Alpha V17 Release

017.0/Anima-512/aidl-v017-anima-512.cm-info.json

@@ -0,0 +1,41 @@
+{
+  "ModelName": "[Anima] AIDL: OmoAIshi",
+  "ModelDescription": "OmoAIshi is the most comprehensive multi-concept LyCORIS for diaper wearing and using, able to comprehend multiple concepts previously unfulfilled by base models and other LoRAs. LyCORIS LoCon is used instead of the regular LoRA format as it allows multiple concepts to be trained within the same model. No more girls in panties! \n\nThis LoRA violates CivitAI\\u0027s terms of service (their TOS does not allow diapers nor scat). Do not upload generations from AIDL onto CivitAI.",
+  "Nsfw": true,
+  "Tags": [
+    "diaper",
+    "abdl",
+    "omorashi",
+    "scat"
+  ],
+  "ModelType": "LoRA",
+  "VersionId": 0,
+  "VersionName": "v017",
+  "VersionDescription": null,
+  "BaseModel": "Anima",
+  "FileMetadata": {
+    "fp": null,
+    "size": null,
+    "format": "SafeTensor"
+  },
+  "ImportedAt": "2024-12-12T07:27:13.2830617+00:00",
+  "Hashes": {
+    "SHA256": "thisisnotahash",
+    "CRC32": "thisisnotahash",
+    "BLAKE3": "thisisnotahash"
+  },
+  "TrainedWords": [
+    "diaper",
+    "peed diaper",
+    "poopy diaper",
+    "pull-ups",
+    "peed pull-ups",
+    "pooping self",
+    "poopy underwear",
+    "poopy shorts",
+    "poopy pants",
+    "open diaper"
+  ],
+  "UserTitle": null,
+  "ThumbnailImageUrl": "aidl-v017-anima-512.preview.png"
+}

