing I can do is use the jpeg version on 4chan and catbox for the png.
Good thing that Ultimate SD upscale give me both files at the end.
>>
File: 2175556003.png (1.96 MB, 1024x1280)
1.96 MB
1.96 MB PNG
>>2816603
>>
File: 00094-1653808900.png (1005 KB, 784x1064)
1005 KB
1005 KB PNG
>>
File: ComfyUI_06470.jpg (2.88 MB, 1536x2688)
2.88 MB
2.88 MB JPG
>>
>>2816714
snapchat filter lookin ass
>>
ANYONE please help, when trying to train a Lora I get this whenever I use fp16: runtimeerror addmm_impl_cpu_ not implemented for 'half', and when I use bf16 it gets too slow at doing steps, I use kohya ss

I'm in Ubuntu 22.04 with an AMD GPU
>>
File: 21177-1603512940.png (3.13 MB, 1280x1920)
3.13 MB
3.13 MB PNG
>>2816603
dock
>>
File: 1389899350.png (1.45 MB, 1024x1280)
1.45 MB
1.45 MB PNG
>>2816722
nice milkers
>>
File: 20988-460486156.png (2.31 MB, 1280x1600)
2.31 MB
2.31 MB PNG
>>2816723
youtoo
>>
File: 00417-524886302.png (3.47 MB, 1768x1768)
3.47 MB
3.47 MB PNG
>>
>>2816727
may i ask what drove you to make this img?

>>2816726
why is the left one so pissed?
>>
File: 00872.jpg (622 KB, 2560x3840)
622 KB
622 KB JPG
>>2816603

Very cool: >>2816727
>>
File: catbox_ffu4ig.png (1.65 MB, 1152x1728)
1.65 MB
1.65 MB PNG
>>2816209
Deploying tactical Witch.
>>
File: catbox_nd88gf.png (1.51 MB, 1440x960)
1.51 MB
1.51 MB PNG
>>2816603

Don't you hate it when you accidentally summon two?
>>
File: catbox_hcbq9s.png (1.51 MB, 1152x1536)
1.51 MB
1.51 MB PNG
Best of the day.
>>
File: catbox_negbkj.png (1.74 MB, 1152x1728)
1.74 MB
1.74 MB PNG
>>2816730
>>2816209
One more Witch
>>
File: 00011-937184445.png (3.25 MB, 1920x1280)
3.25 MB
3.25 MB PNG
>>2816603
>>
>>2816728
witnessing a crimson aurora and the transient nature of the world
also should drink less so i don't fuck up my replies

>>2816729
thanks
>>
File: 1699224430592754-2.png (1.95 MB, 1152x1728)
1.95 MB
1.95 MB PNG
>>2816734
Sir,this is an ecchi board?
>>
>>2816502
Thanks. Spent some time getting the settings right, but it's fairly consistent now. let me know if you have any requests I can try.
>>
File: dark fairytale.jpg (1.86 MB, 2048x1536)
1.86 MB
1.86 MB JPG
>>2816026
>>
File: catbox_6at9xv.png (1.7 MB, 1440x1184)
1.7 MB
1.7 MB PNG
>>
>>2816719
Sounds like kohya doesn't have a half implementation for AMD? Obviously full precision is gonna be slow, but really the best place to ask is the kohya github.

>>2816727
beautiful sky

>>2816783
we genderbendergen now
>>
>>2816727
AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA please promt her nude
>>
File: 20938459034853.png (1.44 MB, 1024x1536)
1.44 MB
1.44 MB PNG
>>
File: 00103-3966275094.png (1.5 MB, 1152x1528)
1.5 MB
1.5 MB PNG
hello all
>>
File: 00298-1915453104.png (940 KB, 768x1152)
940 KB
940 KB PNG
>>
File: 00299-1915453105.png (888 KB, 768x1152)
888 KB
888 KB PNG
>>2816833
>>
File: 00336-1915453102.png (784 KB, 768x1152)
784 KB
784 KB PNG
>>2816834
>>
File: 00091-2806224127.png (2.04 MB, 1024x1536)
2.04 MB
2.04 MB PNG
>>
File: 00018-2113412534.png (1.2 MB, 1024x1024)
1.2 MB
1.2 MB PNG
>>
File: 00108-2680875669.png (2.1 MB, 1024x1536)
2.1 MB
2.1 MB PNG
>>
File: catbox_bm32qq.png (1.26 MB, 960x1440)
1.26 MB
1.26 MB PNG
>>
>>2816728
angry, angry about boobs
>>
File: 00117-BMP.png (1.52 MB, 768x1200)
1.52 MB
1.52 MB PNG
>>
File: 1699200812129674.png (858 KB, 2019x612)
858 KB
858 KB PNG
>>2815824
Request for something similar to be done with this pic as it was done in >>2816482 and >>2816484
>>
Good fucking work, fuckers. Many of these are substantially better than what many hentai artists crap out. No wonder twitter-and-instagram quasi-artists are crying so loudly about evil villlains writing prompts.
>>
I feel like I'm having a stroke every time I read through the guides of how to set up this ai shit lol. I've used bing and NovelAI but this seems like a chore lol
>>
File: 00166-BMP.png (1.68 MB, 1248x1024)
1.68 MB
1.68 MB PNG
>>2816848
I'm not sure if I'm included in this or not but AI kind of blows my mind. For example the leaf shadows on her thigh is kind of crazy. Just imagine this shit 5 years from now.
>>
File: 00277-BMP.png (1.7 MB, 1248x1024)
1.7 MB
1.7 MB PNG
>>2816850
Also it allows artshitters like me to clean up stuff like 6 fingers which I missed with very little effort lmao
>>
File: catbox_fckkkk.png (1.32 MB, 960x1440)
1.32 MB
1.32 MB PNG
>>
>>2816727
amazing. was miyuki lora used for the clouds/plant?
>>
>>2816850
Don't get your hopes up. The low-hanging fruit has been plucked, so I wouldn't expect any major breakthroughs in the next 10-15 years. In the next couple of years, expect skepticism and doomsaying. I'd expect AI from 2028 to be pretty much on this same exact level, except that it'll take less computing power to generate due to optimization etc. Also, it's still only good for porn because of how meaningless the output is, and this will not change until we get AGI, the general intelligence, going. At that point, the tech will probably click, and all bets will be off.
It just looks like, Artstation to Pixiv, the art is so brain-dead an AI can easily approach their level of creativity. Like, take those infinite asian artists painting the same few types of girls over and over and over. Turns out that stuff was so stupidly formulaic, a robot could do it.
>>
>>2816860
retard. you were proven wrong last month with dall-e already
>>
File: 9084569078546.png (1.16 MB, 1024x1536)
1.16 MB
1.16 MB PNG
>>
File: Dehya.png (3.65 MB, 1668x2496)
3.65 MB
3.65 MB PNG
Bigger resolution: https://files.catbox.moe/yalm1x.png
>>
>>2816861
I'm talking about the future, not the past. How stupid can you get?
This is how tech works. You can't just expect regular breakthroughs because we've just had one. Look at the self-driving cars, you ignorant dipshit. A breakthrough followed by a lull of almost a decade now, with nary an end in sight. This is because the first 95% of progress solve the easy problems, while the remaining 5% are the truly hard ones that take more time to solve than everything prior combined.
Use your fucking brain for once, you coomer.
>>
>>2816867
This is honestly a fairly good assessment. Couple that with the fact that the law is trending towards partly outlawing certain practices that we've come to rely on and it makes it that much harder to make significant advancements in the imagen field.
>>
>>2816659
>>2816722
>>2816723
>>2816729
All this are great

