/hdg/ - Stable Diffusion

Anime girls generated with AI

Catalog Archive
Name
Options
Subject
Message

Max message length: 12000

files

Max file size: 15.00 MB

Total max file size: 50.00 MB

Max files: 4

Supported file types: GIF, JPG, PNG, WebM, OGG, and more

E-mail
Password

(used to delete files and posts)

Misc

Remember to follow the Rules

The backup domains are located at 8chan.se and 8chan.cc. TOR access can be found here, or you can access the TOR portal from the clearnet at Redchannit 3.0.

Board Locked? Request Reopening

APNG and GIF uploads are temporarily disabled while we deal with a spammer problem.


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

Rules Anonymous 01/18/2023 (Wed) 09:32:27 No. 1 [Reply]
Make sure to familiarize yourself with the global rules! Board rules can be decided and established if people like this. Also give a check to the rulings on edge cases, specifically these two. https://8chan.moe/site/res/4481.html#q4482 https://8chan.moe/site/res/4481.html#q4483 Loli is fine as long as you stick to the rules of the site and keep it strictly anime only since the site has zero tolerance on anything realistic, but it does not have to be only loli, other anime girls are fine too. And keep the content of your posts to be about Stable Diffusion, characters generated with it or discussion related to SD. So please remember to stay away from realistic tags, any tags that might add realism to your pictures or any models that might add realism to your pictures. Any picture that is too realistic, is based on real living people or is a picture of someone is subject to be deleted immediately and the user posting it can be banned on the spot. Remember, furry and western art styles are not allowed here. 'Western' refers to cartoony art styles, realistic art styles or art styles used or often seen in the western part of the world and not where the artist or franchise is originally from. An artist can be from Japan and draw in a western or cartoony art style, while an artist can also be from the United States and draw using eastern or anime art styles, so please keep in mind this board was made to be focused on anime-related things. Technology and code-related discussions are okay and allowed. These discussions further our understanding of Stable Diffusion and help others improve this technology or help others make better pictures, so feel free to discuss this too.
Edited last time by anyathere on 01/28/2023 (Sat) 22:55:08.

(819.28 KB 1248x1824 1729790462273694-2545167176.jpg)

/hdg/ #25 RED Edition Anonymous 03/30/2025 (Sun) 15:43:43 No. 29491 [Reply] [Last]
Previous thread: >>28235 Resources: https://rentry.org/8chhdgOP
35 posts and 49 images omitted.
(2.17 MB 1627x1632 02148-3771251836.png)

(1.33 MB 3997x2069 xyz_grid-0021-2295193457.jpg)

I'm gonna repost this here because I remember one anon asked me to share this lora but i just couldn't do it at that time because it was a shitty one, I hope he's still around here. It was trained on noob vpred 1.0 Also, I'm sharing this one. She's Monaca, an OC from the artist ShiShigaJ5. Here's his pixiv: https://www.pixiv.net/en/users/13302316. He used to post on /v/, and I think he still does from time to time. Her OC was partially responsible for turning me into a ped-- I mean, lolicon. I really, really love her, to the point that I downloaded koikatsu and her card just to take a bunch of screenshots to make this lora. Yes, it was trained only on koikatsu images, so it might have some issues. Besides that, I remember making a lora with this dataset about 8 months ago, but it was tagged really bad and it used to generate random stuff out of nowhere in the image. So I retagged it way better this time, with a confidence of 0.1, and spent a lot of time curating the tags. (v13 and v14 are loras trained with the old tags and v15 with the new tags). Without further ado here is the lora: https://files.catbox.moe/4xmkhi.safetensors and the trigger words: monacaN, short hair, [light brown hair:brown hair:0.4], blue eyes, short twintails, twin drills, hair ribbon, pink ribbon, thick eyebrows, Well that's all for today, thanks for reading my blogpost. Until next time, anons.
(17.39 KB dbooruUniforms.txt)

(1.36 MB 1152x896 00080-3767145828.png)

(1.37 MB 1152x896 00010-1507905106.png)


these wildcards were long so i'm sharing.
>>29527 >base model is better because [incomprehensible gibberish about fringe styles] i haven't seen anybody saying that base model is outright "better", just that it's more flexible which is correct. I use 102d and while it holds back some styles (painterly and sketchier ones), 95% of the time I don't care that much and stick to 102d now because it's much easier to use and I like its style.

putting together a small OP rentry and then I'll bake
new: >>29491 let me know if any changes should be made to the rentry in the new thread

h/d/g thread Anonymous 02/02/2023 (Thu) 18:09:25 No. 2497 [Reply] [Last]
Some anon mentioned starting one thread for soft /d/ stuff but since he didn't do it guess i'll do it myself.
299 posts and 356 images omitted.
>I can't consistently gen futas being CBTed It's so fucking over.
(103.44 KB 896x1152 image (2).webp)

>>29223 Is that Zheng mixed with some other artist? Genning actual women with Zheng feels illegal.