017.0/Anima-512/aidl-v017-anima-512.metadata.json

@@ -0,0 +1,62 @@
+{
+  "file_name": "aidl-v017-anima-512",
+  "model_name": "[Anima] AIDL: OmoAIshi V017",
+  "file_path": "/home/pops/AI/ComfyUI/models/loras/Own/aidl/aidl-v017-anima-512.safetensors",
+  "size": 573178152,
+  "modified": 1770669474.206853,
+  "sha256": "baf074fe0c09963a68706772329e63c6f2fd4748698d8b8fde521ecf92a16a6e",
+  "base_model": "Anima",
+  "preview_url": "/home/pops/AI/ComfyUI/models/loras/Own/aidl/aidl-v017-anima-512.preview.png",
+  "preview_nsfw_level": 16,
+  "notes": "",
+  "from_civitai": false,
+  "civitai": {
+    "name": "V17 - Anima",
+    "description": "<style>  .main-div {    background-color: #9999ff; padding: 20px; border-radius: 10px; margin-bottom: 20px;  }  h1 {    color: #24292e;    margin-top: 0;    font-size: 25px;  }  h2 {    color: #24292e;    margin-top: 0;    font-size: 22px;  }  h3 {    color: #24292e;    margin-top: 0;    font-size: 20px;  }  h4 {    color: #24292e;    margin-top: 0;    font-size: 15px;  }  p {    color:#24292e;  }  a {    color: #0366d6;    text-decoration: none;  }  .section-div {    background-color: white;    padding: 15px;    border-radius: 8px;    margin: 15px 0;    box-shadow: 0 2px 4px rgba(0,0,0,0.1);  }  .subsection-div {    background-color: #bbb;    padding: 15px;    border-radius: 8px;    margin: 15px 0;    box-shadow: 0 2px 4px rgba(0,0,0,0.1);  }  ul {    margin-bottom: 0;    color: #24292e;  }  ol {    margin-bottom: 0;    color: #24292e;  }  td {    margin-bottom: 0;    color: #24292e;  }  code {    background-color: #333;    padding: 3px 6px;    border-radius: 4px;  }  table {    color: #24292e;  }</style><div class=\"main-div\">    <h1>AIDL: OmoAIShi Changelog</h1>    <div class=\"section-div\">        <h2>V16: Tag Restructure Edition</h2>        <p>Welcome to V16! Refined tags, another new customizable diaper element, and the new Neta Lumina architecture brings AIDL to the world of Diffusion Transformers. While the Lumina variant is the standout variant of AIDL, the SDXL variants can still hold its weight well. With the Gemma 2 2B TE that Neta Lumina has, such concepts like <code>covered diaper</code> are possible without having any images of that concept, as well as the ability for natural language to be used.</p>        <p>Wetness indicators are now tagged to help stop the wetness indicators from appearing during pantypooping. You can also go and set up the wetness indicators to any color the model recognizes. The most trained colors are yellow and blue, which are common colors used for diaper wetness indicators, but if you use Neta Lumina, you can also set it to any color it knows.</p>        <ul>        <li>Added handmade natural language captions to <code>diaper</code> and <code>peed diaper</code> concepts images in the dataset.</li>            <ul>                <li>The <code>diaper</code> and <code>peed diaper</code> concepts are hand captioned.</li>                <li>Other images and newer images will use a combination of three VLMs summarized into one caption with tag grounding: JoyCaption Beta 1, MiMo Vision 7B, and Gemma 3 27B. This will be done on V17.</li>                <li>This is to ensure that this LoRA is easily usable on models such as ~~SD3.5~~ Neta Lumina and any other future natural language models.</li>            </ul>        <li>Added artist tags to all identifiable artworks due to an accidental discovery where AIDL also learned artist styles whn there was enough data.</li>        <li>Added new diaper design: <code>merries</code><li>        <li>Tagged <code>wetness indicator</code>s as an attempt to separate wetness indicators from soiling (apparent when doing panty pees/poops).</li>        <li>Redone prints and made sure to catch as many prints as possible, including the use of <code>polka dot diaper</code>, <code>orientation indicator</code>, <code>size indicator</code></li>        <li>Added LoRA Manager metadata</li>        </ul>    </div></div>",
+    "trainedWords": [
+      "diaper",
+      "peed diaper",
+      "poopy diaper",
+      "pull-ups",
+      "peed pull-ups",
+      "pooping self",
+      "poopy underwear",
+      "poopy shorts",
+      "poopy pants",
+      "open diaper",
+      "covered diaper",
+      "diaper peek",
+      "@cakies22, oekaki",
+      "@omulettes",
+      "@mizusoba",
+      "@mogurin",
+      "@kyoju",
+      "@dia75",
+      "@bunnymim",
+      "@gogo \\(201177\\)",
+      "@ararii",
+      "@tokiha \\(ruinluin\\)",
+      "@azure_sunset4",
+      "@shibachaya",
+      "@alkali",
+      "@road again",
+      "@hc68o33",
+      "@stolas \\(lemegeton\\)"
+    ],
+    "customImages": []
+  },
+  "tags": [
+    "diaper",
+    "abdl",
+    "omorashi",
+    "scat"
+  ],
+  "modelDescription": "<style>  .main-div {    background-color: #9999ff; padding: 20px; border-radius: 10px; margin-bottom: 20px;  }  h1 {    color: #24292e;    margin-top: 0;    font-size: 25px;  }  h2 {    color: #24292e;    margin-top: 0;    font-size: 22px;  }  h3 {    color: #24292e;    margin-top: 0;    font-size: 20px;  }  h4 {    color: #24292e;    margin-top: 0;    font-size: 15px;  }  p {    color:#24292e;  }  a {    color: #0366d6;    text-decoration: none;  }  .section-div {    background-color: white;    padding: 15px;    border-radius: 8px;    margin: 15px 0;    box-shadow: 0 2px 4px rgba(0,0,0,0.1);  }  .subsection-div {    background-color: #bbb;    padding: 15px;    border-radius: 8px;    margin: 15px 0;    box-shadow: 0 2px 4px rgba(0,0,0,0.1);  }  ul {    margin-bottom: 0;    color: #24292e;  }  ol {    margin-bottom: 0;    color: #24292e;  }  td {    margin-bottom: 0;    color: #24292e;  }  code {    background-color: #333;    padding: 3px 6px;    border-radius: 4px;  }  table {    color: #24292e;  }</style><div class=\"main-div\">  <h1>AIDL: OmoAIShi</h1>  <div style=\"background-color: #ffff99; padding: 20px; border-radius: 10px; margin-bottom: 20px;\">  <img src=\"docs/Images/v16-thumb.png\">  <h3>V16: Tag Restructure Edition<br>For Lumina 2, Illustrious 2, NoobAI VPred</h3>  <div style=\"background-color: #ff9999; padding: 20px; border-radius: 10px; margin-bottom: 20px;\">  <h3>This model is designed for **NSFW** purposes, trained and tested on DRAWN CHARACTERS ONLY.</h3>  <h3>PUBLIC ALPHA. GENERATIONS DO NOT REPRESENT THE FINAL MODEL.</h3>  </div>    <a href=\"https://gitgud.io/mrpopsalot/aidl-omoaishi\"><img alt=\"Static Badge\" src=\"https://img.shields.io/badge/GitLab-orange?logo=gitlab&logoColor=white&style=for-the-badge\"></a>    <a href=\"https://huggingface.co/mrpopsalot/aidl-omoaishi\"><img alt=\"Static Badge\" src=\"https://img.shields.io/badge/HuggingFace-yellow?logo=huggingface&logoColor=white&style=for-the-badge\"></a>    <a href=\"https://allthefallen.moe/forum/index.php?resources/aidl-omoaishi.7465/\"><img alt=\"Static Badge\" src=\"https://img.shields.io/badge/AllTheFallen-pink?logo=outlook&logoColor=white&style=for-the-badge\"></a>    <img alt=\"GitLab License\" src=\"https://img.shields.io/gitlab/license/mrpopsalot%2Faidl-omoaishi?gitlab_url=http%3A%2F%2Fgitgud.io&style=for-the-badge\">  </div>  <div class=\"section-div\">    <h2>Overview</h2>    <p>OmoAIshi is the most comprehensive multi-concept LoRA for diaper wearing and using, able to comprehend multiple concepts previously unfulfilled by base models and other LoRAs. LyCORIS LoCon is used instead of the regular LoRA format as it allows multiple concepts to be trained within the same model. No more girls in panties!</p>    <ul>      <li><b>Trained Models:</b></li>      <ul>        <li><b>NoobAI-XL VPred:</b> Laxhar/noobai-XL-Vpred-1.0 @ 1024</li>        <li><b>Illustrious 2:</b> OnomaAIResearch/Illustrious-XL-v2.0 @ 1536</li>          <ul>          <li>Also works on 1024px, as well on Illustrious 1, 0.1, and NoobAI EPS</li>          </ul>        <li><b>Lumina Image 2:</b> neta-art/neta-lumina 1.0 @ 1024</li>      </ul>      <li><b>Developed by:</b> Mr Pops Alot</li>      <li><b>Model type:</b> LyCORIS, Full Preset (LoRA for Lumina 2)</li>      <li><b>License:</b> Apache 2.0</li>    </ul><br>    <p>This is the first LoRA of the AIDL series. <b>AIDL: The AI Diaper LyCORIS</b> is intended to a series of LoRAs that teaches models about diapers and other ABDL related concepts.</p>  </div>  <div class=\"section-div\">    <h2>Showcase</h2>    <p><img src=\"docs/Images/EasyGrid_00001_.png\"></p>  </div>  <div class=\"section-div\">    <h2>Features</h2>    <ul>      <li><b>Tape-on diapers:</b> Two and four taped, printed and plain diapers are supported. Diapers from specific brands and designs are also trained when noticed. Note that these are not fully trained and may not be fully accurate.</li>      <li><b>Pull-up diapers:</b> Pull-ups are also trained and can be prompted in various designs.</li>      <li><b>Peed diapers:</b> Wet diapers of various stages, from slightly wet to completely leaking. Speaking of leaks, they now correctly go at the side of the thighs.</li>      <li><b>Diaper and panty pooping:</b> Soiling of various stages, including blowouts have also been trained, as with double pee and poo soiling as well. Pants, shorts, and dress pooping is also covered. Compatibility is not guaranteed (there is less training data). You may see some exposed scat.</li>      <li><b>Open diapers:</b> Open diapers are now possible to do, complete with wetness and mess in the pads if prompted.</li>      <li><b>Consistent results across different character positions:</b> This model has been trained on a variety of styles and poses, ensuring correct generation on many poses and whatever artstyle you want to use, including standing, squatting, lying down, from below upskirts, and more</li>    </ul>  </div>  <div class=\"section-div\">    <h2>How to Use</h2>    <div class=\"subsection-div\">      <h3>Diapers</h3>      <p>Use the general term: <code>diaper</code>, or <code>in a diaper</code>.</p>      <ul>      <li>You can also specify the tape count using <code>two taped</code>, or <code>four taped</code>.</li>      <li>Prompting <code>plain diaper</code> will get you a diaper with no designs, while <code>print diaper</code> will get you a printed diaper.</li>      <li><code>front-print diaper</code> and <code>back-print diaper</code> can also be used to get you a print on the front or back. Use <a href=\"https://danbooru.donmai.us/tags?commit=Search&search%5Bhide_empty%5D=yes&search%5Bname_or_alias_matches%5D=%2A_print&search%5Border%5D=count\">Danbooru's list of prints</a>.</li>      <li>Add in wetness indicators by prompting <code>yellow wetness indicator</code> or <code>blue wetness indicator</code>.</li>      </ul>      <p>Specific diaper styles:</p>      <ul>        <li><code>pampers</code></li>        <li><code>huggies</code></li>        <li><code>luvs</code></li>        <li><code>abuniverse</code></li>        <li><code>merries</code></li>      </ul>    </div>    <div class=\"subsection-div\">      <h3>Pull-Ups</h3>      <p>Use <code>pull-ups</code>. Same prompting style as with diapers, but replace <code>diaper</code> with <code>pull-ups</code>.</p>    </div>    <div class=\"subsection-div\">      <h3>Diaper Soiling</h3>      <p><b>Peed-in diapers:</b> Use the general <code>peed diaper</code> tag to get wet diapers. From there, you can also go and set how soiled the diaper should be. Without it, you might get unexpected diaper blowouts.</p>      <ol>        <li><code>wet diaper</code></li>        <li><code>soaked diaper</code></li>        <li><code>drenched diaper</code></li>        <li><code>leaking diaper</code>, <code>pee on legs</code></li>      </ol>      <br>      <p><b>Poopy diapers:</b> Use the general <code>poopy diaper</code> tag to get messy diapers. From there, you can also go and set how soiled the diaper should be. Without it, you might get unexpected diaper blowouts.</p>      <ol>        <li><code>messy diaper</code></li>        <li><code>packed diaper</code></li>        <li><code>loaded diaper</code></li>        <li><code>diaper blowout</code>, <code>poop on legs</code></li>      </ol>      <br>      <p><code>smell</code> can also be added to your prompt to give off that soiled smell effect.</p>      <p>If you want more soiled diapers, you can increase the weight of the tag to suit your needs. Tags works well between 0.9-1.5 weight.</p>      <img src=\"docs/Images/unidesSoil_00002_.png\">      <img src=\"docs/Images/unidesSoil_00004_.png\">    </div>    <div class=\"subsection-div\">      <h3>Pantypooping</h3>      <p>Use the term <code>pooping self</code>. You can also use the terms <code>poopy underwear</code> or <code>poopy clothes</code> to have either their underwear be soiled or their lower clothes (like their dress or pants) to be soiled.      </p>      <img src=\"docs/Images/unidesSoil_00005_.png\">      <p>Multiple underwear types supported!</p>      <p>For diapers please use the poopy diaper tag. Pooping self can also work but poopy diaper is the recommended tag for diaper pooping.</p>    </div>    <div class=\"subsection-div\">      <h3>Open Diapers</h3>      <p>Use the term <code>open diaper</code> to get open diapers.</p>      <ul>        <li>Add in <code>peed diaper</code> and <code>poopy diaper</code> respectively if you want the diaper to be wet and messy.</li>        <li>As well, add your respective genitals such as <code>pussy</code> or <code>penis</code> and the uncensored tag</li>      </ul>      <img src=\"docs/Images/openDiaper_00000_.png\">    </div>  </div>  <div class=\"section-div\">    <h2>Bias, Risks, and Limitations</h2>    <p>The model currently struggles with the following concepts:</p>    <ul>      <li>Non-printed and colored pull-ups</li>      <li>Open diapers</li>      <ul>        <li>Open diapers do not have as much data as other concepts, and will struggle to have proper diaper structure.</li>      </ul>      <li>Unworn diapers (both clean and used)</li>      <li>Clothespooping</li>      <li>Technical positions such as falling</li>    </ul>    <br>    <p>As well, there may be some limitations with this LoRA:</p>    <ul>      <li>Panty poops may happen unprompted if <code>smell</code> is prompted</li>      <li>Peed diapers may have poopy diaper bulges unless poopy diaper is put in the negatives</li>      <li>There is currently no training data for poopy pull-ups, and is using the fallback pantypooping data.</li>      <li>Poopy diapers may have unprompted blowouts.</li>      <li>In the Lumina 2 LoRA, you need to prompt for \"wet diaper\" as well with \"peed diaper\" to get a pee soaked pad.</li>      <li>Although you can use Rouwei Gemma in the SDXL variants, you'll only get pull-ups</li>    </ul>  <p>Increase the strength of the LoRA if needed to achieve your desired results.</p>  <div style=\"background-color: #ff9999; padding: 20px; border-radius: 10px; margin-bottom: 20px;\">    <p> I am in no way responsible for any content that the user creates with malicious intent while using any of these models. The user assumes complete responsibility for the misuse of these tools and any unethical content created with them. <b>Follow all local, state, and federal laws as well as online rules regarding this content and generations with this LoRA. I am not responsible if you are arrested or banned from an online service for using this.</b></p>    <p><b>This LoRA violates CivitAI's terms of service (their TOS does not allow diapers nor scat). Do not upload generations from AIDL onto CivitAI.</b></p>  </div>  </div>  <div class=\"section-div\">    <h2>Training Details</h2>    <p>Over 1000 images have been used in the dataset. Images used are <b>exclusively drawn 2D</b> art.</p>    <p><b>No synthetic data has been used</b> for the model. Tagging (Danbooru tag style) is <b>all manually done</b>, as automatic taggers do not recognize the concept in question well. Image captioning (NL support) uses a list of manual captioned images and (planned for V17) JoyCaption Beta 1 and Gemma 3 27B outputs with manual Tag grounding.</p>    <div class=\"subsection-div\">      <h3>Training Procedure</h3>      <p>Training configs are provided with the weights, but as a TL;DR:</p>      <h4>SDXL-based (Illustrious, NoobAI)</h4>      <ul>        <li>Program: 67372a's Kohya Easy Scripts</li>        <li>Optimizer: CAME</li>        <li>Scheduler: Rex</li>        <li>UNet LR: 3e-4</li>        <li>LoRA type: LoCon</li>        <li>Steps: 36600</li>        <li>Network Rank (Dim/Alpha): 64/1</li>        <li>Precision: Full BF16</li>        <li>Hardware: 1x RTX 3090 24GB</li>      </ul>      <h4>Lumina 2</h4>      <ul>        <li>Program: Kohya sd-scripts SD3 branch</li>        <li>Optimizer: CAME</li>        <li>Scheduler: Rex</li>        <li>DiT LR: 1e-4</li>        <li>TE LR: None. TE outputs are cached</li>        <li>LoRA type: LoRA Lumina</li>        <ul>          <li>No LoCon needed as they'res no Conv layers.</li>        </ul>        <li>Steps: 36600 (batch 4)</li>        <li>Network Rank (Dim/Alpha): 64/32</li>        <li>Precision: Full BF16</li>        <li>Hardware: 1x RTX 3090 24GB</li>      </ul>    </div>  </div>  <div class=\"section-div\">    <h2>FAQ</h2>    <ul>      <li><b>Will this model be ported to X?</b> This model is planned to have versions trained on NoobAI-XL VPred, Illustrious 2.0 (ILXL2), and Neta Lumina (Lumina 2). More models will come later.      <ul>        <li>Lumina 2 version only works on Neta Lumina AES paths, such as a5nA and 1.0</li>        <li>The Illustrious 2 version works on Illustrious 1, 0.1, and NoobAI-XL Epsilon Pred.</li>        <li>V17 will have a Wan 2.2 5B</li>        <li>No Pony version is planned. Move to NoobXL or ILXL.</li>      </ul></li>      <li><b>Will there be a version for CivitAI?</b> No. I do not trust CivitAI anymore after the release of Illustrious 1.0 and them allowing closed-weight models, not to mention the overbearing censorship against messy diaper content, bad service, and overall greed.      <ul>        <li>V15.1 Update: Definitely not, especially since urine and diaper content have been expressly banned. Oh, and half the time the site crashes when you try to do anything. Good riddance.</li>      </ul></li>      <li><b>Anything else planned?</b>        <ul>          <li>Diaper changes</li>          <li>Open diapers and pull-ups</li>          <li>Diaper covers</li>          <li>Diaper pulls (like panty pulls)</li>          <li>Clean and used unworn diapers</li>          <li>Cloth diapers</li>          <li>Diaper pulls</li>          <li>The rest of the data in my dataset processed and tagged.</li>          <li>Etc.</li>        </ul>      </li>      <ul>    </ul>  </div>  <div class=\"section-div\">    <h2>License</h2>    <p>This LoRA model is provided under the <a href=\"https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md\">Apache License 2.0</a> license.</p>    <!-- <p>Training configurations and dataset will also be released later. You can use these to further train AIDL.</p> -->  </div>  <div class=\"section-div\">    <h2>Special Thanks</h2>    <ul>      <li>DangoKnight for training some of the test versions of this LoRA</li>      <li>Yatogami for contributing to the dataset.</li>      <li>Hugs288, Lopi99, and others in the NoobAI discord to for helping me get my LoRA training settings right.</li>    </ul>  </div>  <div class=\"section-div\">    <h2>Model Card Contact</h2>    <ul>      <p>I can be contacted on:</p>      <li><b>Matrix:</b> @mr_pops_alot:cutefunny.art</li>      <li><b>GitLab:</b> gitgud.io/mrpopsalot</li>      <li><b>All The Fallen:</b> @MrDoesNothingAlot</li>      <li><b>Discord:</b> 474149843724664854</li>    </ul>  </div></div>",
+  "civitai_deleted": false,
+  "favorite": true,
+  "exclude": false,
+  "db_checked": false,
+  "metadata_source": null,
+  "last_checked_at": 0,
+  "usage_tips": "{\"strength\":1}"
+}

017.0/Anima-512/aidl-v017-anima-512.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d00edaa6e61d7d3cf3d59fd757b53fc857f100f558f8fe9b2696b2fcc6bead5b
+size 243050846

017.0/Chenkin-RF-1024/aidl-v017-chenkin-rf-1024.cm-info.json

@@ -0,0 +1,41 @@
+{
+  "ModelName": "[Chenkin RF] AIDL: OmoAIshi",
+  "ModelDescription": "OmoAIshi is the most comprehensive multi-concept LyCORIS for diaper wearing and using, able to comprehend multiple concepts previously unfulfilled by base models and other LoRAs. LyCORIS LoCon is used instead of the regular LoRA format as it allows multiple concepts to be trained within the same model. No more girls in panties! \n\nThis LoRA violates CivitAI\\u0027s terms of service (their TOS does not allow diapers nor scat). Do not upload generations from AIDL onto CivitAI.",
+  "Nsfw": true,
+  "Tags": [
+    "diaper",
+    "abdl",
+    "omorashi",
+    "scat"
+  ],
+  "ModelType": "LoCon",
+  "VersionId": 0,
+  "VersionName": "v017",
+  "VersionDescription": null,
+  "BaseModel": "Other",
+  "FileMetadata": {
+    "fp": null,
+    "size": null,
+    "format": "SafeTensor"
+  },
+  "ImportedAt": "2024-12-12T07:27:13.2830617+00:00",
+  "Hashes": {
+    "SHA256": "thisisnotahash",
+    "CRC32": "thisisnotahash",
+    "BLAKE3": "thisisnotahash"
+  },
+  "TrainedWords": [
+    "diaper",
+    "peed diaper",
+    "poopy diaper",
+    "pull-ups",
+    "peed pull-ups",
+    "pooping self",
+    "poopy underwear",
+    "poopy shorts",
+    "poopy pants",
+    "open diaper"
+  ],
+  "UserTitle": null,
+  "ThumbnailImageUrl": "/opt/stabilitymatrix/Data/Models/Lora/OWN/aidl-v015-1-illustrious2-1536.preview.png"
+}