>>2816763
Ill now roll on your gacha game

>>2816805
>we genderbendergen now
Its curious its not more recurrinth theme in folklore. Myths are filled with heroes of all pantheons crossdressing but in fairy tales it aint that common
>>
>>2816867
Im honestly not sure where can we even go further since from what I've seen dall-e is near perfect, for image gen we dont even need much of a breakthrough, just further refinements.
Though you're still retarded because we will get a breakthrough in the video/animation department soon™ once big companies get on it. Not to mention text and translation
>>
File: 10959235.jpg (108 KB, 784x446)
108 KB
108 KB JPG
>>2816876
The only people who claim to be able to predict technological breakthroughs in the near term are scammers and retards. Since you're not trying to sell me anything, I'm assuming the latter.
>>
File: Lisa.png (3.34 MB, 1536x2304)
3.34 MB
3.34 MB PNG
Bigger resolution: https://files.catbox.moe/lmfx75.png
>>
>>2816885
>only retards predict
back into the jungle with you
>>
File: 21267-493076132.png (2.32 MB, 1600x1280)
2.32 MB
2.32 MB PNG
>>
>>2816895
There are important words after the word predict too. Without them, you won't understand the meaning. That's how language works, harambe.
>>
>>2816885
by this same logic you predicting the lack of any makes you retarded.
That quote is also regarding specific predictions not a general "it'll happen". You need to have no fucking clue about AI to think it's going to stagnate now.
>>
>>2816928
Breakthroughs are hard to predict. Stagnation after a major breakthrough (because the easy stuff has been done and only the hardest stuff remains) is the default. So it's easy to predict stagnation, whereas it's almost impossible to predict when another breakthrough will actually happen.
God, you're a retarded bunch.
>>
>>2816867
>self driving cars
why not look at tanks or actual cars
or guns, machine guns
planes maybe
how about recent times and PCs?
Of course we won't have major breakthroughs in self driving cars, there's not much more to improve.

>>2816933
Easy to predict (subjective much? it's easy for me to predict AI will not stagnate) or not, trying to predict technological breakthroughs (be it happening or not) is retarded by your own admission.
I hope you're just baiting and are not genuinely this dumb.
>>
File: 00587-2589244750.png (3.73 MB, 1768x1768)
3.73 MB
3.73 MB PNG
>>2816806
alt
https://files.catbox.moe/iwitye.png
extra
https://files.catbox.moe/1iglj4.png

>>2816805
>>2816855
thank

>was miyuki lora used for the clouds/plant
nope just touko and 0.4 beksinski
color comes from img2img
now i wanna try it with miyuki
>>
>>2816937
>Of course we won't have major breakthroughs in self driving cars, there's not much more to improve.
You are ignorant enough to not know how ignorant you are. Get acquainted with the concept of levels of driving automation and go from there.
>>
File: klara.png (1.41 MB, 1024x1536)
1.41 MB
1.41 MB PNG
>>
>>2816937
I think you need to revise how parantheses work, your second point is unreadable
>>
>>2816986
that's just your poor reading comprehension
>>
>>2816867
>nary
this word doesn't make you sound smarter it's just cringe. Please just say "with no end in sight", that's what nary means, no
>>
>>2816954
Nice. Thanks!
>>
File: 00639-1301727410.png (1022 KB, 1152x768)
1022 KB
1022 KB PNG
>>2816849
Its kind of like brute forcing learning another language.
Once you get it going it's like Cypher in The Matrix talking about seeing a "blonde, brunette, redhead" instead of code.
>>
File: 1696197543191444.png (1.46 MB, 3200x3200)
1.46 MB
1.46 MB PNG
>>2815824
Requesting someone try making this more detailed/higher quality overall, but with the same general pose, body type and "outfit." It's Megumin from Konosuba playing on a guitar in her underwear.

