[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
/cgl/ - Cosplay & EGL

Name
Options
Comment
Verification
4chan Pass users can bypass this verification. [Learn More] [Login]
File
  • Please read the Rules and FAQ before posting.
  • There are 25 posters in this thread.

08/21/20New boards added: /vrpg/, /vmg/, /vst/ and /vm/
05/04/17New trial board added: /bant/ - International/Random
10/04/16New board for 4chan Pass users: /vip/ - Very Important Posts
[Hide] [Show All]


Janitor applications are now closed. Thank you to everyone who applied!




File: 12 layer burrito fashion.jpg (1004 KB, 1057x1404)
1004 KB
1004 KB JPG
previous thread >>10776440 hit image limit

In this thread we use https://www.craiyon.com/ (migrating from https://huggingface.co/spaces/dalle-mini/dalle-mini) to generate coords. Please rate and post your own generated images. Let's see if AI can be a source of inspiration for jfashion.
>>
File: face of lolita fashion .jpg (384 KB, 985x1008)
384 KB
384 KB JPG
>>10780849
there are ways to work around its limitations
>>
File: american breakfast sugar.jpg (417 KB, 1031x1291)
417 KB
417 KB JPG
>>
File: green gobelin.jpg (851 KB, 1080x1341)
851 KB
851 KB JPG
>>
>>
File: true love.jpg (977 KB, 1029x1385)
977 KB
977 KB JPG
>>
File: pea coat.jpg (727 KB, 1080x1329)
727 KB
727 KB JPG
>>
File: moomincorn.jpg (516 KB, 960x1129)
516 KB
516 KB JPG
trying to generate a cutsew
>>
File: remember 2012.jpg (920 KB, 1080x1382)
920 KB
920 KB JPG
>>
File: high street lolita goth .jpg (813 KB, 1080x1470)
813 KB
813 KB JPG
>>
>>
File: old school simulator .jpg (878 KB, 1051x1457)
878 KB
878 KB JPG
>>
File: current year.jpg (987 KB, 1080x1531)
987 KB
987 KB JPG
>>10781117
>>
File: ai cannot count to 4.jpg (188 KB, 967x1171)
188 KB
188 KB JPG
i tried to make you a 4chan ita bag, cgl
>>
>>
>>10781152
the AI can handle other shapes, it just cannot count to 4
>>
File: cupcake collection .jpg (828 KB, 2880x2880)
828 KB
828 KB JPG
chocolate, vanilla, and strawberry cupcake handbags
>>
>>
File: 01a.png (2.06 MB, 1590x1980)
2.06 MB
2.06 MB PNG
>>
File: lisa brite.jpg (998 KB, 1079x1380)
998 KB
998 KB JPG
>>
File: rainbow frank .jpg (1.01 MB, 1079x1382)
1.01 MB
1.01 MB JPG
>>10781875
>>
File: visual brite.jpg (939 KB, 1080x1370)
939 KB
939 KB JPG
>>10781877
>>
File: lolita frank.jpg (960 KB, 1079x1365)
960 KB
960 KB JPG
>>10781880
last one