017.0/Chenkin-RF-1024/aidl-v017-chenkin-rf-1024.metadata.json

@@ -0,0 +1,62 @@
+{
+  "file_name": "aidl-v017-noobai-rf-1024",
+  "model_name": "[Chenkin RF] AIDL: OmoAIshi V017",
+  "file_path": "/home/pops/AI/ComfyUI/models/loras/Own/aidl/aidl-v017-noobai-rf-1024.safetensors",
+  "size": 509995232,
+  "modified": 1767142313.522548,
+  "sha256": "cbb06d67f38a4ee65bc20523f3514ddd8325c444a3424a2f2cebbe1811b70972",
+  "base_model": "Other",
+  "preview_url": "/home/pops/AI/ComfyUI/models/loras/Own/aidl/aidl-v017-noobai-rf-1024.preview.png",
+  "preview_nsfw_level": 16,
+  "notes": "",
+  "from_civitai": false,
+  "civitai": {
+    "name": "V17 - Chenkin RF",
+    "description": "<style>  .main-div {    background-color: #9999ff; padding: 20px; border-radius: 10px; margin-bottom: 20px;  }  h1 {    color: #24292e;    margin-top: 0;    font-size: 25px;  }  h2 {    color: #24292e;    margin-top: 0;    font-size: 22px;  }  h3 {    color: #24292e;    margin-top: 0;    font-size: 20px;  }  h4 {    color: #24292e;    margin-top: 0;    font-size: 15px;  }  p {    color:#24292e;  }  a {    color: #0366d6;    text-decoration: none;  }  .section-div {    background-color: white;    padding: 15px;    border-radius: 8px;    margin: 15px 0;    box-shadow: 0 2px 4px rgba(0,0,0,0.1);  }  .subsection-div {    background-color: #bbb;    padding: 15px;    border-radius: 8px;    margin: 15px 0;    box-shadow: 0 2px 4px rgba(0,0,0,0.1);  }  ul {    margin-bottom: 0;    color: #24292e;  }  ol {    margin-bottom: 0;    color: #24292e;  }  td {    margin-bottom: 0;    color: #24292e;  }  code {    background-color: #333;    padding: 3px 6px;    border-radius: 4px;  }  table {    color: #24292e;  }</style><div class=\"main-div\">    <h1>AIDL: OmoAIShi Changelog</h1>    <div class=\"section-div\">        <h2>V16: Tag Restructure Edition</h2>        <p>Welcome to V16! Refined tags, another new customizable diaper element, and the new Neta Lumina architecture brings AIDL to the world of Diffusion Transformers. While the Lumina variant is the standout variant of AIDL, the SDXL variants can still hold its weight well. With the Gemma 2 2B TE that Neta Lumina has, such concepts like <code>covered diaper</code> are possible without having any images of that concept, as well as the ability for natural language to be used.</p>        <p>Wetness indicators are now tagged to help stop the wetness indicators from appearing during pantypooping. You can also go and set up the wetness indicators to any color the model recognizes. The most trained colors are yellow and blue, which are common colors used for diaper wetness indicators, but if you use Neta Lumina, you can also set it to any color it knows.</p>        <ul>        <li>Added handmade natural language captions to <code>diaper</code> and <code>peed diaper</code> concepts images in the dataset.</li>            <ul>                <li>The <code>diaper</code> and <code>peed diaper</code> concepts are hand captioned.</li>                <li>Other images and newer images will use a combination of three VLMs summarized into one caption with tag grounding: JoyCaption Beta 1, MiMo Vision 7B, and Gemma 3 27B. This will be done on V17.</li>                <li>This is to ensure that this LoRA is easily usable on models such as ~~SD3.5~~ Neta Lumina and any other future natural language models.</li>            </ul>        <li>Added artist tags to all identifiable artworks due to an accidental discovery where AIDL also learned artist styles whn there was enough data.</li>        <li>Added new diaper design: <code>merries</code><li>        <li>Tagged <code>wetness indicator</code>s as an attempt to separate wetness indicators from soiling (apparent when doing panty pees/poops).</li>        <li>Redone prints and made sure to catch as many prints as possible, including the use of <code>polka dot diaper</code>, <code>orientation indicator</code>, <code>size indicator</code></li>        <li>Added LoRA Manager metadata</li>        </ul>    </div></div>",
+    "trainedWords": [
+      "diaper",
+      "peed diaper",
+      "poopy diaper",
+      "pull-ups",
+      "peed pull-ups",
+      "pooping self",
+      "poopy underwear",
+      "poopy shorts",
+      "poopy pants",
+      "open diaper",
+      "covered diaper",
+      "diaper peek",
+      "@cakies22, oekaki",
+      "@omulettes",
+      "@mizusoba",
+      "@mogurin",
+      "@kyoju",
+      "@dia75",
+      "@bunnymim",
+      "@gogo \\(201177\\)",
+      "@ararii",
+      "@tokiha \\(ruinluin\\)",
+      "@azure_sunset4",
+      "@shibachaya",
+      "@alkali",
+      "@road again",
+      "@hc68o33",
+      "@stolas \\(lemegeton\\)"
+    ],
+    "customImages": []
+  },
+  "tags": [
+    "diaper",
+    "abdl",
+    "omorashi",
+    "scat"
+  ],
+  "modelDescription": "<style>  .main-div {    background-color: #9999ff; padding: 20px; border-radius: 10px; margin-bottom: 20px;  }  h1 {    color: #24292e;    margin-top: 0;    font-size: 25px;  }  h2 {    color: #24292e;    margin-top: 0;    font-size: 22px;  }  h3 {    color: #24292e;    margin-top: 0;    font-size: 20px;  }  h4 {    color: #24292e;    margin-top: 0;    font-size: 15px;  }  p {    color:#24292e;  }  a {    color: #0366d6;    text-decoration: none;  }  .section-div {    background-color: white;    padding: 15px;    border-radius: 8px;    margin: 15px 0;    box-shadow: 0 2px 4px rgba(0,0,0,0.1);  }  .subsection-div {    background-color: #bbb;    padding: 15px;    border-radius: 8px;    margin: 15px 0;    box-shadow: 0 2px 4px rgba(0,0,0,0.1);  }  ul {    margin-bottom: 0;    color: #24292e;  }  ol {    margin-bottom: 0;    color: #24292e;  }  td {    margin-bottom: 0;    color: #24292e;  }  code {    background-color: #333;    padding: 3px 6px;    border-radius: 4px;  }  table {    color: #24292e;  }</style><div class=\"main-div\">  <h1>AIDL: OmoAIShi</h1>  <div style=\"background-color: #ffff99; padding: 20px; border-radius: 10px; margin-bottom: 20px;\">  <img src=\"docs/Images/v16-thumb.png\">  <h3>V16: Tag Restructure Edition<br>For Lumina 2, Illustrious 2, NoobAI VPred</h3>  <div style=\"background-color: #ff9999; padding: 20px; border-radius: 10px; margin-bottom: 20px;\">  <h3>This model is designed for **NSFW** purposes, trained and tested on DRAWN CHARACTERS ONLY.</h3>  <h3>PUBLIC ALPHA. GENERATIONS DO NOT REPRESENT THE FINAL MODEL.</h3>  </div>    <a href=\"https://gitgud.io/mrpopsalot/aidl-omoaishi\"><img alt=\"Static Badge\" src=\"https://img.shields.io/badge/GitLab-orange?logo=gitlab&logoColor=white&style=for-the-badge\"></a>    <a href=\"https://huggingface.co/mrpopsalot/aidl-omoaishi\"><img alt=\"Static Badge\" src=\"https://img.shields.io/badge/HuggingFace-yellow?logo=huggingface&logoColor=white&style=for-the-badge\"></a>    <a href=\"https://allthefallen.moe/forum/index.php?resources/aidl-omoaishi.7465/\"><img alt=\"Static Badge\" src=\"https://img.shields.io/badge/AllTheFallen-pink?logo=outlook&logoColor=white&style=for-the-badge\"></a>    <img alt=\"GitLab License\" src=\"https://img.shields.io/gitlab/license/mrpopsalot%2Faidl-omoaishi?gitlab_url=http%3A%2F%2Fgitgud.io&style=for-the-badge\">  </div>  <div class=\"section-div\">    <h2>Overview</h2>    <p>OmoAIshi is the most comprehensive multi-concept LoRA for diaper wearing and using, able to comprehend multiple concepts previously unfulfilled by base models and other LoRAs. LyCORIS LoCon is used instead of the regular LoRA format as it allows multiple concepts to be trained within the same model. No more girls in panties!</p>    <ul>      <li><b>Trained Models:</b></li>      <ul>        <li><b>NoobAI-XL VPred:</b> Laxhar/noobai-XL-Vpred-1.0 @ 1024</li>        <li><b>Illustrious 2:</b> OnomaAIResearch/Illustrious-XL-v2.0 @ 1536</li>          <ul>          <li>Also works on 1024px, as well on Illustrious 1, 0.1, and NoobAI EPS</li>          </ul>        <li><b>Lumina Image 2:</b> neta-art/neta-lumina 1.0 @ 1024</li>      </ul>      <li><b>Developed by:</b> Mr Pops Alot</li>      <li><b>Model type:</b> LyCORIS, Full Preset (LoRA for Lumina 2)</li>      <li><b>License:</b> Apache 2.0</li>    </ul><br>    <p>This is the first LoRA of the AIDL series. <b>AIDL: The AI Diaper LyCORIS</b> is intended to a series of LoRAs that teaches models about diapers and other ABDL related concepts.</p>  </div>  <div class=\"section-div\">    <h2>Showcase</h2>    <p><img src=\"docs/Images/EasyGrid_00001_.png\"></p>  </div>  <div class=\"section-div\">    <h2>Features</h2>    <ul>      <li><b>Tape-on diapers:</b> Two and four taped, printed and plain diapers are supported. Diapers from specific brands and designs are also trained when noticed. Note that these are not fully trained and may not be fully accurate.</li>      <li><b>Pull-up diapers:</b> Pull-ups are also trained and can be prompted in various designs.</li>      <li><b>Peed diapers:</b> Wet diapers of various stages, from slightly wet to completely leaking. Speaking of leaks, they now correctly go at the side of the thighs.</li>      <li><b>Diaper and panty pooping:</b> Soiling of various stages, including blowouts have also been trained, as with double pee and poo soiling as well. Pants, shorts, and dress pooping is also covered. Compatibility is not guaranteed (there is less training data). You may see some exposed scat.</li>      <li><b>Open diapers:</b> Open diapers are now possible to do, complete with wetness and mess in the pads if prompted.</li>      <li><b>Consistent results across different character positions:</b> This model has been trained on a variety of styles and poses, ensuring correct generation on many poses and whatever artstyle you want to use, including standing, squatting, lying down, from below upskirts, and more</li>    </ul>  </div>  <div class=\"section-div\">    <h2>How to Use</h2>    <div class=\"subsection-div\">      <h3>Diapers</h3>      <p>Use the general term: <code>diaper</code>, or <code>in a diaper</code>.</p>      <ul>      <li>You can also specify the tape count using <code>two taped</code>, or <code>four taped</code>.</li>      <li>Prompting <code>plain diaper</code> will get you a diaper with no designs, while <code>print diaper</code> will get you a printed diaper.</li>      <li><code>front-print diaper</code> and <code>back-print diaper</code> can also be used to get you a print on the front or back. Use <a href=\"https://danbooru.donmai.us/tags?commit=Search&search%5Bhide_empty%5D=yes&search%5Bname_or_alias_matches%5D=%2A_print&search%5Border%5D=count\">Danbooru's list of prints</a>.</li>      <li>Add in wetness indicators by prompting <code>yellow wetness indicator</code> or <code>blue wetness indicator</code>.</li>      </ul>      <p>Specific diaper styles:</p>      <ul>        <li><code>pampers</code></li>        <li><code>huggies</code></li>        <li><code>luvs</code></li>        <li><code>abuniverse</code></li>        <li><code>merries</code></li>      </ul>    </div>    <div class=\"subsection-div\">      <h3>Pull-Ups</h3>      <p>Use <code>pull-ups</code>. Same prompting style as with diapers, but replace <code>diaper</code> with <code>pull-ups</code>.</p>    </div>    <div class=\"subsection-div\">      <h3>Diaper Soiling</h3>      <p><b>Peed-in diapers:</b> Use the general <code>peed diaper</code> tag to get wet diapers. From there, you can also go and set how soiled the diaper should be. Without it, you might get unexpected diaper blowouts.</p>      <ol>        <li><code>wet diaper</code></li>        <li><code>soaked diaper</code></li>        <li><code>drenched diaper</code></li>        <li><code>leaking diaper</code>, <code>pee on legs</code></li>      </ol>      <br>      <p><b>Poopy diapers:</b> Use the general <code>poopy diaper</code> tag to get messy diapers. From there, you can also go and set how soiled the diaper should be. Without it, you might get unexpected diaper blowouts.</p>      <ol>        <li><code>messy diaper</code></li>        <li><code>packed diaper</code></li>        <li><code>loaded diaper</code></li>        <li><code>diaper blowout</code>, <code>poop on legs</code></li>      </ol>      <br>      <p><code>smell</code> can also be added to your prompt to give off that soiled smell effect.</p>      <p>If you want more soiled diapers, you can increase the weight of the tag to suit your needs. Tags works well between 0.9-1.5 weight.</p>      <img src=\"docs/Images/unidesSoil_00002_.png\">      <img src=\"docs/Images/unidesSoil_00004_.png\">    </div>    <div class=\"subsection-div\">      <h3>Pantypooping</h3>      <p>Use the term <code>pooping self</code>. You can also use the terms <code>poopy underwear</code> or <code>poopy clothes</code> to have either their underwear be soiled or their lower clothes (like their dress or pants) to be soiled.      </p>      <img src=\"docs/Images/unidesSoil_00005_.png\">      <p>Multiple underwear types supported!</p>      <p>For diapers please use the poopy diaper tag. Pooping self can also work but poopy diaper is the recommended tag for diaper pooping.</p>    </div>    <div class=\"subsection-div\">      <h3>Open Diapers</h3>      <p>Use the term <code>open diaper</code> to get open diapers.</p>      <ul>        <li>Add in <code>peed diaper</code> and <code>poopy diaper</code> respectively if you want the diaper to be wet and messy.</li>        <li>As well, add your respective genitals such as <code>pussy</code> or <code>penis</code> and the uncensored tag</li>      </ul>      <img src=\"docs/Images/openDiaper_00000_.png\">    </div>  </div>  <div class=\"section-div\">    <h2>Bias, Risks, and Limitations</h2>    <p>The model currently struggles with the following concepts:</p>    <ul>      <li>Non-printed and colored pull-ups</li>      <li>Open diapers</li>      <ul>        <li>Open diapers do not have as much data as other concepts, and will struggle to have proper diaper structure.</li>      </ul>      <li>Unworn diapers (both clean and used)</li>      <li>Clothespooping</li>      <li>Technical positions such as falling</li>    </ul>    <br>    <p>As well, there may be some limitations with this LoRA:</p>    <ul>      <li>Panty poops may happen unprompted if <code>smell</code> is prompted</li>      <li>Peed diapers may have poopy diaper bulges unless poopy diaper is put in the negatives</li>      <li>There is currently no training data for poopy pull-ups, and is using the fallback pantypooping data.</li>      <li>Poopy diapers may have unprompted blowouts.</li>      <li>In the Lumina 2 LoRA, you need to prompt for \"wet diaper\" as well with \"peed diaper\" to get a pee soaked pad.</li>      <li>Although you can use Rouwei Gemma in the SDXL variants, you'll only get pull-ups</li>    </ul>  <p>Increase the strength of the LoRA if needed to achieve your desired results.</p>  <div style=\"background-color: #ff9999; padding: 20px; border-radius: 10px; margin-bottom: 20px;\">    <p> I am in no way responsible for any content that the user creates with malicious intent while using any of these models. The user assumes complete responsibility for the misuse of these tools and any unethical content created with them. <b>Follow all local, state, and federal laws as well as online rules regarding this content and generations with this LoRA. I am not responsible if you are arrested or banned from an online service for using this.</b></p>    <p><b>This LoRA violates CivitAI's terms of service (their TOS does not allow diapers nor scat). Do not upload generations from AIDL onto CivitAI.</b></p>  </div>  </div>  <div class=\"section-div\">    <h2>Training Details</h2>    <p>Over 1000 images have been used in the dataset. Images used are <b>exclusively drawn 2D</b> art.</p>    <p><b>No synthetic data has been used</b> for the model. Tagging (Danbooru tag style) is <b>all manually done</b>, as automatic taggers do not recognize the concept in question well. Image captioning (NL support) uses a list of manual captioned images and (planned for V17) JoyCaption Beta 1 and Gemma 3 27B outputs with manual Tag grounding.</p>    <div class=\"subsection-div\">      <h3>Training Procedure</h3>      <p>Training configs are provided with the weights, but as a TL;DR:</p>      <h4>SDXL-based (Illustrious, NoobAI)</h4>      <ul>        <li>Program: 67372a's Kohya Easy Scripts</li>        <li>Optimizer: CAME</li>        <li>Scheduler: Rex</li>        <li>UNet LR: 3e-4</li>        <li>LoRA type: LoCon</li>        <li>Steps: 36600</li>        <li>Network Rank (Dim/Alpha): 64/1</li>        <li>Precision: Full BF16</li>        <li>Hardware: 1x RTX 3090 24GB</li>      </ul>      <h4>Lumina 2</h4>      <ul>        <li>Program: Kohya sd-scripts SD3 branch</li>        <li>Optimizer: CAME</li>        <li>Scheduler: Rex</li>        <li>DiT LR: 1e-4</li>        <li>TE LR: None. TE outputs are cached</li>        <li>LoRA type: LoRA Lumina</li>        <ul>          <li>No LoCon needed as they'res no Conv layers.</li>        </ul>        <li>Steps: 36600 (batch 4)</li>        <li>Network Rank (Dim/Alpha): 64/32</li>        <li>Precision: Full BF16</li>        <li>Hardware: 1x RTX 3090 24GB</li>      </ul>    </div>  </div>  <div class=\"section-div\">    <h2>FAQ</h2>    <ul>      <li><b>Will this model be ported to X?</b> This model is planned to have versions trained on NoobAI-XL VPred, Illustrious 2.0 (ILXL2), and Neta Lumina (Lumina 2). More models will come later.      <ul>        <li>Lumina 2 version only works on Neta Lumina AES paths, such as a5nA and 1.0</li>        <li>The Illustrious 2 version works on Illustrious 1, 0.1, and NoobAI-XL Epsilon Pred.</li>        <li>V17 will have a Wan 2.2 5B</li>        <li>No Pony version is planned. Move to NoobXL or ILXL.</li>      </ul></li>      <li><b>Will there be a version for CivitAI?</b> No. I do not trust CivitAI anymore after the release of Illustrious 1.0 and them allowing closed-weight models, not to mention the overbearing censorship against messy diaper content, bad service, and overall greed.      <ul>        <li>V15.1 Update: Definitely not, especially since urine and diaper content have been expressly banned. Oh, and half the time the site crashes when you try to do anything. Good riddance.</li>      </ul></li>      <li><b>Anything else planned?</b>        <ul>          <li>Diaper changes</li>          <li>Open diapers and pull-ups</li>          <li>Diaper covers</li>          <li>Diaper pulls (like panty pulls)</li>          <li>Clean and used unworn diapers</li>          <li>Cloth diapers</li>          <li>Diaper pulls</li>          <li>The rest of the data in my dataset processed and tagged.</li>          <li>Etc.</li>        </ul>      </li>      <ul>    </ul>  </div>  <div class=\"section-div\">    <h2>License</h2>    <p>This LoRA model is provided under the <a href=\"https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md\">Apache License 2.0</a> license.</p>    <!-- <p>Training configurations and dataset will also be released later. You can use these to further train AIDL.</p> -->  </div>  <div class=\"section-div\">    <h2>Special Thanks</h2>    <ul>      <li>DangoKnight for training some of the test versions of this LoRA</li>      <li>Yatogami for contributing to the dataset.</li>      <li>Hugs288, Lopi99, and others in the NoobAI discord to for helping me get my LoRA training settings right.</li>    </ul>  </div>  <div class=\"section-div\">    <h2>Model Card Contact</h2>    <ul>      <p>I can be contacted on:</p>      <li><b>Matrix:</b> @mr_pops_alot:cutefunny.art</li>      <li><b>GitLab:</b> gitgud.io/mrpopsalot</li>      <li><b>All The Fallen:</b> @MrDoesNothingAlot</li>      <li><b>Discord:</b> 474149843724664854</li>    </ul>  </div></div>",
+  "civitai_deleted": false,
+  "favorite": true,
+  "exclude": false,
+  "db_checked": false,
+  "metadata_source": null,
+  "last_checked_at": 0,
+  "usage_tips": "{\"strength\":1}"
+}