Preferably use this lora: https://civitai.com/images/1892396

If possible, make her bra/panties black and her expression less aggressive.
>>
>>2816988
>cringe
This word doesn't make you sound smarter either, to put it mildly.
>>
>>2816988
I must politely yet firmly disagree with your assertion that my modest lexical selection betrayed vain affectation rather than erudite eloquence. The notion that an expansive vocabulary anatomizes one's intellect renders shallow insight; truly, it is the judiciously chosen word that demonstrates linguistic panache. Though your preference for brevity and directness has merit, to dismiss as "cringe" the embellishments of language risks sacrificing nuance upon the altar of simplicity. I shall endeavor to take your perspective under thoughtful advisement, yet cannot conscience stripping my modes of expression down to sterile words alone.
>>
File: 00589-BMP_cleanup.png (1.7 MB, 1024x1024)
1.7 MB
1.7 MB PNG
>>
File: 00231-BMP_cleanup(2).png (1.67 MB, 1024x1024)
1.67 MB
1.67 MB PNG
>>
>>2816999
that's funny because of the pic related but don't let the Cypher analogy dissuade you from starting AI art. there's no language learning involved. you don't need to know Python. once you get it going you're dealing with a user friendly web UI
>>
>>2817022
hi, I can try this for you but I can you clarify first? you want to keep the outfit but you want to use the Megumin LoRA. that LoRA is meant for doing the classic Megumin outfit with the hat, the dress, the cape, etc. The only element from that outfit I can see in this pic is the collar.

so, which elements do you wanna see from the Megumin LoRA?
>>
File: a.jpg (62 KB, 416x600)
62 KB
62 KB JPG
>>2815987
Definitely better. It's hard to find arts that match my fetishes.
>Like instead of imagining something to fap to, I get my pc to imagine for me.
I have aphantasia so imagination doesn't work for me.
>>
>>2817052
Really like the styling on this one. Catbox?
>>
>>2817060
https://files.catbox.moe/rnb4ny.png
I just noticed I messed up the face when I did the ear removal. Was probably drunk
>>
>>2817064
what do you do for cleanup?
>>
>>2817072
Llama cleaner and Gimp
>>
File: Zero_Suit_Samus_SSBB.jpg (61 KB, 280x464)
61 KB
61 KB JPG
Can someone just inpaint Zero Suit Samus' render as nude? Just keep her darker blue boots. I want to use it for a brawl mod and can't use SD right now.
>>
>>2817075
thank you. with gimp you mean edit out flaws or do use some filter or something?
>>
File: 00034-BMP_cleanup.png (3.74 MB, 2044x1024)
3.74 MB
3.74 MB PNG
>>2817085
Its good for easy fixes and getting the colors that I like. Everything in the top Colors tab is useful. For filters Enhance > Sharpen I use on pretty much every pic. Noise at a low opacity can make a nice grain effect for some gens. Components > Channel mixer > Red in Blue channel is good for skin tones.
>>
>>2817086
cool thank you very much
>>
File: 1_cleanup.png (1.81 MB, 1024x1552)
1.81 MB
1.81 MB PNG
>>2817075
this is pretty neat. i have no clue what im going to use this for, but im sure something will come up
>>
File: 00000-679561285.png (3.08 MB, 1024x1536)
3.08 MB
3.08 MB PNG
>>
File: 00003-324942555.png (3.24 MB, 1024x1536)
3.24 MB
3.24 MB PNG
>>
File: 00040-4160928031-edit.png (3.22 MB, 1024x1536)
3.22 MB
3.22 MB PNG
>>
File: 00041-4160928020-edit.png (3.36 MB, 1024x1536)
3.36 MB
3.36 MB PNG
>>
>>2817056
Didn't realize that one worked that way. I mainly went with that one because I liked the general style, in terms of the face and shading; is there any way at all you could apply the overall shading style (and the face) to the entire thing without giving her her default outfit?

If not, or if it's just too much work, then kind of just go with whatever would work best (as long it's not a flat or really generic style.)

Just one other thing- if at all possible, try to make her fishnet stockings into fishnet thighhighs (cut off/top of the thighhighs similar to this)
>>
>>2817088
> 1landscape, huge_mountains, (thick_bush:1.2)
>>
File deleted.
>>2816860
>I wouldn't expect any major breakthroughs in the next 10-15 years
lol lmao
>>
File: 00003-4102421294.png (2.87 MB, 1280x1920)
2.87 MB
2.87 MB PNG
>>
>>2817101
most of the example pics of that LoRA were done with the SakushiMix model --
https://civitai.com/models/78056/sakushimix-finished
Check it out. If you want I can try to redo your pic in that style but it won't have anything from the Megumin character besides hair style and the collar. Happy with that?
>>
>>2817101
>>2817127
also what kind of background do you want?
>>
File: 00134-2365874481-edit.png (3.04 MB, 1024x1536)
3.04 MB
3.04 MB PNG
>>2817154
>>2817155
>>2817101
>>2817022
in the end I used a different model because SakushiMix didn't handle inpainting too well
>>
File: 00018-1772517664.jpg (1.06 MB, 3648x2048)
1.06 MB
1.06 MB JPG
Figured I'd post it here as well.
My first attempt at a proper picture with stable diffusion.
Took me 2 days lol
>>
>>2817055
Not as in learning a program language, but there absolutely is a new vocabulary to learn.
As someone with no python experience and no idea what a windows batch file was, following the guide took regular goggle searches just to get through many of the steps.

Beyond that, models require specific terms to get the desired output.
For example, if you are going to try fulfilling a request, you cannot just enter the request verbatim into the prompt.
It needs to be translated into something the program will understand.
And each model will interpret the prompt differently.

Then there are commands that need to be added to the .bat (or somewhere) for improvements or to even make some things work.
A few threads back anons were going over how to get better results from the animation models and how to make the gifs/webms loop.
I gave up trying to figure out what they were doing.
>>
>>2817159
You can try running the image back through SakushiMix with img2img and see if something serviceable comes out.
>>
>>2817154
>>2817155
>>2817159
Sorry I didn't get back sooner. Thanks for doing what you did here, but I wasn't looking for one this realistic; if you're up to trying it again in a more typical anime style, use whatever lora works best. I'd just like it for it to be her.

