<h3 id="heading-22058">TL;DR</h3>An ahegao LoRA model intended to generate those "ahegao profile pictures". Trained with 100% monochromatic images of ahegao anime girls, zoomed in on their faces.<h1 id="heading-22059"><code>1girl, monochrome, gao, open mouth, tongue out, close up</code></h1><h1 id="heading-22059"> 🌸 aheGAO - a LoRA 🌸</h1><h2 id="heading-19834">Description</h2>Gao is a LoRA concept model trained using cropped pictures from hentai mangas, focusing solely on the female's face.The creation of this concept was intended for generating "ahegao profile pictures" out of curiosity, not specifically for use as a profile picture.However, of course, nobody is stopping you from using this for your profile picture... 🤔The training images were 100% monochromatic and were zoomed-in ahegao faces intended to be profile pictures, just for clarification.The LoRA was trained with the <a target="_blank" rel="ugc" href="https://civarchive.com/models/9409?modelVersionId=90854">Anything</a> checkpoint.You don't have to use that checkpoint, just for your information.<h2 id="heading-22060">Usage</h2>This LoRA is NOT SUITED for resolutions that aren't 1:1You CAN still generate images with a size like 512 x 768, but around ⅓ of the time, it's going to look horrendous.The following includes trigger words added to the training captions. Use them in your positive prompt to generate more specific details, or exclude them in your negative prompt if you don't want such features.<code>gao</code> = the main trigger word<code>ahegao</code> = an optional choice; could further enhance the 'ahegao' face<code>monochrome</code> = monochromatic coloring - even without specifying it, the results are occasionally monochrome, so include it in the negative prompt to decrease the probability.<code>open mouth</code> = give the subject an open mouth<code>tongue out</code> = give the subject a tongue that's sticking out<code>ecstasy</code> = add a stronger euphoric moaning effect or a feeling of ecstasy to the subject, along with a slight grin or an open-mouthed smile - essentially giving the subject a "happy" expression rather than a "neutral" or "frowning" one with their mouth being open.<code>crying</code> = give the subject watery eyes, or tears - can look somewhat odd; this aspect will be improved upon in future versions.<code>rolling eyes</code> = make the subject's eyes appear to be rolling upwards, conveying an ecstasy-like expression<code>heart-shaped pupils</code> = turn the subject's pupils into a heart shape<code>blush</code> = add a blush to the subject<code>close up</code> = gives the image a stronger profile picture effect, zooms in closer to the subject's face - also useful for when the image isn't even zoomed in at all<h3 id="heading-19">LoRA's MODEL STRENGTH</h3><code>0.7 - 0.9</code> works decently for me.And, don't forget to add this into your negative prompt:<code>(worst quality, low quality:1.4)</code>For that FULL effect 😉You can go mess around with the prompt, CFG, whatever sampler you prefer, etc.Go ahead and find what works good enough for you!<h2 id="heading-8644">Cons</h2>These issues are not guaranteed to be evident 100% of the time; these cons only occur occasionally.<ul><li>Unwanted speech bubbles / captions - the concept was trained on manga, so of course, there will be captions everywhere...</li><li>Uncanny empty white eyes - likely due to the extreme rolling back of the eyes in the training images... interesting...</li><li>Strange objects - those text captions ( from the manga / training images ) cause Stable Diffusion to interpret them as random floating objects, especially with those speech bubbles, leading to even stranger results...</li></ul>Other cons include malformed head shape, strangely-shaped tongue, etc. Adding such cons to the negative prompt can fix the problem, other times, not the case.

ahe-GAO [ アヘ顔 ]

<ul><li>Completely reset training, no finetuning of any of the last versions... again...</li><li>v1.75 has more training steps than v1.0Honestly don't know why I uploaded v1.5, it's honestly seems a bit worse than v1.0 v1.75 should be better though</li><li>Edited some caption files for some imagesSome images had glasses, so I added <code>glasses</code> in the image's prompt to make the training understand it more.Also added <code>headband</code> on a few images, not sure what it was, but some images of the women had this white thing on their head, like a headband or a bandana or something.On v1.0 / v1.5, these "headbands" were generated involuntary, you couldn't really do much about it.</li><li>v1.0 / v1.5 had issues of like weird settings, strange objects like near the edges of any generated image. v1.75 fixed most of that.</li><li>OVERALL, v1.75 should be better than v1.0 and v1.5v1.5 -&gt; Supposed to fix issues with captioning, had less training, making the model's generation quality worse than v1.0.v1.75 -&gt; Supposed to increase model's generation quality, with better captioning, more controllable prompts, etc. A very good upgrade.</li></ul>

Files with SHA256: 6a160f472067266e18d2379ff9e31a491f2ed1965cfd8489b11a0ed51fbba988