017.0/Chenkin-RF-1024/aidl-v017-chenkin-rf-1024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f30adf2bf2ab16a19360cee57bc5335034e81cca11d9af34c0480e679a10f243
+size 509994568

017.0/Illustrious2-1024/aidl-v017-illustrious2-1024.cm-info.json

@@ -0,0 +1,41 @@
+{
+  "ModelName": "[ILXL2] AIDL: OmoAIshi",
+  "ModelDescription": "OmoAIshi is the most comprehensive multi-concept LyCORIS for diaper wearing and using, able to comprehend multiple concepts previously unfulfilled by base models and other LoRAs. LyCORIS LoCon is used instead of the regular LoRA format as it allows multiple concepts to be trained within the same model. No more girls in panties! \n\nThis LoRA violates CivitAI\\u0027s terms of service (their TOS does not allow diapers nor scat). Do not upload generations from AIDL onto CivitAI.",
+  "Nsfw": true,
+  "Tags": [
+    "diaper",
+    "abdl",
+    "omorashi",
+    "scat"
+  ],
+  "ModelType": "LoCon",
+  "VersionId": 0,
+  "VersionName": "v017",
+  "VersionDescription": null,
+  "BaseModel": "Illustrious",
+  "FileMetadata": {
+    "fp": null,
+    "size": null,
+    "format": "SafeTensor"
+  },
+  "ImportedAt": "2024-12-12T07:27:13.2830617+00:00",
+  "Hashes": {
+    "SHA256": "thisisnotahash",
+    "CRC32": "thisisnotahash",
+    "BLAKE3": "thisisnotahash"
+  },
+  "TrainedWords": [
+    "diaper",
+    "peed diaper",
+    "poopy diaper",
+    "pull-ups",
+    "peed pull-ups",
+    "pooping self",
+    "poopy underwear",
+    "poopy shorts",
+    "poopy pants",
+    "open diaper"
+  ],
+  "UserTitle": null,
+  "ThumbnailImageUrl": "/opt/stabilitymatrix/Data/Models/Lora/OWN/aidl-v015-1-illustrious2-1536.preview.png"
+}