Background doesn't particularly matter. If you're up to it, have it be like a concert stage I guess.
>>
File: 00157-2783065835-edit.png (848 KB, 1024x1536)
848 KB
848 KB PNG
>>2817166
>>
>>2815824
Requesting Komori Yui (from diabolic lovers) gens with her all nude. Jusy her or a look-alike that resembles her as there is almost no proper art of her in her birthday suit.
>>
>>2817162
>eyes
you sure ur using a vae bubby
>>
File: 00455-733756355.png (2.46 MB, 1536x1536)
2.46 MB
2.46 MB PNG
>>
File: 00041-3798922842.png (960 KB, 768x1152)
960 KB
960 KB PNG
>>2817189
>>
File: 00123-1141722967.png (911 KB, 768x1152)
911 KB
911 KB PNG
>>
File: 00160-2700817875.png (1.08 MB, 1152x768)
1.08 MB
1.08 MB PNG
>>
File: 00189-1836182287.png (1.04 MB, 768x1152)
1.04 MB
1.04 MB PNG
>>2817194
>>
>>2817179
I did use one, yes. What's the problem with the eyes?
>>
>>2817206
kinda blurry? lacking color? not sure
>>
File: 1893266804.png (1.97 MB, 1152x1536)
1.97 MB
1.97 MB PNG
>>
>>2817208
Oh I made them like that on purpose. I like that they look like rubies.
>>
>>2817214
>>2817208
Oh wait, I misread that.
Do you need to tell adetailer to use a vae separately? Cause I didn't do that.
>>
>>2817179
the vae changes the color saturation, doesn't have much to do with the eyes. He's just using a western style model.
>>
>>2817215
no, no need for that afaik. It's just the model as the other anon said, if it doesn't look off to you then it's probably a preference thing

>>2817233
im aware, it's easier to spot with the eyes and the whole thing looked similar to vaeless symptoms
>>
File: AiPatty 005.jpg (642 KB, 1024x1440)
642 KB
642 KB JPG
>>
>>2815824
Requesting Bloodborne or Lies of P kind of characters, Inspired on the setting I mean, not specific characters of those games
>>
File: 00597-BMP.png (1.53 MB, 1376x768)
1.53 MB
1.53 MB PNG
>>
File: 00014-277686724-edit.png (3.17 MB, 1024x1536)
3.17 MB
3.17 MB PNG
>>2817237
>>
File: 24971960.png (1.76 MB, 1024x1280)
1.76 MB
1.76 MB PNG
>>2816209
Sword is too hard
>>
File: 1699086678587467.png (875 KB, 704x1024)
875 KB
875 KB PNG
I am a complete noob when it comes to this, although already browsing some wikis. I was wondering what would be the best way of creating AI art drawn in various styles of a character that has like 3 different color palettes (using one palette at a time ofc)? Thanks in advance!
>>
File: 123.png (107 KB, 1892x892)
107 KB
107 KB PNG
>>2817295
get a lora of the character that you want to create and a lora of the style you want to use and then fuck around with the weight of both until you like the output. the model can make a huge difference for certain styles. some are trained for a specific style. look around on civitai and pick what u like, but for a beginner id recommend to pick one in the op. i never tried to use a specific color palette, but a search in the extension tab gives a couple of results. im certain you´ll find something there.
>>
File: file.png (2.54 MB, 1440x1600)
2.54 MB
2.54 MB PNG
>>
>>2817295
Train a lora on the images. If they're tagged properly you should be able to switch color palettes with prompts, worst case if you run into issues you'll have to make a separate lora for each color.
>>
File: Lightsaber_009.png (2.13 MB, 1024x1536)
2.13 MB
2.13 MB PNG
>>2817277
this unfortunately
>>
how much longer before AI can reliably do hands
>>
>>2817214
nothing wrong with the eyes, I like them. pretty good for something done so early on
>>
>>2817170
Thanks again- but this doesn't particularly resemble her either. Did you use a lora other than one for her? (it also seems excessively blurry)
>>
File: YJK11.jpg (184 KB, 1024x1024)
184 KB
184 KB JPG
>>
File: YJK22.jpg (205 KB, 1024x1024)
205 KB
205 KB JPG
>>
File: YJK33.jpg (185 KB, 1024x1024)
185 KB
185 KB JPG
>>
File: YJK44.jpg (163 KB, 1024x1024)
163 KB
163 KB JPG
Last one
>>
>>2817368
That one's spooky.
>>
>>2817368
>>2817370
Is Cujo ecchi?
>>
>>2817125
>wow, this year there was a significant breakthrough!!
>it means that every year there is one, right?!
>I am very young and know nothing about tehcnological progress!!
>wow I legit don't understand that 2022's breakthrough was based on decades of slow iterative development that coalesced into a critical mass!
>I legit think 2022 and 2023 will just keep repeating!!
>>
File: 00092-228779316.png (2.27 MB, 1024x1536)
2.27 MB
2.27 MB PNG
>>
File: 00000-1156999472.png (1.86 MB, 1024x1536)
1.86 MB
1.86 MB PNG
>>
>>2816860
>>2816867
I think if your referring solely to the black-box realization of LLMs you are on point - and for a lot of anon coomers who are using LLM's as a time-killing dopamine button they'll get jaded once they hit a recognizable level of consistency (aka mediocrity) in their output.

I think you underestimate what creative industry even the current technology can enable - good and bad - to people who possess some creative wherewithal. The example that is already being bemoaned is people using AI assets instead of hiring someone or using stock assets. Practically this enables the realization of games that wouldn't have been otherwise - but depending on the artist's taste the use of AI can go anywhere from taking away from the execution to enhancing it.
>>
File: 09485903475834.png (1.43 MB, 1024x1536)
1.43 MB
1.43 MB PNG
>>
>>2817447
I'm the person you're replying to, and agreed on all points.
>>
>>2817441
>>2817444
catbox pls?
>>
>>2817454
https://files.catbox.moe/zhuk6a.png
https://files.catbox.moe/65qpz9.png
>>
>>2817368
The others look nice but this one the dogs look terrifiying
>>
File: 00115-251420973.png (1.93 MB, 1024x1536)
1.93 MB
1.93 MB PNG
>>
File: 00027-1815348694.png (2.01 MB, 1024x1536)
2.01 MB
2.01 MB PNG
>>
>>2817483
oh wow! catbox please?
>>
File: 00022-4093585264-edit.png (835 KB, 1024x1536)
835 KB
835 KB PNG
>>2817364
alright here you go. when I put this through Deepboru it gives me the "megumin" tag so it must look like her.
let me know what you think!
>>
>>2817493
some parts a little blurry when you blow the image up. that's because I did a lot of inpainting because SD doesn't deal well with all the details when you treat this as a full body pic. there's the guitar, the lingerie, the face, the hands...
I'll try to tidy it up.
>>
File: 00177-613596061-final.png (1.81 MB, 1800x2700)
1.81 MB
1.81 MB PNG
>>2817493
>>2817494
>>2817364
final version
>>
>>2817498
just don't view it in Chrome because it blows it up beyond 100% zoom and makes it blurry
>>
I'm enjoying putting girly stuff on boyish girls
>>
>>2817490
https://files.catbox.moe/ey8n7j.png