i wonder if AI like this could be used to teach or illustrate the differences between such niche fashions. it would first need more training since its current knowledge is narrow. still, it is surprisingly close with these 4.
>>
I tried to get it to generate Ouji coords
>>
>>10782014
Last one
>>
File: 01b.png (1.64 MB, 1537x1885)
1.64 MB
1.64 MB PNG
>>
File: 01c.png (2.03 MB, 1555x1971)
2.03 MB
2.03 MB PNG
>>10782045
interestingly, the above post and this one shows heavy preference to a single design. I wonder if it's basing it off some single reference set of images somewhere on the internets.
>>
File: lol.png (2.24 MB, 1569x1715)
2.24 MB
2.24 MB PNG
wall-e thinks these are itai as fuck.
>>
>>10782047
The search won't know what "itai" means. Gotta use more common terms.
>>
>>10782014
>>10782015
nice
>>
File: dream holic style wigs.jpg (806 KB, 2880x2880)
806 KB
806 KB JPG
>>
File: arnold palmlita.jpg (432 KB, 1080x1387)
432 KB
432 KB JPG
>>
File: arnold palmlita variants.jpg (1.15 MB, 2880x2880)
1.15 MB
1.15 MB JPG
>>10782508
variants, clockwise: honey lavender, raspberry peach, vanilla mint, blackberry + blueberry
>>
File: mclita-020958_Chrome.jpg (634 KB, 1080x1287)
634 KB
634 KB JPG
>>
>>
File: softserve ita.jpg (530 KB, 986x1129)
530 KB
530 KB JPG
>>10782602
it struggles with shapes sometimes
>>
File: tfw.jpg (796 KB, 1080x1275)
796 KB
796 KB JPG
>>10782604
>>
File: auto complita.jpg (825 KB, 1026x1329)
825 KB
825 KB JPG
predictive text craiyon made doglita
>>
File: gobelin beets.jpg (581 KB, 1045x1379)
581 KB
581 KB JPG
gobelin for the forest goblins
>>
File: tea bees.jpg (1.1 MB, 1080x1281)
1.1 MB
1.1 MB JPG
>>10783178
more gobelin fun
>>
File: goblita 1.jpg (1.1 MB, 1030x1439)
1.1 MB
1.1 MB JPG
>>10783191
putting prompts together
>>
>>10783325
>>
File: larmstream .jpg (532 KB, 960x1130)
532 KB
532 KB JPG
it knows larme
>>
File: triple threat .jpg (626 KB, 961x1131)
626 KB
626 KB JPG
>>
>>10782612
I love this, it totally worked
>>
File: chocka chock.jpg (1.03 MB, 1030x1283)
1.03 MB
1.03 MB JPG
>>10783696
it is amazing what the ai can understand
>>
File: Clipboard02.png (1.15 MB, 1169x1251)
1.15 MB
1.15 MB PNG
>>
File: Clipboard05.png (1.01 MB, 1141x1246)
1.01 MB
1.01 MB PNG
>>10784001
second attempt.
>>
File: Clipboard04.png (1.68 MB, 1138x1292)
1.68 MB
1.68 MB PNG
>>10783338
my take on a similar theme
>>
File: Clipboard07.png (1.52 MB, 1152x1250)
1.52 MB
1.52 MB PNG
>>
>>10784007
nice
>>
this is the least unsettling result of the batch
>>
File: victorious .jpg (800 KB, 1031x1360)
800 KB
800 KB JPG
>>
vivienne westwood ita bag with kamikaze girls theme
>>
File: crai coord 01.jpg (794 KB, 1033x1340)
794 KB
794 KB JPG
what do you think, gulls? did the ai understand the assignment?
>>
File: lmao1.png (2.56 MB, 1247x1265)
2.56 MB
2.56 MB PNG
>>
File: 4chan lol 2.jpg (403 KB, 1221x1272)
403 KB
403 KB JPG
lmao
>>
File: LMAOOOOOOOOOOOOO.jpg (351 KB, 1201x1250)
351 KB
351 KB JPG
>>
>>10784554
>deamholic

fuck
>>
File: crai coord 02.jpg (743 KB, 1033x1392)
743 KB
743 KB JPG
>>10784554
attempt #2 with minimal changes

trying to keep it simple and see at what point the complexity becomes too much
>>
File: crai coord 03 .jpg (782 KB, 1080x1390)
782 KB
782 KB JPG
>>10784580
attempt #3

it refused to process the wig request until i changed the wording, and some colors it would not generate.
>>
>>10784647
i think this is because of the extra details (material + pattern) i added to the clothing items. the order of items matters less when the prompt is simple.
>>
File: yoshairy kei.jpg (607 KB, 959x1130)
607 KB
607 KB JPG
>>
File: crai coord 04.jpg (899 KB, 1034x1390)
899 KB
899 KB JPG
>>10784647
at the limits of complexity with this formula
>>
Has this ever happened to you?
>>
>>
File: see gulls fight.jpg (823 KB, 1027x1277)
823 KB
823 KB JPG
>>
File: old school time heist .jpg (423 KB, 1040x1355)
423 KB
423 KB JPG
>>
File: racoogal.jpg (855 KB, 1023x1276)
855 KB
855 KB JPG
>>
the data set includes images from Tokyo Fashion, Harajuku Fashion Walk, and wear.jp for sure. the ai's ability to reproduce the average wear.jp fashion snap is top notch, and we know other image sets have used wear.jp for machine learning.

so then why is the ai's knowledge of japanese brands so restricted? why does it recognize (and give extraordinary weight to) "angelic pretty", but it has nothing for "baby, the stars shine bright"? it does not even return an "everything but the girl" album, just literal baby dresses with stars on them. if it is because AP is more popular, then why is "metamorphose temps de fille" recognized but not btssb? is it due to AP and Meta being easier for the ai to recognize visually? is it because, despite being a generic name like "innnocent world" or "victorian maiden," the brand "angelic pretty" is the most iconic usage of its words, while "baby, the stars shine bright" is too ambiguous (along with VM, IW, MM etc.)?