Prompting musouzuki on illustrious seems to generate text all over even if I put text and speech bubbles on neg
bake bread
(2.01 MB 1248x1824 catbox_1fnm50.png)


>almost 1200 someone make a new thread soon please thanks
(29.59 KB 474x315 bread.jpg)

>>25903 Bread baked: >>25904 >>25904
>>25900 Box for the tianliang-looking one pls

(2.70 MB 1280x1856 weddingnight.png)

/hdg/ #20 Wedding Night Edition Anonymous 12/15/2023 (Fri) 19:51:39 No. 23690 [Reply] [Last]
1019 posts and 1189 images omitted.
>>24732 Original cup poster. I tried using pretty much every pony mix, but I just can't get results I like. Maybe I need to fiddle around more.
>>24733 The style tag combinations here https://github.com/Siberpone/pd-styles/blob/main/styles-pd-v6.csv + style LoRAs is what made me happy with my autismmix gens.
(2.14 MB 1280x1920 catbox_c7iybr.png)

New bread >>24735 >>24735

(1.13 MB 960x1320 bread.png)

/hdg/ #19 Anonymous 10/24/2023 (Tue) 21:26:15 No. 22560 [Reply] [Last]
1095 posts and 938 images omitted.
>>23687 >what's this about HRT ruining nerd communities? You haven't noticed all the trannies in the gaming/anime/computer space since ~2016?
make bread

>>22554 Here is the lora, still needs some improvement, I'll keep an eye out. https://mega.nz/folder/dfBQDDBJ#3RLMrU3gZmO6uj167o-YZg/file/ZapnBZhI
>>22555 oh no this mesugaki is about to be corrected by a crowd

/hdg/ #17 Anonymous 08/16/2023 (Wed) 22:03:41 No. 19952 [Reply] [Last]
Previous thread >>18739
1475 posts and 667 images omitted.
this anon needs to go back to varishangout where he belongs
>>21448 they're gonna love the shoutout
>>21447 >go back to where you came from Sorry, can't go back to /h/, I don't have a time machine that can take me back to february/march.

>>19948 dumb nigger
>>19948 Do you even know what FUD means dumbass
Catbox seems to be airtight when dealing with adversaries, litterbox is pretty bullet proof, and I think the small size limits of catbox and its quick detect of shutting down questionable material help it avoid the issues anonfiles could have ran into by a potential glowops

(1.07 MB 1024x1488 Y3VuY3Vu.png)

/hdg/ pixiv\twitter share thread Anonymous 01/28/2023 (Sat) 02:55:21 No. 912 [Reply] [Last]
Share your pixiv or twitter here if you're an /hdg/ anon that made a pixiv\twitter to upload their generated work. Share techniques or feedback to other anon's works if you want to help them out >Support our based /hdg/ brothers, cunny or no cunny
297 posts and 26 images omitted.
pixiv users
>>17960 I'm almost certain that it's a shitpost
https://twitter.com/skbjijii https://www.pixiv.net/en/users/96264320 Just starting out, I plan to do lots of loli (as well as non-loli too).

/hdg/ #15 Anonymous 06/06/2023 (Tue) 17:53:35 No. 17518 [Reply] [Last]
Previous thread >>16264
1197 posts and 937 images omitted.
(2.80 MB 1024x1536 catbox_gh2kib.png)

(2.37 MB 1024x1536 catbox_rj271s.png)

(2.56 MB 1024x1536 catbox_fy66hx.png)

(2.35 MB 1024x1536 catbox_lx8cov.png)

man do i love ai
>>18734 Why would you even watch vtubers, just gen the cuncun
Any new good mixes around or are we still stuck with b64v3?

(1.86 MB 1024x1536 00008-2178941320.png)

/hdg/ #14 Anonymous 05/08/2023 (Mon) 09:59:19 No. 16264 [Reply] [Last]
Previous thread >>14999
1197 posts and 580 images omitted.
>>17514 Did anyone even benefit from that?
Might want to get to baking that new thread
>>17515 The "speedup" requires converting pytorch models to onnx. You can convert existing models but I haven't bothered to try because it's also not compatible with lora https://devblogs.microsoft.com/directx/optimize-directml-performance-with-olive/

[ 12 ]
Forms
Delete
Report