Used this model: https://civitai.com/models/174090/mariner

required a bit of inpainting in the toes afterwards
>>
File: 00169-188270104.png (1.94 MB, 1024x1536)
1.94 MB
1.94 MB PNG
>>
File: witch.jpg (164 KB, 1024x1024)
164 KB
164 KB JPG
>>2816209
was thinking of doing a pic like that with inpainting but my brain is too fried
gave it a shot in dall-e and it's pretty good for this kind of thing with just a prompt so it seems like you can easily do it yourself (unless you want booba)

in terms of /e/ what do you imagine it's supposed to look like? aside from weapons, camo pants + witch robe/hat, bikini plate armor with a modern helmet?
>>
File: 00057-4223388427.png (1.34 MB, 960x1376)
1.34 MB
1.34 MB PNG
>>
>>2817504
>giant tits
>gargantuan hips
>pretty long hair
>BOYISH GIRL OMG
>>
>>2817532
nice style can i get a catbox?
>>
File: 00079-3257726692.png (1.61 MB, 1024x1536)
1.61 MB
1.61 MB PNG
>>
File: 00101-2924865381.png (1.64 MB, 1024x1536)
1.64 MB
1.64 MB PNG
>>2817606
>>
File: 00168-2572008697.png (1.54 MB, 1024x1536)
1.54 MB
1.54 MB PNG
>>2817607
>>
File: 00171-2572008700.png (1.63 MB, 1024x1536)
1.63 MB
1.63 MB PNG
>>2817609
>>
>>2817603
it's dall-e 3
>>
>>2817612
i see. thank you
>>
>>2817532
Thats super cool
>>
File: 09829034584903853.png (1.44 MB, 1024x1536)
1.44 MB
1.44 MB PNG
where the mummy fans
>>
File: catbox_moezm7lgb.png.png (1.53 MB, 1024x1536)
1.53 MB
1.53 MB PNG
https://files.catbox.moe/zm7lgb.png
>>
File: 00056-3559563894 (1).png (1.5 MB, 1024x1536)
1.5 MB
1.5 MB PNG
>>
File: 169911516532432595.jpg (329 KB, 1200x1600)
329 KB
329 KB JPG
>>2815823
>loras trained on SD 1.5 typically only work with realism models
>loras trained on nai or nai-like models typically only work with cartoon/semi-realism models
> using regular regularization images assists in the learning process by making sure it's not too rigid with the train directory images (for example, this allows you to put a subject in any environment or any kind of clothing even if every single train image has that person inside and wearing only one type of clothing)

So here's my theory. People smarter than me probably have already figured this out but I think this is how it could work. I regularly train realism loras based on real people. Train on SD 1.5. Have a regularization directory of 500 or 600 images depending on who I'm training. That directory is to ensure the model does not overfit. My biggest gripe with training in general is that I can use these models on wheelers and models but they do not work well, if at all, on anime models like aom3, anything v4, Meina, etc.

So here are my questions:

1) what having a regularization directory of let's say $250 realism images and 250 anime / cartoonish images allow it to have more versatility and be able to work with not just SD 1.5 models but anime models too?

2) my theory is that perhaps merging SD 1.5 with another enemy model like Nai or anything V3 could also help with this too.