is there an internet photo site that has hashtag categories for AP and Meta, but not for any other lolita brand? or did the data set only include certain tagged brands, to save space?

as for possible issues with uniqueness or vocabulary: "hime gyaru" is recognized as distinct from "gyaru," with small variations, but "ganguro" returns something completely off, despite its iconic distinctive look and unique name. (what the ai returns for "ganguro" is a thing you should see for yourself lol.)

the gaps in its knowledge are strange. it does not recognize "moi meme moitie", but it has a rough idea of what "egl" means, which is just wild. it can produce good yosuke shoes with the right prompts, but no other gothic jfash brand i have tested will show.

also it cannot understand "h.naoto" (or any variation thereof) but it knows hypercore, which is just disrespectful.

all of the brands and styles i mentioned are on the websites the ai definitely knows. so why does it only recognize a sliver of them?
>>
File: me without my brand.jpg (681 KB, 1016x1170)
681 KB
681 KB JPG
>>10785007
(ctd.)

what the ai can do already is amazing. it knows much more about the particulars of jfashion than what i expected from a free-to-use image generating bot. i love it. but its logic confuses me. i suspect human interference, probably eliminating whole categories to save space, but idk how the categories to save vs categories to exclude were decided on. does anyone have any insight?

in closing, here is Mana from Moi dix Mois in egl that is sadly too unlike Moitie
>>
File: instant regretsy .jpg (555 KB, 1021x1205)
555 KB
555 KB JPG
neat
>>
File: regretsy 2.jpg (282 KB, 1052x1228)
282 KB
282 KB JPG
>>10785091
small improvement
>>
File: 0637 - 5MvfDg3.jpg (39 KB, 310x422)
39 KB
39 KB JPG
>>10781117
Middle top row totally referenced this image for the poses
>>
>>10785169
awesome
>>
trying to prompt border prints
>>
>>
>>10784714
>Otakon
Yes literally
>>
>>10785108
Oh the ai used a betsey johnson necklace for this lol. Look up You Give Me Butterflies necklace.
>>
File: fairples.jpg (715 KB, 1031x1221)
715 KB
715 KB JPG
>>
File: 1629528872612.png (2.71 MB, 1328x1645)
2.71 MB
2.71 MB PNG
>>
nothing abnormal here

finger fringe is the future
>>
>>10785169
That's wild that you recognized that, nonna
>>
>>10784696
I love these, would absolutely wear
>>
File: TimeToDisco(4)_4.png (1.53 MB, 768x1280)
1.53 MB
1.53 MB PNG
Anyone here ever try disco diffusion? I've been trying gothic lolita related prompts and it's been interesting
>>
biblically accurate angelic pretty
>>
File: fabchallenge.jpg (795 KB, 2880x2880)
795 KB
795 KB JPG
i tried to generate a lolita dress like a faberge egg. i cannot do it to my satisfaction.

challenge: make a prompt for the AI to reliably make faberge egg lolita.

>easy mode
a dress with jeweled egg elements
>normal mode
a dress with a lolita silhouette (i.e., not egg-shaped) with faberge egg-like elements
>hard mode
a lolita wearing the normal mode dress
>impossibiru mode
hard mode but it has to look like an actual person and not a funky homunculus
>>
wig game too strong
>>
File: angelic puppy.jpg (870 KB, 1028x1329)
870 KB
870 KB JPG
>>
File: metamorphose temps de pig.jpg (942 KB, 1024x1382)
942 KB
942 KB JPG
>>10787267
>>
File: lolita mobile game .jpg (780 KB, 1080x1028)
780 KB
780 KB JPG
>>
File: lolita fighting game .jpg (927 KB, 1031x1487)
927 KB
927 KB JPG
>>
File: lolidate sim.jpg (702 KB, 960x1130)
702 KB
702 KB JPG
lolita fashion lesbian dating sim
>>
File: great lolita salt off .jpg (492 KB, 1053x1404)
492 KB
492 KB JPG
>>
how well does craiyon know its two recognized lolita brands?
>>
>>10788098
>>
File: angelic pretty prints .jpg (1015 KB, 2880x2880)
1015 KB
1015 KB JPG
>>10788099
using the prompt:

>ultra hdr 1080p close-up shot of high-quality fabric with highly detailed border print : "print name" designed by angelic pretty

cat tea party, sugar dream dome, crystal dream carnival, and misty sky. for misty sky i took out "border".
>>
File: meta prints .jpg (1.66 MB, 2880x2880)
1.66 MB
1.66 MB JPG
>>10788120
ditto for meta: wonder carousel, twinkle journey, fruit punch soda, and nostalgic matryoshka doll
>>
>>10788098
it turns out that the ai can sometimes guess which dress does not have a print. Meta's dresses whose names are also physical descriptions make good prompts.
>>
fake AP prints are fun for the whole comm

you could generate prints using common AP words or phrases, then have people guess which words were used. was it "melty dream diner", or maybe "sugar cream parlour"? a "candy theater" or a "bonbon circus"?
>>
File: new angelic pretty drops.jpg (1.34 MB, 2160x3840)
1.34 MB
1.34 MB JPG
>>10788415
dropped the damn pic
>>
File: ap hire me.jpg (1.4 MB, 2160x3840)
1.4 MB
1.4 MB JPG
>>10788415
i need "cherry chocolate whip" to exist irl
>>
>>
>>
File: thank mr wanwan.jpg (618 KB, 960x1130)
618 KB
618 KB JPG
>>
>>
File: what does it mean .jpg (678 KB, 961x1131)
678 KB
678 KB JPG
wait what
>>
>>10789486
Algorithm thought you meant Impact Wrestling
>>
Best timeline
>>
get into the future
>>
>>10789486
the pictures alone are funny but the misinterpreted prompt makes it hilarious
>>
>>
>>
File: uhhhhhhhhh.jpg (662 KB, 960x1129)
662 KB
662 KB JPG
30% of my comm
>>
File: everything's dancing .jpg (1.05 MB, 1029x1330)
1.05 MB
1.05 MB JPG
no, craiyon

let's try something else
>>
File: goblin queen .jpg (987 KB, 1030x1329)
987 KB
987 KB JPG
>>10791071
still Bowie, ok.

thanks for trying, craiyon
>>
File: cats kibble party .jpg (279 KB, 953x1118)
279 KB
279 KB JPG
>>
>>10789986
embrace tradition
>>
File: ap phase six lineup.jpg (1.35 MB, 2160x3840)
1.35 MB
1.35 MB JPG
>>10788797
more AP word salad mixing
>>
File: dreamy bloodbath room .jpg (780 KB, 1032x1178)
780 KB
780 KB JPG
jesus christ
>>
File: OtaDon.png (1.37 MB, 789x846)
1.37 MB
1.37 MB PNG
>>
>>
File: leonardo da petti .jpg (407 KB, 1035x1243)
407 KB
407 KB JPG
he was ahead of his time in so many ways
>>
do you think this is funny, craiyon?
>>
File: mana sama why .jpg (1.16 MB, 2160x2552)
1.16 MB
1.16 MB JPG
>>10791868
i cannot keep these results to myself any more

try "moi meme moitie", pls, and tell me if you get this consistently unsettling shit
>>
>be me
>be AI
>recognize bodyline on sight
>cannot tell moitie apart from war crimes

que the fuck
>>
>>10791869
I love the atepie images, he just wants to be a designer
>>
File: literally atpie.jpg (746 KB, 1080x1248)
746 KB
746 KB JPG
>>10791876
craiyon keeps showing me naked cavorting soldiers and dead bodies when i prompt it with variations of Moitie*,

so to cleanse my eyes, your comment inspired me to prompt pic related. bottom left looks cute, bottom right looks like it popped straight out of an Eiko Ishioka exhibit.

*when i tried moimememoitie, it showed me The Hague lol
>>
Advanced AI art (midjourney) for you noobs.

"sweetlolita angelic pretty fashion brand with sheep print"

Anytime I do angelic pretty and sweetlolita together, I get fucked up looking mascots.
>>
The future of ita threads is here
>>
I just got accepted into dall-e 2 beta
>>
>>10791972
>>
>>10791959
amazing

>>10791973
awesome, congrats!
>>
File: pretty fake.jpg (1.41 MB, 2160x3840)
1.41 MB
1.41 MB JPG
>>10791959
>Anytime I do angelic pretty and sweetlolita together, I get fucked up looking mascots.
how much control do you get with midjourney? have you tested for other brands?

