<h3 id="simile-comparison-likeness-parallel-similar-resembling"><strong><em>Simile </em>= comparison, likeness, parallel, similar, resembling</strong></h3><h3></h3><p><strong>Note:</strong> Preview images are generated without the use of LORAs</p><h2></h2><h3></h3><h1 id="noobai-ver.-v3.0-v4.0-v5.0-v6.0"><span style="color:rgb(34, 139, 230)"><strong>No</strong></span><span style="color:rgb(21, 170, 191)"><strong>ob</strong></span><span style="color:rgb(18, 184, 134)"><strong>AI</strong></span><span style="color:rgb(250, 176, 5)"><strong> </strong></span><span style="color:rgb(64, 192, 87)"><strong>ve</strong></span><span style="color:rgb(130, 201, 30)"><strong>r. </strong></span><strong>[v3.0, v4.0, v5.0, v6.0]</strong></h1><p></p><h2 id="attention"><strong>⚠️ATTENTION⚠️</strong></h2><p>Check 'about this version' tab for more details..</p><p>Also, <a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/1837143?type=Training%20Data">here</a> is the list for the artist tags. There are two files in the zip file, one if the full artist list and the other is the list of artist that I've personally tested to be working and most of them are also from gay artists..</p><p></p><h3 id="about"><strong>About</strong></h3><p>To be honest I didn't expect to update this quickly but I can't resist NoobAI's updated datasets. Artist tags also performs much better with less dependent on emphasis to achieve a desired effect. Overall it is an improvement of the already great model, Illustrous XL.</p><p></p><h3 id="tips-for-artist-styles-characters"><strong>Tips for artist styles / characters</strong></h3><p>Similar to ILXL, just add in the artist or character tags and that's it. If you're not sure what to write for the tags, just search it on <a target="_blank" rel="ugc" href="https://danbooru.donmai.us/">danbooru</a> or <a target="_blank" rel="ugc" href="https://www.downloadmost.com/NoobAI-XL/danbooru-artist/?page=1">here</a>. See sample images for examples on how to prompt the tags..</p><p></p><p></p><h3 id="my-settings"><strong>My Settings</strong></h3><pre><code>Sampling Method: - Euler a (less detailed and smoother textures)
                 - DPM++ 2M (more detailed lines and textures)
Sampling Steps: 20+
Upscaler: 4x_NMKD-Siax_200k / Remacri
CFG Scale: 3 - 5
Clip Skip: 2
VAE : Already built-in</code></pre><p></p><h3 id="positive-prompt:"><strong>Positive Prompt:</strong></h3><pre><code>very awa, masterpiece, best quality, absurdres, perfect quality, detailed background, intricate details</code></pre><p></p><h3 id="negative-prompt:"><strong>Negative Prompt:</strong></h3><pre><code>lowres, worst quality, bad quality, bad anatomy, signature, username, logo, watermark, artist name, bad hands</code></pre><h3></h3><h3></h3><h1 id="illustrious-ver.-v2.0"><span style="color:rgb(34, 139, 230)"><strong>Ill</strong></span><span style="color:rgb(21, 170, 191)"><strong>ust</strong></span><span style="color:rgb(18, 184, 134)"><strong>rio</strong></span><span style="color:rgb(64, 192, 87)"><strong>us v</strong></span><span style="color:rgb(130, 201, 30)"><strong>er. </strong></span><strong>[v2.0]</strong></h1><h3 id="about"><strong>About</strong></h3><p>Personally I still prefer the default style of the Pony version but the prompt adherence and style flexibility of the Illustrious XL is just too good to pass up. Prompting and tagging is also a lot easier than the pony version from what I've tested. I tried to replicate the look of the Pony version but there's just too much artist styles for me to do anything without messing with the overall quality, oh well..</p><p></p><h3 id="tips-for-artist-styles-characters"><strong>Tips for artist styles / characters</strong></h3><p>Illustrious is a fine-tuned model trained on Danbooru datasets, so there are a lot of data on various artist's styles and characters. So you can prompt a specific style or characters without the need of loras as long as they have substantial amount of dataset on Danbooru and are not too recent. See sample images for examples on how to prompt styles..</p><p></p><p></p><h3 id="my-settings"><strong>My Settings</strong></h3><pre><code>Sampling Method: Euler a, DPM++ 2M / DPM++ 3M SDE