To the people ITT who are way smarter than me, does what I said and why I wanna accomplish make sense? I want a person-lora to work both with a model like realistic vision AND an orangemix model. Is this possible? Are the methods I described feasible? Would they even work?
>>
>>2817652
I'm not a training expert, so I can only speculate based on what I have used, but there's a gap that needs to be bridged between realism and anime style. Most modern anime models already have SD 1.5 and nai as ancestors, so that is not really the issue. I've used concept loras based on realistic style and it's been hit and miss on whether they work in an anime context. It usually ends up looking muddy and incomprehensible.
After you bridge the gap, what do you expect the output to look like? It will be neither anime nor realistic. Basically the same problem applies in real life if you were to ask an artist to do something that is both realistic and anime.
>>
>>2817656
>and it's been hit and miss on whether they work in an anime context
At which point we've faced with catastrophic forgetting?
>>
>>2817702
What do you want? A list of realistic loras that work vs ones that don't? Like I said, I'm not an expert on training so I don't know how things are trained and so I don't know what works and what doesn't. I don't know what goes into training to make certain loras compatible with the nai/anime strain of models. Maybe there are other anons that can chime in, but all I know is that it's a tall order to make realistic things work in an anime context and vice versa.
>>
>>2815824
I want to see girls getting [spoiler]headpats[/spoiler]
>>
>>2817264
catbox?
>>
>>2817705
I'm not an expert on this either, but AFAIK overbaking and forgetting are the first things the model developers should care about and avoid of. Generalizing is the purpose of machine learning after all. I want to have a model which is able to create not only photorealistic images, but also cartoon, anime etc, and it should not just be good at it all, but also be able to effortlessly float between the styles and even combine them (which is quite possible) if that's your wish. That's what you really can call a good model. In this regard, NAI is garbage. And many newer models don't even know some things the base NAI knows. And that's exactly the reason why you can't really "bridge the gap". Simply take a look at DE3, it's not perfect, but it has shown potential. In the end it all comes down to the training methods, quality and quantity of the datasets used, the size of the models and computational costs.
You'll probably want to bring style or concept to your LORA anyway though, so you should try to avoid fucking up the model as well. It the base is good, it shouldn't be very hard though, I imagine, since the good model already recognizes most of the things present on your dataset and won't crap out your lora.
>>
File: Nemona.png (2.88 MB, 1566x2340)
2.88 MB
2.88 MB PNG
Bigger resolution: https://files.catbox.moe/798wz0.png
>>
>>2817716
Very nice... Now show me her butt hole.
>>
>>2817716
Is she supposed to only have three fingers?
You really should work on your QC if you're using it to promote yourself.
>>
File: 00000.png (2.63 MB, 1536x1920)
2.63 MB
2.63 MB PNG
boob curtain test
>>
File: 01129-BMP.png (1.3 MB, 1024x1024)
1.3 MB
1.3 MB PNG
>>
File: 00009-3518781079.png (2.92 MB, 1280x1920)
2.92 MB
2.92 MB PNG
>>
>>2817493
>>2817498
OR here, sorry about being late to get back (again.) These are indeed quite a lot better and much more in line with what I was looking for, thank you. Though what is leading to the blurriness in these?
>>
>>2817781
It's an artifact of the diffusion process. These things aren't magic, if you want the best results you're going to have to do some work yourself.
>>
>>2817783
I'm mainly just curious; I just haven't noticed this type blurriness in most other AI anime art.
>>
File: 01342-BMP.png (1.56 MB, 1024x1024)
1.56 MB
1.56 MB PNG
>>
File: 00369-3670922345.png (1.76 MB, 1024x1536)
1.76 MB
1.76 MB PNG
>>>/h/7651924
>>
File: catbox_vfzjc4.png (1.48 MB, 1024x1520)
1.48 MB
1.48 MB PNG
>>
File: 00011-BMP_cleanup.png (1.33 MB, 1024x1024)
1.33 MB
1.33 MB PNG
>>
File: 00612-4270635228.png (724 KB, 768x1152)
724 KB
724 KB PNG
>>
File: 00792-2941715972.png (717 KB, 768x1152)
717 KB
717 KB PNG
>>2817825
>>
File: 00737-2941715972.png (817 KB, 768x1152)
817 KB
817 KB PNG
>>2817826
>>
File: 00774-2941715972.png (618 KB, 768x1152)
618 KB
618 KB PNG
>>2817827
>>
File: 00013-123490059e2.png (2.5 MB, 1440x2160)
2.5 MB
2.5 MB PNG
>>
>>2817652
tl;dr
whats the issue?
>>
>>2817828
catbox pls
>>
>>2817834
probably the tagging
>>
>>
>>
>>
>>2817789
it depends...if you're viewing the image in Chrome it blows it up beyond 100% which makes it blurry.
if you're looking at it normal size, there are some blurry patches. it's basically because we're doing img2img of a full body portrait. in trying to respect the original image, SD has a hard time filling in little details of a full body portrait, like hands, face, and the guitar. So I have to go in afterwards and inpaint details, which is why you get blurry patches like around her right elbow area.
"most other AI anime art" that you see on here is not img2img it's text2img, so the AI has free reign to generate original details with a huge database of reference material. It's not tied to copying one image. It's hard for SD to translate elements of a source pic in another style while keeping detail AND fidelity. I could have turned up denoising strength and gotten more detail but you were quite specific about wanting to keep certain elements. Also, in text2img the AI artist will gen 20 images from one prompt and cherry pick the best ones without defects.

I gave you a huge image. if you can bare to reduce the image size, it looks fine. There is a limited amount of time I'm prepared to spend perfecting the inpainting on an image that I have no personal connection to. If you're still unhappy with the results I would echo what the other anon said and I would recommend that you consider investing in the time to learn about using SD independently.
>>
>>2817866
blurriness is also a factor of the model and upscaler. This can usually be fixed with an additional img2img pass at low denoising.
Here I've downscaled >>2817498 and re-upscaled it at 0.4 denoising. Notice the outer lines especially are more crisp and defined, and this is likely because I used based67 which is known for producing very clean lines.
Note that I'm not saying it's "wrong" to have softer lineart or a chromatic abberation effect from a model, it's just a different aesthetic and some people view this as being blurry.
>>
File: 1836039288.png (1.85 MB, 1280x1024)
1.85 MB
1.85 MB PNG
Should I cover up the pussy too?
>>
Their marching band outfits are fun.
>>
>>2817866
>>2817877
You've really done more than I ever expected and I hugely appreciate that. I'm still trying to gauge the kind of setup I'd need to get what I need out of SD, and this has also been more than informative.
>>
File: xyz_grid-0033-622183991.png (3.41 MB, 2112x2565)
3.41 MB
3.41 MB PNG
Thoughts?
>>
File: 00997-1226281266.png (527 KB, 768x960)
527 KB
527 KB PNG
>>2817836
>1200+ images in todays folder
https://files.catbox.moe/uusael.png
>>
File: 1699733334409614.jpg (543 KB, 1158x1637)
543 KB
543 KB JPG
>>2815824
Can the AI improve the coloring of a picture? Like taking this picture and make the coloring more elaborated with shades, brights, etc
>>
File: 23496598797558783.jpg (721 KB, 3072x2048)
721 KB
721 KB JPG
>>
File: xyz_grid-0056-928384319.png (2.65 MB, 2112x2438)
2.65 MB
2.65 MB PNG
>>2817907
>>
>>2817907
>>2817931
i wanna see her spreading her pussy
>>
>>2817910
I'm unaware of any loras that allow for stippled coloring like that, so that detail and a lot of other fine details like the gradient coloring and linework for shading are getting lost as I crank up the denoising. This is with lineart controlnet, denoising 0.65. Below this, the colors just didn't pop. fwiw I think this came out objectively worse than the original.
If you want to preserve the original details and just saturate it more, curves in photoshop/krita is probably what you're looking for.
>>
>>2817799
Very nice style. Give details if you feel like it pls
>>
Is posting real photos for references and such permissible in this thread?
>>
>>2817953
yeah, nobody mods on /e/
>>
>>2817907
For me, it's the high ponytail with blunt bangs
>>
File: catbox_osue7b.png (923 KB, 960x1440)
923 KB
923 KB PNG
Spent the day making thumbnails for my Loras

It's a ton of fun and I highly recommend it.
>>
File: catbox_27hi50.png (2.28 MB, 1280x1920)
2.28 MB
2.28 MB PNG
Gusset Pantyhose
>>
File: catbox_9r91zk.png (1.23 MB, 960x1440)
1.23 MB
1.23 MB PNG
Good old Shirow.

