If you enjoyed this model, why don't you check out my other works? I put a lot of effort into correctly recreating artist styles and making the occasional character LoRA.😊This model was requested by someone who has already deleted their account 😂This model was trained using the collab/guide by holostrawberry <a target="_blank" rel="ugc" href="https://civarchive.com/models/22530/guide-make-your-own-loras-easy-and-free">[Guide] Make your own Loras, easy and free - colabs | Stable Diffusion Other | Civitai</a>Checkpoint trained on and used in examples:<a target="_blank" rel="ugc" href="https://huggingface.co/a1079602570/animefull-final-pruned/blob/main/model.ckpt">model.ckpt · a1079602570/animefull-final-pruned at main (</a><a target="_blank" rel="ugc" href="http://huggingface.co">huggingface.co</a><a target="_blank" rel="ugc" href="https://huggingface.co/a1079602570/animefull-final-pruned/blob/main/model.ckpt">)</a>If you want optimal results and don't want to experiment combining styles, use this base model!It is old but gold, and allows for model training that gets a lot closer to the original, compared to tons of other often used models like AnyLoRA. Otherwise I recommend using simple anime style checkpoints.I am once again open for suggestions for other styles, SFW and NSFW.You can always drop model suggestions in the comments, both for styles that are missing on civit or those that are outdated. No guarantees but if it interests me I'll give it a go.<h2 id="heading-226"></h2><h2 id="heading-226">About the artist:</h2>Twitter: 十五夜【バツ泣き改 単行本発売！】 (@zyugoya) / X (<a target="_blank" rel="ugc" href="http://twitter.com">twitter.com</a><a target="_blank" rel="ugc" href="https://twitter.com/zyugoya">)</a>Zyugoya draws manga and hentai with a strong focus on almost excessively busty women. Their original characters are drawn in an easily recognizable style.On the nsfw side there is a lot of implied and steamy sex and very strong censorship. Check out 497373<h2 id="heading-227">Weights &amp; Prompts</h2>The activation prompt is:<pre><code>zyugoya</code></pre>The training data on the nsfw side is exclusively implied or heavily censored sex. So full censorship is quite likely even with prompting uncensored. It can be used at full strength with lightweight character LoRA.Here are some useful prompts to recreate their characters (also in the example images):<pre><code>purple eyes, huge breasts, black hair, twintails, blue hair, short twintails, sidelocks, multicolored hair, two-tone hair, blunt bangs,sharp teeth, fangs, thighhighs, collarbone, shorts, tank top, striped thighhighs, striped</code></pre><pre><code>long hair, blonde hair, black hair, brown eyes, multicolored hair, huge breasts, @_@</code></pre><pre><code>long hair, pink hair, teeth, pink eyes, huge breasts, piercing, ear piercing, hair over breasts</code></pre><pre><code>
long hair, skirt, large breasts, shirt, black hair, red eyes, hair between eyes, school uniform, pleated skirt, teeth, socks, sharp teeth, messy hair</code></pre><pre><code>short hair, large breasts, red eyes, gloves, cleavage, jewelry, tail, pink hair, earrings, wings, pointy ears, pink eyes, leotard, makeup, detached collar, head wings, demon tail, black leotard, eyeshadow, black wings, black feathers</code></pre><pre><code>short hair, blue eyes, blonde hair, bright pupils, white pupils,large breasts</code></pre><pre><code>long hair, blonde hair, large breasts, twintails, brown eyes</code></pre>Use a weight of 0.9-1.3, adjust to taste and depending on your checkpoint. Other checkpoints will often only work with a much lower weight (0.6 or similar).As usual I have included an XYZ plot for reference.Please leave a review if you enjoyed this model or have problems with it. This helps me with improving future models and finetuning them in general. Give it a try and throw some images down below! 👇

Files with SHA256: 2e5a36280bfba97e3ec974744c99c87599db9f0af16c523fe3804ee6ea5f616d