017.0/Illustrious2-1024/aidl-v017-illustrious2-1024.metadata.json

@@ -0,0 +1,62 @@
+{
+  "file_name": "aidl-v017-illustrious2-1024",
+  "model_name": "[ILXL 2] AIDL: OmoAIshi V017",
+  "file_path": "/home/pops/AI/ComfyUI/models/loras/Own/aidl/aidl-v017-illustrious2-1024.safetensors",
+  "size": 509994560,
+  "modified": 1767655905.12756,
+  "sha256": "49381235ea4dc458b10943ef5fc96908da1b4b54de61dbe730db3f144aeee21c",
+  "base_model": "Illustrious",
+  "preview_url": "/home/pops/AI/ComfyUI/models/loras/Own/aidl/aidl-v017-illustrious2-1024.preview.png",
+  "preview_nsfw_level": 16,
+  "notes": "",
+  "from_civitai": false,
+  "civitai": {
+    "name": "V17 - Illustrious 2",
+    "description": "<style>  .main-div {    background-color: #9999ff; padding: 20px; border-radius: 10px; margin-bottom: 20px;  }  h1 {    color: #24292e;    margin-top: 0;    font-size: 25px;  }  h2 {    color: #24292e;    margin-top: 0;    font-size: 22px;  }  h3 {    color: #24292e;    margin-top: 0;    font-size: 20px;  }  h4 {    color: #24292e;    margin-top: 0;    font-size: 15px;  }  p {    color:#24292e;  }  a {    color: #0366d6;    text-decoration: none;  }  .section-div {    background-color: white;    padding: 15px;    border-radius: 8px;    margin: 15px 0;    box-shadow: 0 2px 4px rgba(0,0,0,0.1);  }  .subsection-div {    background-color: #bbb;    padding: 15px;    border-radius: 8px;    margin: 15px 0;    box-shadow: 0 2px 4px rgba(0,0,0,0.1);  }  ul {    margin-bottom: 0;    color: #24292e;  }  ol {    margin-bottom: 0;    color: #24292e;  }  td {    margin-bottom: 0;    color: #24292e;  }  code {    background-color: #333;    padding: 3px 6px;    border-radius: 4px;  }  table {    color: #24292e;  }</style><div class=\"main-div\">    <h1>AIDL: OmoAIShi Changelog</h1>    <div class=\"section-div\">        <h2>V16: Tag Restructure Edition</h2>        <p>Welcome to V16! Refined tags, another new customizable diaper element, and the new Neta Lumina architecture brings AIDL to the world of Diffusion Transformers. While the Lumina variant is the standout variant of AIDL, the SDXL variants can still hold its weight well. With the Gemma 2 2B TE that Neta Lumina has, such concepts like <code>covered diaper</code> are possible without having any images of that concept, as well as the ability for natural language to be used.</p>        <p>Wetness indicators are now tagged to help stop the wetness indicators from appearing during pantypooping. You can also go and set up the wetness indicators to any color the model recognizes. The most trained colors are yellow and blue, which are common colors used for diaper wetness indicators, but if you use Neta Lumina, you can also set it to any color it knows.</p>        <ul>        <li>Added handmade natural language captions to <code>diaper</code> and <code>peed diaper</code> concepts images in the dataset.</li>            <ul>                <li>The <code>diaper</code> and <code>peed diaper</code> concepts are hand captioned.</li>                <li>Other images and newer images will use a combination of three VLMs summarized into one caption with tag grounding: JoyCaption Beta 1, MiMo Vision 7B, and Gemma 3 27B. This will be done on V17.</li>                <li>This is to ensure that this LoRA is easily usable on models such as ~~SD3.5~~ Neta Lumina and any other future natural language models.</li>            </ul>        <li>Added artist tags to all identifiable artworks due to an accidental discovery where AIDL also learned artist styles whn there was enough data.</li>        <li>Added new diaper design: <code>merries</code><li>        <li>Tagged <code>wetness indicator</code>s as an attempt to separate wetness indicators from soiling (apparent when doing panty pees/poops).</li>        <li>Redone prints and made sure to catch as many prints as possible, including the use of <code>polka dot diaper</code>, <code>orientation indicator</code>, <code>size indicator</code></li>        <li>Added LoRA Manager metadata</li>        </ul>    </div></div>",
+    "trainedWords": [
+      "diaper",
+      "peed diaper",
+      "poopy diaper",
+      "pull-ups",
+      "peed pull-ups",
+      "pooping self",
+      "poopy underwear",
+      "poopy shorts",
+      "poopy pants",
+      "open diaper",
+      "covered diaper",
+      "diaper peek",
+      "@cakies22, oekaki",
+      "@omulettes",
+      "@mizusoba",
+      "@mogurin",
+      "@kyoju",
+      "@dia75",
+      "@bunnymim",
+      "@gogo \\(201177\\)",
+      "@ararii",
+      "@tokiha \\(ruinluin\\)",
+      "@azure_sunset4",
+      "@shibachaya",
+      "@alkali",
+      "@road again",
+      "@hc68o33",
+      "@stolas \\(lemegeton\\)"
+    ],
+    "customImages": []
+  },
+  "tags": [
+    "diaper",
+    "abdl",
+    "omorashi",
+    "scat"
+  ],
+  "modelDescription": "<style>  .main-div {    background-color: #9999ff; padding: 20px; border-radius: 10px; margin-bottom: 20px;  }  h1 {    color: #24292e;    margin-top: 0;    font-size: 25px;  }  h2 {    color: #24292e;    margin-top: 0;    font-size: 22px;  }  h3 {    color: #24292e;    margin-top: 0;    font-size: 20px;  }  h4 {    color: #24292e;    margin-top: 0;    font-size: 15px;  }  p {    color:#24292e;  }  a {    color: #0366d6;    text-decoration: none;  }  .section-div {    background-color: white;    padding: 15px;    border-radius: 8px;    margin: 15px 0;    box-shadow: 0 2px 4px rgba(0,0,0,0.1);  }  .subsection-div {    background-color: #bbb;    padding: 15px;    border-radius: 8px;    margin: 15px 0;    box-shadow: 0 2px 4px rgba(0,0,0,0.1);  }  ul {    margin-bottom: 0;    color: #24292e;  }  ol {    margin-bottom: 0;    color: #24292e;  }  td {    margin-bottom: 0;    color: #24292e;  }  code {    background-color: #333;    padding: 3px 6px;    border-radius: 4px;  }  table {    color: #24292e;  }</style><div class=\"main-div\">  <h1>AIDL: OmoAIShi</h1>  <div style=\"background-color: #ffff99; padding: 20px; border-radius: 10px; margin-bottom: 20px;\">  <img src=\"docs/Images/v16-thumb.png\">  <h3>V16: Tag Restructure Edition<br>For Lumina 2, Illustrious 2, NoobAI VPred</h3>  <div style=\"background-color: #ff9999; padding: 20px; border-radius: 10px; margin-bottom: 20px;\">  <h3>This model is designed for **NSFW** purposes, trained and tested on DRAWN CHARACTERS ONLY.</h3>  <h3>PUBLIC ALPHA. GENERATIONS DO NOT REPRESENT THE FINAL MODEL.</h3>  </div>    <a href=\"https://gitgud.io/mrpopsalot/aidl-omoaishi\"><img alt=\"Static Badge\" src=\"https://img.shields.io/badge/GitLab-orange?logo=gitlab&logoColor=white&style=for-the-badge\"></a>    <a href=\"https://huggingface.co/mrpopsalot/aidl-omoaishi\"><img alt=\"Static Badge\" src=\"https://img.shields.io/badge/HuggingFace-yellow?logo=huggingface&logoColor=white&style=for-the-badge\"></a>    <a href=\"https://allthefallen.moe/forum/index.php?resources/aidl-omoaishi.7465/\"><img alt=\"Static Badge\" src=\"https://img.shields.io/badge/AllTheFallen-pink?logo=outlook&logoColor=white&style=for-the-badge\"></a>    <img alt=\"GitLab License\" src=\"https://img.shields.io/gitlab/license/mrpopsalot%2Faidl-omoaishi?gitlab_url=http%3A%2F%2Fgitgud.io&style=for-the-badge\">  </div>  <div class=\"section-div\">    <h2>Overview</h2>    <p>OmoAIshi is the most comprehensive multi-concept LoRA for diaper wearing and using, able to comprehend multiple concepts previously unfulfilled by base models and other LoRAs. LyCORIS LoCon is used instead of the regular LoRA format as it allows multiple concepts to be trained within the same model. No more girls in panties!</p>    <ul>      <li><b>Trained Models:</b></li>      <ul>        <li><b>NoobAI-XL VPred:</b> Laxhar/noobai-XL-Vpred-1.0 @ 1024</li>        <li><b>Illustrious 2:</b> OnomaAIResearch/Illustrious-XL-v2.0 @ 1536</li>          <ul>          <li>Also works on 1024px, as well on Illustrious 1, 0.1, and NoobAI EPS</li>          </ul>        <li><b>Lumina Image 2:</b> neta-art/neta-lumina 1.0 @ 1024</li>      </ul>      <li><b>Developed by:</b> Mr Pops Alot</li>      <li><b>Model type:</b> LyCORIS, Full Preset (LoRA for Lumina 2)</li>      <li><b>License:</b> Apache 2.0</li>    </ul><br>    <p>This is the first LoRA of the AIDL series. <b>AIDL: The AI Diaper LyCORIS</b> is intended to a series of LoRAs that teaches models about diapers and other ABDL related concepts.</p>  </div>  <div class=\"section-div\">    <h2>Showcase</h2>    <p><img src=\"docs/Images/EasyGrid_00001_.png\"></p>  </div>  <div class=\"section-div\">    <h2>Features</h2>    <ul>      <li><b>Tape-on diapers:</b> Two and four taped, printed and plain diapers are supported. Diapers from specific brands and designs are also trained when noticed. Note that these are not fully trained and may not be fully accurate.</li>      <li><b>Pull-up diapers:</b> Pull-ups are also trained and can be prompted in various designs.</li>      <li><b>Peed diapers:</b> Wet diapers of various stages, from slightly wet to completely leaking. Speaking of leaks, they now correctly go at the side of the thighs.</li>      <li><b>Diaper and panty pooping:</b> Soiling of various stages, including blowouts have also been trained, as with double pee and poo soiling as well. Pants, shorts, and dress pooping is also covered. Compatibility is not guaranteed (there is less training data). You may see some exposed scat.</li>      <li><b>Open diapers:</b> Open diapers are now possible to do, complete with wetness and mess in the pads if prompted.</li>      <li><b>Consistent results across different character positions:</b> This model has been trained on a variety of styles and poses, ensuring correct generation on many poses and whatever artstyle you want to use, including standing, squatting, lying down, from below upskirts, and more</li>    </ul>  </div>  <div class=\"section-div\">    <h2>How to Use</h2>    <div class=\"subsection-div\">      <h3>Diapers</h3>      <p>Use the general term: <code>diaper</code>, or <code>in a diaper</code>.</p>      <ul>      <li>You can also specify the tape count using <code>two taped</code>, or <code>four taped</code>.</li>      <li>Prompting <code>plain diaper</code> will get you a diaper with no designs, while <code>print diaper</code> will get you a printed diaper.</li>      <li><code>front-print diaper</code> and <code>back-print diaper</code> can also be used to get you a print on the front or back. Use <a href=\"https://danbooru.donmai.us/tags?commit=Search&search%5Bhide_empty%5D=yes&search%5Bname_or_alias_matches%5D=%2A_print&search%5Border%5D=count\">Danbooru's list of prints</a>.</li>      <li>Add in wetness indicators by prompting <code>yellow wetness indicator</code> or <code>blue wetness indicator</code>.</li>      </ul>      <p>Specific diaper styles:</p>      <ul>        <li><code>pampers</code></li>        <li><code>huggies</code></li>        <li><code>luvs</code></li>        <li><code>abuniverse</code></li>        <li><code>merries</code></li>      </ul>    </div>    <div class=\"subsection-div\">      <h3>Pull-Ups</h3>      <p>Use <code>pull-ups</code>. Same prompting style as with diapers, but replace <code>diaper</code> with <code>pull-ups</code>.</p>    </div>    <div class=\"subsection-div\">      <h3>Diaper Soiling</h3>      <p><b>Peed-in diapers:</b> Use the general <code>peed diaper</code> tag to get wet diapers. From there, you can also go and set how soiled the diaper should be. Without it, you might get unexpected diaper blowouts.</p>      <ol>        <li><code>wet diaper</code></li>        <li><code>soaked diaper</code></li>        <li><code>drenched diaper</code></li>        <li><code>leaking diaper</code>, <code>pee on legs</code></li>      </ol>      <br>      <p><b>Poopy diapers:</b> Use the general <code>poopy diaper</code> tag to get messy diapers. From there, you can also go and set how soiled the diaper should be. Without it, you might get unexpected diaper blowouts.</p>      <ol>        <li><code>messy diaper</code></li>        <li><code>packed diaper</code></li>        <li><code>loaded diaper</code></li>        <li><code>diaper blowout</code>, <code>poop on legs</code></li>      </ol>      <br>      <p><code>smell</code> can also be added to your prompt to give off that soiled smell effect.</p>      <p>If you want more soiled diapers, you can increase the weight of the tag to suit your needs. Tags works well between 0.9-1.5 weight.</p>      <img src=\"docs/Images/unidesSoil_00002_.png\">      <img src=\"docs/Images/unidesSoil_00004_.png\">    </div>    <div class=\"subsection-div\">      <h3>Pantypooping</h3>      <p>Use the term <code>pooping self</code>. You can also use the terms <code>poopy underwear</code> or <code>poopy clothes</code> to have either their underwear be soiled or their lower clothes (like their dress or pants) to be soiled.      </p>      <img src=\"docs/Images/unidesSoil_00005_.png\">      <p>Multiple underwear types supported!</p>      <p>For diapers please use the poopy diaper tag. Pooping self can also work but poopy diaper is the recommended tag for diaper pooping.</p>    </div>    <div class=\"subsection-div\">      <h3>Open Diapers</h3>      <p>Use the term <code>open diaper</code> to get open diapers.</p>      <ul>        <li>Add in <code>peed diaper</code> and <code>poopy diaper</code> respectively if you want the diaper to be wet and messy.</li>        <li>As well, add your respective genitals such as <code>pussy</code> or <code>penis</code> and the uncensored tag</li>      </ul>      <img src=\"docs/Images/openDiaper_00000_.png\">    </div>  </div>  <div class=\"section-div\">    <h2>Bias, Risks, and Limitations</h2>    <p>The model currently struggles with the following concepts:</p>    <ul>      <li>Non-printed and colored pull-ups</li>      <li>Open diapers</li>      <ul>        <li>Open diapers do not have as much data as other concepts, and will struggle to have proper diaper structure.</li>      </ul>      <li>Unworn diapers (both clean and used)</li>      <li>Clothespooping</li>      <li>Technical positions such as falling</li>    </ul>    <br>    <p>As well, there may be some limitations with this LoRA:</p>    <ul>      <li>Panty poops may happen unprompted if <code>smell</code> is prompted</li>      <li>Peed diapers may have poopy diaper bulges unless poopy diaper is put in the negatives</li>      <li>There is currently no training data for poopy pull-ups, and is using the fallback pantypooping data.</li>      <li>Poopy diapers may have unprompted blowouts.</li>      <li>In the Lumina 2 LoRA, you need to prompt for \"wet diaper\" as well with \"peed diaper\" to get a pee soaked pad.</li>      <li>Although you can use Rouwei Gemma in the SDXL variants, you'll only get pull-ups</li>    </ul>  <p>Increase the strength of the LoRA if needed to achieve your desired results.</p>  <div style=\"background-color: #ff9999; padding: 20px; border-radius: 10px; margin-bottom: 20px;\">    <p> I am in no way responsible for any content that the user creates with malicious intent while using any of these models. The user assumes complete responsibility for the misuse of these tools and any unethical content created with them. <b>Follow all local, state, and federal laws as well as online rules regarding this content and generations with this LoRA. I am not responsible if you are arrested or banned from an online service for using this.</b></p>    <p><b>This LoRA violates CivitAI's terms of service (their TOS does not allow diapers nor scat). Do not upload generations from AIDL onto CivitAI.</b></p>  </div>  </div>  <div class=\"section-div\">    <h2>Training Details</h2>    <p>Over 1000 images have been used in the dataset. Images used are <b>exclusively drawn 2D</b> art.</p>    <p><b>No synthetic data has been used</b> for the model. Tagging (Danbooru tag style) is <b>all manually done</b>, as automatic taggers do not recognize the concept in question well. Image captioning (NL support) uses a list of manual captioned images and (planned for V17) JoyCaption Beta 1 and Gemma 3 27B outputs with manual Tag grounding.</p>    <div class=\"subsection-div\">      <h3>Training Procedure</h3>      <p>Training configs are provided with the weights, but as a TL;DR:</p>      <h4>SDXL-based (Illustrious, NoobAI)</h4>      <ul>        <li>Program: 67372a's Kohya Easy Scripts</li>        <li>Optimizer: CAME</li>        <li>Scheduler: Rex</li>        <li>UNet LR: 3e-4</li>        <li>LoRA type: LoCon</li>        <li>Steps: 36600</li>        <li>Network Rank (Dim/Alpha): 64/1</li>        <li>Precision: Full BF16</li>        <li>Hardware: 1x RTX 3090 24GB</li>      </ul>      <h4>Lumina 2</h4>      <ul>        <li>Program: Kohya sd-scripts SD3 branch</li>        <li>Optimizer: CAME</li>        <li>Scheduler: Rex</li>        <li>DiT LR: 1e-4</li>        <li>TE LR: None. TE outputs are cached</li>        <li>LoRA type: LoRA Lumina</li>        <ul>          <li>No LoCon needed as they'res no Conv layers.</li>        </ul>        <li>Steps: 36600 (batch 4)</li>        <li>Network Rank (Dim/Alpha): 64/32</li>        <li>Precision: Full BF16</li>        <li>Hardware: 1x RTX 3090 24GB</li>      </ul>    </div>  </div>  <div class=\"section-div\">    <h2>FAQ</h2>    <ul>      <li><b>Will this model be ported to X?</b> This model is planned to have versions trained on NoobAI-XL VPred, Illustrious 2.0 (ILXL2), and Neta Lumina (Lumina 2). More models will come later.      <ul>        <li>Lumina 2 version only works on Neta Lumina AES paths, such as a5nA and 1.0</li>        <li>The Illustrious 2 version works on Illustrious 1, 0.1, and NoobAI-XL Epsilon Pred.</li>        <li>V17 will have a Wan 2.2 5B</li>        <li>No Pony version is planned. Move to NoobXL or ILXL.</li>      </ul></li>      <li><b>Will there be a version for CivitAI?</b> No. I do not trust CivitAI anymore after the release of Illustrious 1.0 and them allowing closed-weight models, not to mention the overbearing censorship against messy diaper content, bad service, and overall greed.      <ul>        <li>V15.1 Update: Definitely not, especially since urine and diaper content have been expressly banned. Oh, and half the time the site crashes when you try to do anything. Good riddance.</li>      </ul></li>      <li><b>Anything else planned?</b>        <ul>          <li>Diaper changes</li>          <li>Open diapers and pull-ups</li>          <li>Diaper covers</li>          <li>Diaper pulls (like panty pulls)</li>          <li>Clean and used unworn diapers</li>          <li>Cloth diapers</li>          <li>Diaper pulls</li>          <li>The rest of the data in my dataset processed and tagged.</li>          <li>Etc.</li>        </ul>      </li>      <ul>    </ul>  </div>  <div class=\"section-div\">    <h2>License</h2>    <p>This LoRA model is provided under the <a href=\"https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md\">Apache License 2.0</a> license.</p>    <!-- <p>Training configurations and dataset will also be released later. You can use these to further train AIDL.</p> -->  </div>  <div class=\"section-div\">    <h2>Special Thanks</h2>    <ul>      <li>DangoKnight for training some of the test versions of this LoRA</li>      <li>Yatogami for contributing to the dataset.</li>      <li>Hugs288, Lopi99, and others in the NoobAI discord to for helping me get my LoRA training settings right.</li>    </ul>  </div>  <div class=\"section-div\">    <h2>Model Card Contact</h2>    <ul>      <p>I can be contacted on:</p>      <li><b>Matrix:</b> @mr_pops_alot:cutefunny.art</li>      <li><b>GitLab:</b> gitgud.io/mrpopsalot</li>      <li><b>All The Fallen:</b> @MrDoesNothingAlot</li>      <li><b>Discord:</b> 474149843724664854</li>    </ul>  </div></div>",
+  "civitai_deleted": false,
+  "favorite": true,
+  "exclude": false,
+  "db_checked": false,
+  "metadata_source": null,
+  "last_checked_at": 0,
+  "usage_tips": "{\"strength\":1}"
+}

