sexual situations

physical violence

disturbing

male nudity

extremist

hanging

hate symbols

nazi party

weapon violence

female swimwear or underwear

male swimwear or underwear

partial nudity

white supremacy

adult toys

graphic male nudity

illustrated explicit nudity

nudity

self injury

corpses

convenient censoring

oral invitation

emaciated bodies

exposed female nipple

female nudity

sexual activity

sexual intent

undressed

male underwear

female swimwear

genitals

female underwear

thick thighs

breasts out

strapless leotard

vore

bestiality

breast out

one breast out

huge breasts

gigantic breasts

huge butt

covered nipples

hair over breasts

no panties

sitting on face

anal

dildo riding

downblouse

oral

porn

futanari

hentai

nude

lingerie

sexy

nsfw

revealing clothes

graphic violence or gore

graphic female nudity

wide hips

peeing

blowjob

suggestive

bukkake

cumshot

cumdrip

cum in pussy

cum on face

cum on hair

cum on body

cum on tongue

cum on hands

cum in mouth

cum on pussy

eat_cum

fellatio

implied fellatio

after fellatio

triple fellatio

autofellatio

pov fellatio

fucked silly

presenting ass

presenting pussy

spreading legs

spread legs

swimwear

This Version of Hassaku is the hentai variant of my other <a target="_blank" rel="ugc" href="https://civitai.com/models/140272/hassaku-xl-sfwandnsfw?modelVersionId=378499">hassaku xl model. </a>But again, like my 1.5 model with a priority for hentai art. It is trained on top of <a target="_blank" rel="ugc" href="https://civitai.com/models/257749/pony-diffusion-v6-xl">pony. </a>Goal is to make it easier to archive good hentai anime art, without the need to use complicated source and long quality prompts.My <a target="_blank" rel="ugc" href="https://discord.gg/zSR5FcYWWE">Discord</a> for everything related to anime models and art. You can support me on my <a target="_blank" rel="ugc" href="https://www.patreon.com/user?u=27247323">patreon</a> and if you are interested.My models:<a target="_blank" rel="ugc" href="https://civitai.com/models/2583"> hassaku,</a> <a target="_blank" rel="ugc" href="https://civitai.com/models/85909/sudachi">sudachi(flat 2d)</a>, <a target="_blank" rel="ugc" href="https://civitai.com/models/41916/koji">koji(2d)</a>, <a target="_blank" rel="ugc" href="https://civitai.com/models/67120/yuzu">yuzu(light semirealistic)</a>, <a target="_blank" rel="ugc" href="https://civitai.com/models/24383">grapefruit</a>_____________________________________________________Supporters:Thanks to my supporters Riyu, SETI, Jelly and Kodokuna on my <a target="_blank" rel="ugc" href="https://patreon.com/user?u=27247323&amp;utm_medium=clipboard_copy&amp;utm_source=copyLink&amp;utm_campaign=creatorshare_creator&amp;utm_content=join_link">patreon</a>! _____________________________________________________Using the model:Use this extension to use it easier with booru tags: <a target="_blank" rel="ugc" href="https://github.com/DominikDoom/a1111-sd-webui-tagcomplete"> https://github.com/DominikDoom/a1111-sd-webui-tagcomplete</a> <ul><li>Use score_9 in positive and score_4 in negative masterpiece -&gt; score_9 best quality -&gt; score_8 high quality -&gt; score_7 medium quality -&gt; score_6 normal quality -&gt; score_5 low quality -&gt; score_4 worst quality -&gt; score_4 You can also use score_8_up, score_7_up and such, but effects are reduced. Model is merged with a style lora, to make its style stable and to higher up the quality. Because of that, score_4 and score_5 have less effect, Lora /Checkpoint was trained with score_9, but can also be leaved out, for a bit more basic look.</li><li>width and height should be a multiple of 64, to prevent gray borders (not a model issue, its a general thing for sdxl models)</li><li>Tag order: 1girl/1boy, character name, everything else in any order</li><li>Some concepts appear with strong 2.5d faces. Negatives like nose, lips and sources helps (in 1.1 reduced and in 1.2 rare, in 1.3 not a problem anymore)</li><li>It is a continuation of pony, source_pony, source_furry, source_cartoon, 3d, monochrome, realistic in negative works. Even with less effects on it</li></ul><ul><li>Model is trained with images with minimal disruptive features like floating texts, logos, speak bubbles and signatures as possible. If such features appearing in a image, please use prompt "signature" as negative.</li><li>Excluded metadata and franchise tags, don't use them. meta data -&gt; something like "highres", franchise tags like "re:zero kara hajimeru isekai seikatsu" are pruned on characters like "rem_(re:zero)". Pony was trained on them, it seems.</li><li>Here are some good resolution options for SDXL/Pony:<ul><li>1024 x 1024</li><li>1152 x 896</li><li>896 x 1152</li><li>1216 x 832</li><li>832 x 1216</li><li>1344 x 768</li><li>768 x 1344</li><li>1536 x 640</li><li>640 x 1536</li></ul></li></ul>License info:Because this model is a continuation of <a target="_blank" rel="ugc" href="https://civitai.com/models/257749/pony-diffusion-v6-xl">pony</a>, from PurpleSmartAI, it have this license: This model is licensed under a modified Fair AI Public License 1.0-SD<a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/"> </a>(<a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">https://freedevproject.org/faipl-1.0-sd/</a>) license.The following modifications have been added to Fair AI Public License:<ul><li>You are not permitted to run inference of this model on websites or applications allowing any form of monetization (paid inference, faster tiers, etc.). This applies to any derivative models or model merges.</li></ul>