i have played with Starry AI. it lacks a lot of creative freedom, so even if the images are high quality, i did not enjoy it.
>>
>>10792022
>pic unrelated

i literally cannot stop generating prints based on nothing but brand name + brand-style word strings. craiyon's unlimited iterations and opportunities to fine-tune make its quality constraints hardly an issue.
>>
File: melty scalping town .jpg (979 KB, 1030x1281)
979 KB
979 KB JPG
>>
shipping delays got out of hand
>>
File: outback hoarders .jpg (995 KB, 1027x1352)
995 KB
995 KB JPG
>>
File: accurate and realistic .jpg (515 KB, 1027x1223)
515 KB
515 KB JPG
>>
File: prime forester .jpg (882 KB, 1025x1278)
882 KB
882 KB JPG
>>
File: radical mori .jpg (1.09 MB, 1046x1248)
1.09 MB
1.09 MB JPG
>>10792328
>>
File: civic forestry .jpg (910 KB, 1040x1241)
910 KB
910 KB JPG
>>10792330
>>
File: lolita wedding meetup .jpg (520 KB, 1058x1456)
520 KB
520 KB JPG
>>10791959
>>10791973
can they understand multi-subject prompts? craiyon tries, but fails
>>
>>10782047
>>10782091
>>
>>10792533
perfect
>>
>>
>>10792029
As someone who's been waiting 6+ months for their seamail parcel containing a Meta DD, I can relate
>>
>>
Is it just me, or is the algorithm getting smarter and recognizing lolita terms better due to all the people here making lolita prompts?
>>
File: AOC Cosplaying.png (1.35 MB, 784x848)
1.35 MB
1.35 MB PNG
>>10793033
>>
>>10793034
theoretically it does not work that way. however, there was a recent update that improved overall quality for all results, which may be what you have noticed.
>>
File: SpongeBob Tutuskirt.jpg (611 KB, 1033x1165)
611 KB
611 KB JPG
>>
File: y2kei 1.jpg (805 KB, 1046x1214)
805 KB
805 KB JPG
what if decora, but zumiez
>>
File: y2kei 2.jpg (681 KB, 1057x1273)
681 KB
681 KB JPG
>>
File: y2kei 3.jpg (815 KB, 1026x1171)
815 KB
815 KB JPG
sXe sk8er grrrl
>>
File: y2kei 4.jpg (859 KB, 1026x1170)
859 KB
859 KB JPG
>>
File: y2kei 5.jpg (639 KB, 1028x1224)
639 KB
639 KB JPG
>>
File: y2kei 6.jpg (714 KB, 1049x1170)
714 KB
714 KB JPG
>>
File: just normal lolita .jpg (174 KB, 1041x1186)
174 KB
174 KB JPG
>>
File: dont look in her eyes .jpg (171 KB, 1034x1177)
171 KB
171 KB JPG
>>10794027
>>
File: waifu.jpg (232 KB, 1038x1193)
232 KB
232 KB JPG
>>10794029
damn what's her skincare routine
>>
File deleted.
>>10792458
yes. very well, but there's some tricks to getting it to work right. you'll end up writing a big ass fucking paragraph and re-iterating until you get something you like, which it gives you a lot of flexibility.

I'm not fully sure it registers lolita well though. I've gotten some lolita esque art, but nothing fully "this is lolita"

It does make high quality art, however.
>>
File: lolitaart.png (1.87 MB, 820x822)
1.87 MB
1.87 MB PNG
>>10794118
>>
>>
>>10794122
based

>>10794121
cool
>>
File: ostomy bag kei.jpg (190 KB, 1018x1170)
190 KB
190 KB JPG
y'all got any of them accidental nightmare results worth sharing?
>>
>>10794118
>I'm not fully sure it registers lolita well though. I've gotten some lolita esque art, but nothing fully "this is lolita"
i wonder if that's due to censoring, to avoid users abusing the AI for harmful shit.

craiyon will give a sweet lolita dress if it's by AP, even if you don't specify "lolita" at all, and you can fiddle with design elements (pic related). if different AIs do censor the word "lolita" i hope they still include the japanese fashion datasets that use brand and print names.
>>
File: design testing.jpg (1.29 MB, 2160x2558)
1.29 MB
1.29 MB JPG
>>10794152
actual pic related
>>
>>10794147
Looks like hardboiled eggs glued onto the dress
>>
File: CZR.png (1.43 MB, 770x841)
1.43 MB
1.43 MB PNG
>>
>>10794292
face like an angel
>>
>>
File: bears .jpg (255 KB, 1018x1190)
255 KB
255 KB JPG
i would buy it
>>
>>
File: gyaruoshit.jpg (815 KB, 1032x1179)
815 KB
815 KB JPG
>>
a familiar face appeared
>>
>>10796425
looks like crystal from old
>>
Craiyon & DALL·E mini are over. StableDiffusion is the new big player in town
>>
>>10797034
>>
>>10797037
>>
>>10797034
>Craiyon & DALL·E mini
same thing

nice pics, how much control do you have over the result?



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.