017.0/Illustrious2-1024/aidl-v017-illustrious2-1024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49381235ea4dc458b10943ef5fc96908da1b4b54de61dbe730db3f144aeee21c
+size 509994560

017.0/NoobAI-RF-1024/aidl-v017-noobai-rf-1024.cm-info.json

@@ -0,0 +1,41 @@
+{
+  "ModelName": "[NoobAI RF] AIDL: OmoAIshi",
+  "ModelDescription": "OmoAIshi is the most comprehensive multi-concept LyCORIS for diaper wearing and using, able to comprehend multiple concepts previously unfulfilled by base models and other LoRAs. LyCORIS LoCon is used instead of the regular LoRA format as it allows multiple concepts to be trained within the same model. No more girls in panties! \n\nThis LoRA violates CivitAI\\u0027s terms of service (their TOS does not allow diapers nor scat). Do not upload generations from AIDL onto CivitAI.",
+  "Nsfw": true,
+  "Tags": [
+    "diaper",
+    "abdl",
+    "omorashi",
+    "scat"
+  ],
+  "ModelType": "LoCon",
+  "VersionId": 0,
+  "VersionName": "v017",
+  "VersionDescription": null,
+  "BaseModel": "NoobAI",
+  "FileMetadata": {
+    "fp": null,
+    "size": null,
+    "format": "SafeTensor"
+  },
+  "ImportedAt": "2024-12-12T07:27:13.2830617+00:00",
+  "Hashes": {
+    "SHA256": "thisisnotahash",
+    "CRC32": "thisisnotahash",
+    "BLAKE3": "thisisnotahash"
+  },
+  "TrainedWords": [
+    "diaper",
+    "peed diaper",
+    "poopy diaper",
+    "pull-ups",
+    "peed pull-ups",
+    "pooping self",
+    "poopy underwear",
+    "poopy shorts",
+    "poopy pants",
+    "open diaper"
+  ],
+  "UserTitle": null,
+  "ThumbnailImageUrl": "/opt/stabilitymatrix/Data/Models/Lora/OWN/aidl-v015-1-illustrious2-1536.preview.png"
+}