I like a subtle lingerie nightgown.
>>
File: 00004-2023-11-11.png (1.28 MB, 960x1440)
1.28 MB
1.28 MB PNG
Ishikei
>>
File: catbox_nkofwy.png (547 KB, 640x960)
547 KB
547 KB PNG
>>2817994
>>
File: catbox_yd201y.png (1.28 MB, 960x1440)
1.28 MB
1.28 MB PNG
Dako
>>
File: catbox_xa0ief.png (715 KB, 640x976)
715 KB
715 KB PNG
Drow
>>
File: catbox_wr8y2x.png (1.36 MB, 960x1440)
1.36 MB
1.36 MB PNG
>>2817992
>>
File: catbox_5cjpmg.png (771 KB, 640x960)
771 KB
771 KB PNG
Bluethebone
>>
File: catbox_knmc0r.png (1.27 MB, 960x1440)
1.27 MB
1.27 MB PNG
Viera
>>
File: 39048756903476.png (1.53 MB, 1024x1536)
1.53 MB
1.53 MB PNG
>>2817992
>>2817993
>>2817994
cute
>>
File: 00139-333019336.png (1.44 MB, 1024x1024)
1.44 MB
1.44 MB PNG
>>2817907
>>2817828
>>2817827
>>2817931
Just to see if I could do it.
Needs more work, but I have four basic [without the swimsuits] loraless looks that I like.
>>
File: img-QpMab3kIucdlioNQDg8xy.jpg (147 KB, 1024x1024)
147 KB
147 KB JPG
>>
>>2818012
Looks like we're both in a similar mood.
>>
>>
File: catbox_yw3nia.png (1.02 MB, 960x1440)
1.02 MB
1.02 MB PNG
>>2818004
Thanks :D
>>
File: catbox_rbhuka.png (985 KB, 960x1440)
985 KB
985 KB PNG
>>2818020
>>
File: catbox_6jw8j4.png (1.1 MB, 960x1440)
1.1 MB
1.1 MB PNG
>>2818021
>>
File: catbox_i15cxm.png (1.41 MB, 960x1440)
1.41 MB
1.41 MB PNG
>>
File: catbox_ig0hoy.png (1.44 MB, 960x1440)
1.44 MB
1.44 MB PNG
>>2817237
It's having trouble making it as gloomy and depressing as BB, but it's a start.
>>
File: 00192-547996282.png (1.02 MB, 768x1152)
1.02 MB
1.02 MB PNG
>>2818011
>>
>>
File: catbox_3wdtg6.png (1.34 MB, 960x1440)
1.34 MB
1.34 MB PNG
>>2817991
A few more before bed.
Melon22
>>
File: catbox_t76jvn.png (1.08 MB, 960x1440)
1.08 MB
1.08 MB PNG
Nyantcha
>>
File: catbox_5fhe46.png (1024 KB, 768x1152)
1024 KB
1024 KB PNG
Squishy underboob
>>
>>2817833
Catbox please?
>>2817907
high ponytail + blunt bangs activates my neurons
>>
File: catbox_g45tdm.png (1.54 MB, 1024x1520)
1.54 MB
1.54 MB PNG
>>
File: high res.png (595 KB, 513x751)
595 KB
595 KB PNG
im retarded, anyone got catbox for this or any similar ones?
>>
File: 09348590437643.png (1.29 MB, 1024x1536)
1.29 MB
1.29 MB PNG
>>
File: catbox_jc6btw.png (1.36 MB, 960x1464)
1.36 MB
1.36 MB PNG
drew
>>
File: catbox_g0vdxr.png (1.33 MB, 960x1440)
1.33 MB
1.33 MB PNG
>>
File: catbox_qc07ev.png (1.46 MB, 960x1440)
1.46 MB
1.46 MB PNG
>>
File: catbox_m3cwkc.png (1.23 MB, 960x1440)
1.23 MB
1.23 MB PNG
>>
File: catbox_rqh2jo.png (1.43 MB, 960x1440)
1.43 MB
1.43 MB PNG
>>
File: 00071-1227777200.png (3.42 MB, 1280x1920)
3.42 MB
3.42 MB PNG
>>
File: 098754690875464.png (1.58 MB, 1024x1536)
1.58 MB
1.58 MB PNG
>>2818070
cool
>>
File: 00135-2820285112.png (3.14 MB, 1920x1280)
3.14 MB
3.14 MB PNG
genning this produced some eldritch horror
https://files.catbox.moe/wmpclr.jpg