I repaired the eyes, but it still as example generates green or red eyes when prompted for brown eyes. However, it no longer produces damaged eyes in my tests. Additionally, it now creates fewer blurry, white, or messy genitals. Unfortunately, I had to remove a bit of the SDXL merge to make these repairs. This part was responsible for making the backgrounds nice and providing knowledge outside of my normal anime dataset and tags. As a result, the backgrounds are a bit worse and less detailed, and the model seems a little less stable due to my merging back to a version without eye problems and my additional training on it. Using training for better backgrounds resulted in much simpler and worse backgrounds, so I dropped that attempt and created this compromise model, which still generates good backgrounds. You can still use version 1.3, but if you don't care much about backgrounds and don't mind slightly less colorful images, you can use this model instead. What is better:<ul><li>Eye artifacts should be now very rare</li></ul><ul><li>Fewer incorrect eye colors.</li><li>Better formed out pupils (including special pupils like hearts-shaped pupils)</li><li>Reduced blurry, white, or messy genitals.</li></ul> What is worse:<ul><li>Colors are more muted.</li><li>Worse and less detailed backgrounds and landscapes.</li><li>Minimal more issues with hands and composition.</li><li>Some sfw concepts are a little bit less precise</li></ul> I am now working on my natural language model to generate NSFW captions for images and on SD3.

v1.3(better eyes version)

It is a merge with normal sdxl and my training to create a balance of nsfw capabilitys, character retain, look and backgrounds. I needed to do this, because to fix couple of things of ponys training, the most effective way is to merge models in, that are not "broken". But that also brings problems with it (see the last point).What is better:<ul><li>Contrast and colors are much toned down</li></ul><ul><li>Backgrounds</li><li>sfw knowlege</li></ul>What is worse:<ul><li>nsfw composition</li><li>nsfw precision (some nsfw prompts work less good then before)</li><li>Anime character precision</li><li>Artist tags</li></ul>Problems that i want to fix the next couple days, because it is a merge with complete different unet, prompts ect:<ul><li>Eyes have sometimes artifacts</li><li>Especialy "brown eyes" have problems</li><li>Genitals appears blurry sometimes (especially insertions)</li></ul>Notice: censored in negatives censor or makes genitals blurry/white/black

v1.3

Style is more anime like on some concepts and is overall more brightWhat is better:<ul><li>much more stable in style and limbs</li><li>slightly better artist tag understanding (nonLora 1.1 remains much better at it)</li><li>it is a strait up update of mostly everything (in detail and style)</li></ul>What is worse:<ul><li>Backgrounds changed, feels more illogical, but is much better at certain backgrounds in compare to pony</li><li>Can be to bright for some concepts</li><li>Faces appear less "mature" and having a more generic anime look, for some, thats a negative</li></ul>Problems:<ul><li>Overall too bright, working on that, except if SD3 comes out. So bright in fact, that dark night images are hard to get.</li><li>Eyes are sometimes undefined (blurry or circle pupil or such)</li><li>Some strange image artifacts can appear</li></ul>

v1.2

Use this as default model. It used a lora to force a relative stable default style to it. But artist tags don't work or work semi good because of it. Whats better:<ul><li>More anime like with much less realistic looking faces</li><li>Much stronger stable model art style</li><li>Less detached limbs (for nsfw)</li><li>Some characters working better then before</li><li>Higher output quality</li></ul>Remains mostly the same:Hands remained mostly the same, some concept have better working hands, some not. Notes:<ul><li>I concentrated my training mostly for nsfw, don't expect stable and good constructed sfw images with good hands and poses.</li></ul><ul><li>Censored in negative tends to output more realistic looking images. But most created images are in default not censored.</li></ul>

v1.1

Use this only if you want to use artist tags or to train it further, without a lora in its way. Not recommened for normal use! Highly unstable in style, limbs and hands with high tendencies to gen realistic faces. I have train it with a high learning rate latetly for testing and it got more unstable but better with artist tags. Because normal 1.1 is inteded for normal use, i picket this one with better artist tag recocnition, but is essentialy worse in every part in compare to the lora merge that was already in its base model more stable.

v1.1nonLoraMerge

Its a bit unstable in overall art style and have some problems with hands/limbs. But is easier to handle in compare to pony, if you want anime art out of it. It knows now artist tags and some anime characters better in compare to pony. What i want to fix/making better on it now, until SD3 comes out:<ul><li>A bit more anime like (some concepts do strong 2.5 faces)</li><li>Make hands better</li><li>Less detached limbs</li><li>A bit better sfw with better prompt understanding for it</li></ul>

v1.0

Hassaku XL (Pony)