017.0/NoobAI-RF-1024/aidl-v017-noobai-rf-1024.metadata.json

@@ -0,0 +1,62 @@
+{
+  "file_name": "aidl-v017-noobai-rf-1024",
+  "model_name": "[NoobAI RF] AIDL: OmoAIshi V017",
+  "file_path": "/home/pops/AI/ComfyUI/models/loras/Own/aidl/aidl-v017-noobai-rf-1024.safetensors",
+  "size": 509995232,
+  "modified": 1767142313.522548,
+  "sha256": "cbb06d67f38a4ee65bc20523f3514ddd8325c444a3424a2f2cebbe1811b70972",
+  "base_model": "NoobAI",
+  "preview_url": "/home/pops/AI/ComfyUI/models/loras/Own/aidl/aidl-v017-noobai-rf-1024.preview.png",
+  "preview_nsfw_level": 16,
+  "notes": "",
+  "from_civitai": false,
+  "civitai": {
+    "name": "V17 - NoobAI RF",
+    "description": "<style>  .main-div {    background-color: #9999ff; padding: 20px; border-radius: 10px; margin-bottom: 20px;  }  h1 {    color: #24292e;    margin-top: 0;    font-size: 25px;  }  h2 {    color: #24292e;    margin-top: 0;    font-size: 22px;  }  h3 {    color: #24292e;    margin-top: 0;    font-size: 20px;  }  h4 {    color: #24292e;    margin-top: 0;    font-size: 15px;  }  p {    color:#24292e;  }  a {    color: #0366d6;    text-decoration: none;  }  .section-div {    background-color: white;    padding: 15px;    border-radius: 8px;    margin: 15px 0;    box-shadow: 0 2px 4px rgba(0,0,0,0.1);  }  .subsection-div {    background-color: #bbb;    padding: 15px;    border-radius: 8px;    margin: 15px 0;    box-shadow: 0 2px 4px rgba(0,0,0,0.1);  }  ul {    margin-bottom: 0;    color: #24292e;  }  ol {    margin-bottom: 0;    color: #24292e;  }  td {    margin-bottom: 0;    color: #24292e;  }  code {    background-color: #333;    padding: 3px 6px;    border-radius: 4px;  }  table {    color: #24292e;  }</style><div class=\"main-div\">    <h1>AIDL: OmoAIShi Changelog</h1>    <div class=\"section-div\">        <h2>V16: Tag Restructure Edition</h2>        <p>Welcome to V16! Refined tags, another new customizable diaper element, and the new Neta Lumina architecture brings AIDL to the world of Diffusion Transformers. While the Lumina variant is the standout variant of AIDL, the SDXL variants can still hold its weight well. With the Gemma 2 2B TE that Neta Lumina has, such concepts like <code>covered diaper</code> are possible without having any images of that concept, as well as the ability for natural language to be used.</p>        <p>Wetness indicators are now tagged to help stop the wetness indicators from appearing during pantypooping. You can also go and set up the wetness indicators to any color the model recognizes. The most trained colors are yellow and blue, which are common colors used for diaper wetness indicators, but if you use Neta Lumina, you can also set it to any color it knows.</p>        <ul>        <li>Added handmade natural language captions to <code>diaper</code> and <code>peed diaper</code> concepts images in the dataset.</li>            <ul>                <li>The <code>diaper</code> and <code>peed diaper</code> concepts are hand captioned.</li>                <li>Other images and newer images will use a combination of three VLMs summarized into one caption with tag grounding: JoyCaption Beta 1, MiMo Vision 7B, and Gemma 3 27B. This will be done on V17.</li>                <li>This is to ensure that this LoRA is easily usable on models such as ~~SD3.5~~ Neta Lumina and any other future natural language models.</li>            </ul>        <li>Added artist tags to all identifiable artworks due to an accidental discovery where AIDL also learned artist styles whn there was enough data.</li>        <li>Added new diaper design: <code>merries</code><li>        <li>Tagged <code>wetness indicator</code>s as an attempt to separate wetness indicators from soiling (apparent when doing panty pees/poops).</li>        <li>Redone prints and made sure to catch as many prints as possible, including the use of <code>polka dot diaper</code>, <code>orientation indicator</code>, <code>size indicator</code></li>        <li>Added LoRA Manager metadata</li>        </ul>    </div></div>",
+    "trainedWords": [
+      "diaper",
+      "peed diaper",
+      "poopy diaper",
+      "pull-ups",
+      "peed pull-ups",
+      "pooping self",
+      "poopy underwear",
+      "poopy shorts",
+      "poopy pants",
+      "open diaper",
+      "covered diaper",
+      "diaper peek",
+      "@cakies22, oekaki",
+      "@omulettes",
+      "@mizusoba",
+      "@mogurin",
+      "@kyoju",
+      "@dia75",
+      "@bunnymim",
+      "@gogo \\(201177\\)",
+      "@ararii",
+      "@tokiha \\(ruinluin\\)",
+      "@azure_sunset4",
+      "@shibachaya",
+      "@alkali",
+      "@road again",
+      "@hc68o33",
+      "@stolas \\(lemegeton\\)"
+    ],
+    "customImages": []
+  },
+  "tags": [
+    "diaper",
+    "abdl",
+    "omorashi",
+    "scat"
+  ],
+  "modelDescription": "<style>  .main-div {    background-color: #9999ff; padding: 20px; border-radius: 10px; margin-bottom: 20px;  }  h1 {    color: #24292e;    margin-top: 0;    font-size: 25px;  }  h2 {    color: #24292e;    margin-top: 0;    font-size: 22px;  }  h3 {    color: #24292e;    margin-top: 0;    font-size: 20px;  }  h4 {    color: #24292e;    margin-top: 0;    font-size: 15px;  }  p {    color:#24292e;  }  a {    color: #0366d6;    text-decoration: none;  }  .section-div {    background-color: white;    padding: 15px;    border-radius: 8px;    margin: 15px 0;    box-shadow: 0 2px 4px rgba(0,0,0,0.1);  }  .subsection-div {    background-color: #bbb;    padding: 15px;    border-radius: 8px;    margin: 15px 0;    box-shadow: 0 2px 4px rgba(0,0,0,0.1);  }  ul {    margin-bottom: 0;    color: #24292e;  }  ol {    margin-bottom: 0;    color: #24292e;  }  td {    margin-bottom: 0;    color: #24292e;  }  code {    background-color: #333;    padding: 3px 6px;    border-radius: 4px;  }  table {    color: #24292e;  }</style><div class=\"main-div\">  <h1>AIDL: OmoAIShi</h1>  <div style=\"background-color: #ffff99; padding: 20px; border-radius: 10px; margin-bottom: 20px;\">  <img src=\"docs/Images/v16-thumb.png\">  <h3>V16: Tag Restructure Edition<br>For Lumina 2, Illustrious 2, NoobAI VPred</h3>  <div style=\"background-color: #ff9999; padding: 20px; border-radius: 10px; margin-bottom: 20px;\">  <h3>This model is designed for **NSFW** purposes, trained and tested on DRAWN CHARACTERS ONLY.</h3>  <h3>PUBLIC ALPHA. GENERATIONS DO NOT REPRESENT THE FINAL MODEL.</h3>  </div>    <a href=\"https://gitgud.io/mrpopsalot/aidl-omoaishi\"><img alt=\"Static Badge\" src=\"https://img.shields.io/badge/GitLab-orange?logo=gitlab&logoColor=white&style=for-the-badge\"></a>    <a href=\"https://huggingface.co/mrpopsalot/aidl-omoaishi\"><img alt=\"Static Badge\" src=\"https://img.shields.io/badge/HuggingFace-yellow?logo=huggingface&logoColor=white&style=for-the-badge\"></a>    <a href=\"https://allthefallen.moe/forum/index.php?resources/aidl-omoaishi.7465/\"><img alt=\"Static Badge\" src=\"https://img.shields.io/badge/AllTheFallen-pink?logo=outlook&logoColor=white&style=for-the-badge\"></a>    <img alt=\"GitLab License\" src=\"https://img.shields.io/gitlab/license/mrpopsalot%2Faidl-omoaishi?gitlab_url=http%3A%2F%2Fgitgud.io&style=for-the-badge\">  </div>  <div class=\"section-div\">    <h2>Overview</h2>    <p>OmoAIshi is the most comprehensive multi-concept LoRA for diaper wearing and using, able to comprehend multiple concepts previously unfulfilled by base models and other LoRAs. LyCORIS LoCon is used instead of the regular LoRA format as it allows multiple concepts to be trained within the same model. No more girls in panties!</p>    <ul>      <li><b>Trained Models:</b></li>      <ul>        <li><b>NoobAI-XL VPred:</b> Laxhar/noobai-XL-Vpred-1.0 @ 1024</li>        <li><b>Illustrious 2:</b> OnomaAIResearch/Illustrious-XL-v2.0 @ 1536</li>          <ul>          <li>Also works on 1024px, as well on Illustrious 1, 0.1, and NoobAI EPS</li>          </ul>        <li><b>Lumina Image 2:</b> neta-art/neta-lumina 1.0 @ 1024</li>      </ul>      <li><b>Developed by:</b> Mr Pops Alot</li>      <li><b>Model type:</b> LyCORIS, Full Preset (LoRA for Lumina 2)</li>      <li><b>License:</b> Apache 2.0</li>    </ul><br>    <p>This is the first LoRA of the AIDL series. <b>AIDL: The AI Diaper LyCORIS</b> is intended to a series of LoRAs that teaches models about diapers and other ABDL related concepts.</p>  </div>  <div class=\"section-div\">    <h2>Showcase</h2>    <p><img src=\"docs/Images/EasyGrid_00001_.png\"></p>  </div>  <div class=\"section-div\">    <h2>Features</h2>    <ul>      <li><b>Tape-on diapers:</b> Two and four taped, printed and plain diapers are supported. Diapers from specific brands and designs are also trained when noticed. Note that these are not fully trained and may not be fully accurate.</li>      <li><b>Pull-up diapers:</b> Pull-ups are also trained and can be prompted in various designs.</li>      <li><b>Peed diapers:</b> Wet diapers of various stages, from slightly wet to completely leaking. Speaking of leaks, they now correctly go at the side of the thighs.</li>      <li><b>Diaper and panty pooping:</b> Soiling of various stages, including blowouts have also been trained, as with double pee and poo soiling as well. Pants, shorts, and dress pooping is also covered. Compatibility is not guaranteed (there is less training data). You may see some exposed scat.</li>      <li><b>Open diapers:</b> Open diapers are now possible to do, complete with wetness and mess in the pads if prompted.</li>      <li><b>Consistent results across different character positions:</b> This model has been trained on a variety of styles and poses, ensuring correct generation on many poses and whatever artstyle you want to use, including standing, squatting, lying down, from below upskirts, and more</li>    </ul>  </div>  <div class=\"section-div\">    <h2>How to Use</h2>    <div class=\"subsection-div\">      <h3>Diapers</h3>      <p>Use the general term: <code>diaper</code>, or <code>in a diaper</code>.</p>      <ul>      <li>You can also specify the tape count using <code>two taped</code>, or <code>four taped</code>.</li>      <li>Prompting <code>plain diaper</code> will get you a diaper with no designs, while <code>print diaper</code> will get you a printed diaper.</li>      <li><code>front-print diaper</code> and <code>back-print diaper</code> can also be used to get you a print on the front or back. Use <a href=\"https://danbooru.donmai.us/tags?commit=Search&search%5Bhide_empty%5D=yes&search%5Bname_or_alias_matches%5D=%2A_print&search%5Border%5D=count\">Danbooru's list of prints</a>.</li>      <li>Add in wetness indicators by prompting <code>yellow wetness indicator</code> or <code>blue wetness indicator</code>.</li>      </ul>      <p>Specific diaper styles:</p>      <ul>        <li><code>pampers</code></li>        <li><code>huggies</code></li>        <li><code>luvs</code></li>        <li><code>abuniverse</code></li>        <li><code>merries</code></li>      </ul>    </div>    <div class=\"subsection-div\">      <h3>Pull-Ups</h3>      <p>Use <code>pull-ups</code>. Same prompting style as with diapers, but replace <code>diaper</code> with <code>pull-ups</code>.</p>    </div>    <div class=\"subsection-div\">      <h3>Diaper Soiling</h3>      <p><b>Peed-in diapers:</b> Use the general <code>peed diaper</code> tag to get wet diapers. From there, you can also go and set how soiled the diaper should be. Without it, you might get unexpected diaper blowouts.</p>      <ol>        <li><code>wet diaper</code></li>        <li><code>soaked diaper</code></li>        <li><code>drenched diaper</code></li>        <li><code>leaking diaper</code>, <code>pee on legs</code></li>      </ol>      <br>      <p><b>Poopy diapers:</b> Use the general <code>poopy diaper</code> tag to get messy diapers. From there, you can also go and set how soiled the diaper should be. Without it, you might get unexpected diaper blowouts.</p>      <ol>        <li><code>messy diaper</code></li>        <li><code>packed diaper</code></li>        <li><code>loaded diaper</code></li>        <li><code>diaper blowout</code>, <code>poop on legs</code></li>      </ol>      <br>      <p><code>smell</code> can also be added to your prompt to give off that soiled smell effect.</p>      <p>If you want more soiled diapers, you can increase the weight of the tag to suit your needs. Tags works well between 0.9-1.5 weight.</p>      <img src=\"docs/Images/unidesSoil_00002_.png\">      <img src=\"docs/Images/unidesSoil_00004_.png\">    </div>    <div class=\"subsection-div\">      <h3>Pantypooping</h3>      <p>Use the term <code>pooping self</code>. You can also use the terms <code>poopy underwear</code> or <code>poopy clothes</code> to have either their underwear be soiled or their lower clothes (like their dress or pants) to be soiled.      </p>      <img src=\"docs/Images/unidesSoil_00005_.png\">      <p>Multiple underwear types supported!</p>      <p>For diapers please use the poopy diaper tag. Pooping self can also work but poopy diaper is the recommended tag for diaper pooping.</p>    </div>    <div class=\"subsection-div\">      <h3>Open Diapers</h3>      <p>Use the term <code>open diaper</code> to get open diapers.</p>      <ul>        <li>Add in <code>peed diaper</code> and <code>poopy diaper</code> respectively if you want the diaper to be wet and messy.</li>        <li>As well, add your respective genitals such as <code>pussy</code> or <code>penis</code> and the uncensored tag</li>      </ul>      <img src=\"docs/Images/openDiaper_00000_.png\">    </div>  </div>  <div class=\"section-div\">    <h2>Bias, Risks, and Limitations</h2>    <p>The model currently struggles with the following concepts:</p>    <ul>      <li>Non-printed and colored pull-ups</li>      <li>Open diapers</li>      <ul>        <li>Open diapers do not have as much data as other concepts, and will struggle to have proper diaper structure.</li>      </ul>      <li>Unworn diapers (both clean and used)</li>      <li>Clothespooping</li>      <li>Technical positions such as falling</li>    </ul>    <br>    <p>As well, there may be some limitations with this LoRA:</p>    <ul>      <li>Panty poops may happen unprompted if <code>smell</code> is prompted</li>      <li>Peed diapers may have poopy diaper bulges unless poopy diaper is put in the negatives</li>      <li>There is currently no training data for poopy pull-ups, and is using the fallback pantypooping data.</li>      <li>Poopy diapers may have unprompted blowouts.</li>      <li>In the Lumina 2 LoRA, you need to prompt for \"wet diaper\" as well with \"peed diaper\" to get a pee soaked pad.</li>      <li>Although you can use Rouwei Gemma in the SDXL variants, you'll only get pull-ups</li>    </ul>  <p>Increase the strength of the LoRA if needed to achieve your desired results.</p>  <div style=\"background-color: #ff9999; padding: 20px; border-radius: 10px; margin-bottom: 20px;\">    <p> I am in no way responsible for any content that the user creates with malicious intent while using any of these models. The user assumes complete responsibility for the misuse of these tools and any unethical content created with them. <b>Follow all local, state, and federal laws as well as online rules regarding this content and generations with this LoRA. I am not responsible if you are arrested or banned from an online service for using this.</b></p>    <p><b>This LoRA violates CivitAI's terms of service (their TOS does not allow diapers nor scat). Do not upload generations from AIDL onto CivitAI.</b></p>  </div>  </div>  <div class=\"section-div\">    <h2>Training Details</h2>    <p>Over 1000 images have been used in the dataset. Images used are <b>exclusively drawn 2D</b> art.</p>    <p><b>No synthetic data has been used</b> for the model. Tagging (Danbooru tag style) is <b>all manually done</b>, as automatic taggers do not recognize the concept in question well. Image captioning (NL support) uses a list of manual captioned images and (planned for V17) JoyCaption Beta 1 and Gemma 3 27B outputs with manual Tag grounding.</p>    <div class=\"subsection-div\">      <h3>Training Procedure</h3>      <p>Training configs are provided with the weights, but as a TL;DR:</p>      <h4>SDXL-based (Illustrious, NoobAI)</h4>      <ul>        <li>Program: 67372a's Kohya Easy Scripts</li>        <li>Optimizer: CAME</li>        <li>Scheduler: Rex</li>        <li>UNet LR: 3e-4</li>        <li>LoRA type: LoCon</li>        <li>Steps: 36600</li>        <li>Network Rank (Dim/Alpha): 64/1</li>        <li>Precision: Full BF16</li>        <li>Hardware: 1x RTX 3090 24GB</li>      </ul>      <h4>Lumina 2</h4>      <ul>        <li>Program: Kohya sd-scripts SD3 branch</li>        <li>Optimizer: CAME</li>        <li>Scheduler: Rex</li>        <li>DiT LR: 1e-4</li>        <li>TE LR: None. TE outputs are cached</li>        <li>LoRA type: LoRA Lumina</li>        <ul>          <li>No LoCon needed as they'res no Conv layers.</li>        </ul>        <li>Steps: 36600 (batch 4)</li>        <li>Network Rank (Dim/Alpha): 64/32</li>        <li>Precision: Full BF16</li>        <li>Hardware: 1x RTX 3090 24GB</li>      </ul>    </div>  </div>  <div class=\"section-div\">    <h2>FAQ</h2>    <ul>      <li><b>Will this model be ported to X?</b> This model is planned to have versions trained on NoobAI-XL VPred, Illustrious 2.0 (ILXL2), and Neta Lumina (Lumina 2). More models will come later.      <ul>        <li>Lumina 2 version only works on Neta Lumina AES paths, such as a5nA and 1.0</li>        <li>The Illustrious 2 version works on Illustrious 1, 0.1, and NoobAI-XL Epsilon Pred.</li>        <li>V17 will have a Wan 2.2 5B</li>        <li>No Pony version is planned. Move to NoobXL or ILXL.</li>      </ul></li>      <li><b>Will there be a version for CivitAI?</b> No. I do not trust CivitAI anymore after the release of Illustrious 1.0 and them allowing closed-weight models, not to mention the overbearing censorship against messy diaper content, bad service, and overall greed.      <ul>        <li>V15.1 Update: Definitely not, especially since urine and diaper content have been expressly banned. Oh, and half the time the site crashes when you try to do anything. Good riddance.</li>      </ul></li>      <li><b>Anything else planned?</b>        <ul>          <li>Diaper changes</li>          <li>Open diapers and pull-ups</li>          <li>Diaper covers</li>          <li>Diaper pulls (like panty pulls)</li>          <li>Clean and used unworn diapers</li>          <li>Cloth diapers</li>          <li>Diaper pulls</li>          <li>The rest of the data in my dataset processed and tagged.</li>          <li>Etc.</li>        </ul>      </li>      <ul>    </ul>  </div>  <div class=\"section-div\">    <h2>License</h2>    <p>This LoRA model is provided under the <a href=\"https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md\">Apache License 2.0</a> license.</p>    <!-- <p>Training configurations and dataset will also be released later. You can use these to further train AIDL.</p> -->  </div>  <div class=\"section-div\">    <h2>Special Thanks</h2>    <ul>      <li>DangoKnight for training some of the test versions of this LoRA</li>      <li>Yatogami for contributing to the dataset.</li>      <li>Hugs288, Lopi99, and others in the NoobAI discord to for helping me get my LoRA training settings right.</li>    </ul>  </div>  <div class=\"section-div\">    <h2>Model Card Contact</h2>    <ul>      <p>I can be contacted on:</p>      <li><b>Matrix:</b> @mr_pops_alot:cutefunny.art</li>      <li><b>GitLab:</b> gitgud.io/mrpopsalot</li>      <li><b>All The Fallen:</b> @MrDoesNothingAlot</li>      <li><b>Discord:</b> 474149843724664854</li>    </ul>  </div></div>",
+  "civitai_deleted": false,
+  "favorite": true,
+  "exclude": false,
+  "db_checked": false,
+  "metadata_source": null,
+  "last_checked_at": 0,
+  "usage_tips": "{\"strength\":1}"
+}