>>2818073
thanks
>>
>>2818070
moth Toko. Cute spider tattoos here too >>2818075
>>
File: 00156-1068983494.png (3.83 MB, 1920x1280)
3.83 MB
3.83 MB PNG
>>2818078
i was attempting some sort of mosquito vampire at first but then i decided to just go along with the whims of sd, now that i look at it again it does resemble a moth kek, thanks for pointing that out
a mothpire is fine too
>>
>>2818080
nice spooky expression and cool cock monster with balls on the sides of its head
lol
>mothpire
+2 pen when biting through clothes
>>
>>2818050
https://files.catbox.moe/v0wl08.png
>>
>>2817992
this is some god tier hayrstyle
>>
>>2818083
Thanks!
>>2818075
NIce gen. That catbox is cursed, though
>>
>>2818080
Neat. I'm also a fan of trippy and eldritch type horror stuff. Though I'm not gonna push it too far and keep it /e/.
>>
>>
Some really good gens here. I'm waiting for someone to gen a Loli Tainaka Ritsu from K-on!
>>
File: 1289095992.png (1.64 MB, 1536x1024)
1.64 MB
1.64 MB PNG
>>
>>
>>2818099
>Loli
Might have to go to /b/ for that.
>>
File: 00013-1431591904.png (2.93 MB, 1280x1920)
2.93 MB
2.93 MB PNG
>>
>>2818115
well it doesnt have to nude or rule breaking, Just never seen one made
>>
>>2818080
That is honestly one of the coolest AI generated images I've ever seen. Good job, man. True art. Maybe you could catbox? Also, what model were you using?
>>
File: FE46203.jpg (62 KB, 1024x768)
62 KB
62 KB JPG
>>2815824
This is an ancient photo I was curious to see if someone could try converting into anime and expanding on. Ideally, I'd like to see it as Ryuuguu Rena. Here's loras for her:
https://civitai.com/models/7894/ryuuguu-rena-higurashi
https://civitai.com/models/104536/rena-ryuuguu-when-the-cicadas-cry
>>
>>
OP here. Page 8 and 35 images to go. Won't have time to do it tomorrow so new thread tonight.
The last highlights have a couple gaps that can fit small but very wide images. If you want to fill it, feel free to post, otherwise I'll fill it myself with either downsized pics from the thread of filler gens.
Good day, anons.
>>
>>2818115
>>2818123
Just link it offsite.
>>
File: BibooSpirit.png (1.67 MB, 1152x1728)
1.67 MB
1.67 MB PNG
>>2818105
>>
File: 00034-133238418.png (1.93 MB, 1024x1536)
1.93 MB
1.93 MB PNG
>>
File: 00031-1584192258.png (2.19 MB, 1920x1080)
2.19 MB
2.19 MB PNG
>>
File: 2348562395673345.jpg (702 KB, 3072x2048)
702 KB
702 KB JPG
>>
File: 00026-2233591971.png (3.08 MB, 1920x1280)
3.08 MB
3.08 MB PNG
>>
>>
>>2818177
I see you've found my /vt/ posts.

Anyway. Gonna try to take us to a new thread in an hour or two. Anyone browsing, feel free to help the thread get to the image limit first. 27 images left, done with highlights, so maybe post your old favorites or experiments that didn't turn out perfect.
>>
>>2818082
>+2 pen when biting through clothes
heh
terrifying

>>2818087
sd does best cursed body horror when it's an accident

>>2818097
those are some cool horntacles

>>2818131
thanks, the model is just based64
there's a bit of a process to how it was genned because it was img2img

here's a catbox of the original gen
https://files.catbox.moe/zizi4u.png
png info and send it into img2img

next you put this whole image into img2img as the source
https://files.catbox.moe/4l69i4.jpg
i'm on an older version of sd so you might not get the exact replica but i just tested this process and it replicates the original gen just fine

both loras are on civit, touko lora is excellent, the artist lora might need some wrangling with neg prompt because it loves turning girls into monsters and making everything brown

prompt in there is half nonsense cause i like typing in random shit and seeing if i get anything out of it
>>
>>2818215
your gens with galaxy girls are really cool
>>
>>2818196
catbox?
>>
>>2818222
Thanks for sharing your workflow. Interesting use of img2img.
New thread incoming.
>>
File: 2806504-part1.jpg (2.14 MB, 3000x3000)
2.14 MB
2.14 MB JPG
old highlights and old gens in no particular order
>>
File: 2806504-part2.jpg (1.85 MB, 3000x3000)
1.85 MB
1.85 MB JPG
>>
File: 2806504-part3.jpg (1.81 MB, 3000x3000)
1.81 MB
1.81 MB JPG
>>
File: 2806504-part4.jpg (1.88 MB, 3000x3000)
1.88 MB
1.88 MB JPG
>>
File: 2806504-part5.jpg (1.71 MB, 3000x3000)
1.71 MB
1.71 MB JPG
>>
File: 2806504-part6.jpg (1.82 MB, 3000x2804)
1.82 MB
1.82 MB JPG
>>
File: 2806504-part7.jpg (2.81 MB, 3000x3000)
2.81 MB
2.81 MB JPG
>>
File: 2806504-part8.jpg (1.91 MB, 3000x3000)
1.91 MB
1.91 MB JPG
>>
File: 2803902-part1.jpg (1.8 MB, 3000x2808)
1.8 MB
1.8 MB JPG
>>
File: 2803902-part2.jpg (1.97 MB, 3000x2812)
1.97 MB
1.97 MB JPG
>>
File: 2803902-part3.jpg (1.76 MB, 2800x3000)
1.76 MB
1.76 MB JPG
>>
File: 2803902-part4.jpg (1.49 MB, 3000x2880)
1.49 MB
1.49 MB JPG
>>
File: 2803902-part5.jpg (1.9 MB, 2988x2940)
1.9 MB
1.9 MB JPG
>>
File: 2803902-part6.jpg (1.62 MB, 2812x2544)
1.62 MB
1.62 MB JPG
>>
File: 2803902-part7.jpg (1.72 MB, 3000x3000)
1.72 MB
1.72 MB JPG
>>
File: 2803902-part8.jpg (1.87 MB, 3000x3000)
1.87 MB
1.87 MB JPG
>>
File: 2801266-part1.jpg (2.19 MB, 2916x3000)
2.19 MB
2.19 MB JPG
>>
File: 2801266-part2.jpg (1.8 MB, 2832x3000)
1.8 MB
1.8 MB JPG
>>
File: 2801266-part3.jpg (1.95 MB, 3000x2896)
1.95 MB
1.95 MB JPG
>>
File: 2801266-part4.jpg (2.21 MB, 2640x3000)
2.21 MB
2.21 MB JPG
>>
File: 2801266-part5.jpg (2.44 MB, 3000x2932)
2.44 MB
2.44 MB JPG
>>
File: 2801266-part6.jpg (1.75 MB, 2992x2744)
1.75 MB
1.75 MB JPG
>>
File: 2801266-part7.jpg (2.09 MB, 2876x3000)
2.09 MB
2.09 MB JPG
>>
File: 2776426-part5.jpg (2.09 MB, 3000x3000)
2.09 MB
2.09 MB JPG
>>
File: 2762003-part4.jpg (1.49 MB, 2848x2464)
1.49 MB
1.49 MB JPG
>>
New thread
>>2818252
>>2818252
>>2818252



[Advertise on 4chan]

Delete Post: [File Only] Style:
[Disable Mobile View / Use Desktop Site]

[Enable Mobile View / Use Mobile Site]

All trademarks and copyrights on this page are owned by their respective parties. Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.