Sampling Steps: 25+
Upscaler: 4x_NMKD-Siax_200k / Remacri
CFG Scale: 3 - 6
Clip Skip: 2
VAE : Already built-in</code></pre><p></p><h3 id="positive-prompt:"><strong>Positive Prompt:</strong></h3><pre><code>masterpiece, best quality, absurdres, newest, perfect quality, best quality, absolutely eye-catching, detailed background, intricate details</code></pre><p></p><h3 id="negative-prompt:"><strong>Negative Prompt:</strong></h3><pre><code>lowres, worst quality, bad quality, bad anatomy, sketch, jpeg artifacts, signature, watermark, artist name, old</code></pre><h3></h3><h3></h3><h1 id="pony-ver.-v1.0"><span style="color:rgb(34, 139, 230)"><strong>P</strong></span><span style="color:rgb(21, 170, 191)"><strong>on</strong></span><span style="color:rgb(18, 184, 134)"><strong>y</strong></span><span style="color:rgb(250, 176, 5)"><strong> </strong></span><span style="color:rgb(64, 192, 87)"><strong>ve</strong></span><span style="color:rgb(130, 201, 30)"><strong>r. </strong></span><strong>[v1.0]</strong></h1><h3 id="about"><strong>About</strong></h3><p>Just like with my <a target="_blank" rel="ugc" href="https://civarchive.com/models/138441/homosimile">HomoSimile</a> model, I'm trying to get that specific look that's between 'anime' and 'western art'. I went a bit easy with the LORAs to ensure better compatibility with other styles. So if you want to use a specific artist's styles it wont diminish the results.</p><p></p><p></p><h3 id="my-settings"><strong>My Settings</strong></h3><pre><code>Sampling Method: DPM++ 2M / DPM++ 3M SDE
Sampling Steps: 30+
Upscaler: 4x_NMKD-Siax_200k / Remacri
CFG Scale: 4 - 6
Clip Skip: 2
VAE : Already built-in</code></pre><p></p><h3 id="positive-prompt:"><strong>Positive Prompt:</strong></h3><pre><code>score_9, score_8_up, score_7_up, highly detailed, intricate details, detailed background</code></pre><p></p><h3 id="negative-prompt:"><strong>Negative Prompt:</strong></h3><pre><code>score_6, score_5, score_4, score_3, score_2, score_1, low quality, deformed, bad hands, watermark</code></pre><h3></h3><h3 id="disclaimer"><strong>⚠️DISCLAIMER⚠️</strong></h3><p>Please do <strong>NOT </strong>generate illegal content with this model. You are solely responsible for any unethical use of this model(s)</p><h3></h3><h3 id="model-license"><strong>Model License</strong></h3><ul><li><p><a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">Pony Diffusion v6 XL</a></p></li><li><p><a target="_blank" rel="ugc" href="https://huggingface.co/OnomaAIResearch/Illustrious-xl-early-release-v0">Illustrious XL</a></p></li><li><p><a target="_blank" rel="ugc" href="https://civarchive.com/models/833294/noobai-xl-nai-xl">NoobAI-XL</a></p></li></ul><p></p>

HomoSimile XL [Pony, Illustrious, NoobAI]

<p><strong>v6.0</strong></p><p><strong>What's new:</strong></p><ul><li><p>Added 6 new artists tags : toto18, tenji89, hotchax, holo eden, robokeh, silverjow. Check preview images.</p></li><li><p>Heavily focused on 'bara' body type. Can still gen slim body with the right prompts.</p></li><li><p>Merged with the latest version of WAI for their updated datasets. The weight of the merge is pretty low so the effect might not be that noticeable.</p></li><li><p>Less reliant on quality tags.</p></li><li><p>Other minor adjustments.</p></li></ul>

Files with SHA256: 1cafc1538bf26bc3466e1b8f47ead1068013ef0cca95349f30448dd98f1b38df