017.0/NoobAI-RF-1024/aidl-v017-noobai-rf-1024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c91a69dd876ebc0541ca69d81620d570de242a1e4d361322c0dd58715eda13e3
+size 509994552

017.0/NoobAI-RF-F2Vae-1024/aidl-v017-noobai-rf-f2vae-1024.cm-info.json

@@ -0,0 +1,41 @@
+{
+  "ModelName": "[NoobAI RF F2VAE] AIDL: OmoAIshi",
+  "ModelDescription": "OmoAIshi is the most comprehensive multi-concept LyCORIS for diaper wearing and using, able to comprehend multiple concepts previously unfulfilled by base models and other LoRAs. LyCORIS LoCon is used instead of the regular LoRA format as it allows multiple concepts to be trained within the same model. No more girls in panties! \n\nThis LoRA violates CivitAI\\u0027s terms of service (their TOS does not allow diapers nor scat). Do not upload generations from AIDL onto CivitAI.",
+  "Nsfw": true,
+  "Tags": [
+    "diaper",
+    "abdl",
+    "omorashi",
+    "scat"
+  ],
+  "ModelType": "LoCon",
+  "VersionId": 0,
+  "VersionName": "v017",
+  "VersionDescription": null,
+  "BaseModel": "Other",
+  "FileMetadata": {
+    "fp": null,
+    "size": null,
+    "format": "SafeTensor"
+  },
+  "ImportedAt": "2024-12-12T07:27:13.2830617+00:00",
+  "Hashes": {
+    "SHA256": "thisisnotahash",
+    "CRC32": "thisisnotahash",
+    "BLAKE3": "thisisnotahash"
+  },
+  "TrainedWords": [
+    "diaper",
+    "peed diaper",
+    "poopy diaper",
+    "pull-ups",
+    "peed pull-ups",
+    "pooping self",
+    "poopy underwear",
+    "poopy shorts",
+    "poopy pants",
+    "open diaper"
+  ],
+  "UserTitle": null,
+  "ThumbnailImageUrl": "/opt/stabilitymatrix/Data/Models/Lora/OWN/aidl-v015-1-illustrious2-1536.preview.png"
+}

017.0/NoobAI-RF-F2Vae-1024/aidl-v017-noobai-rf-f2vae-1024.metadata.json

@@ -0,0 +1,62 @@
+{
+  "file_name": "aidl-v017-noobai-rf-f2vae-1024",
+  "model_name": "[NoobAI RF FLUX.2 VAE] AIDL: OmoAIshi V017",
+  "file_path": "/home/pops/AI/ComfyUI/models/loras/Own/aidl/aidl-v017-noobai-rf-f2vae-1024.safetensors",
+  "size": 509994656,
+  "modified": 1768027485.390599,
+  "sha256": "5df616867606e079b8c61c5e94583ebb2b43fda5c8d36e53ee151b7914b1df12",
+  "base_model": "Other",
+  "preview_url": "/home/pops/AI/ComfyUI/models/loras/Own/aidl/aidl-v017-noobai-rf-f2vae-1024.preview.png",
+  "preview_nsfw_level": 16,
+  "notes": "",
+  "from_civitai": false,
+  "civitai": {
+    "name": "V17 - NoobAI RF",
+    "description": "<style>  .main-div {    background-color: #9999ff; padding: 20px; border-radius: 10px; margin-bottom: 20px;  }  h1 {    color: #24292e;    margin-top: 0;    font-size: 25px;  }  h2 {    color: #24292e;    margin-top: 0;    font-size: 22px;  }  h3 {    color: #24292e;    margin-top: 0;    font-size: 20px;  }  h4 {    color: #24292e;    margin-top: 0;    font-size: 15px;  }  p {    color:#24292e;  }  a {    color: #0366d6;    text-decoration: none;  }  .section-div {    background-color: white;    padding: 15px;    border-radius: 8px;    margin: 15px 0;    box-shadow: 0 2px 4px rgba(0,0,0,0.1);  }  .subsection-div {    background-color: #bbb;    padding: 15px;    border-radius: 8px;    margin: 15px 0;    box-shadow: 0 2px 4px rgba(0,0,0,0.1);  }  ul {    margin-bottom: 0;    color: #24292e;  }  ol {    margin-bottom: 0;    color: #24292e;  }  td {    margin-bottom: 0;    color: #24292e;  }  code {    background-color: #333;    padding: 3px 6px;    border-radius: 4px;  }  table {    color: #24292e;  }</style><div class=\"main-div\">    <h1>AIDL: OmoAIShi Changelog</h1>    <div class=\"section-div\">        <h2>V16: Tag Restructure Edition</h2>        <p>Welcome to V16! Refined tags, another new customizable diaper element, and the new Neta Lumina architecture brings AIDL to the world of Diffusion Transformers. While the Lumina variant is the standout variant of AIDL, the SDXL variants can still hold its weight well. With the Gemma 2 2B TE that Neta Lumina has, such concepts like <code>covered diaper</code> are possible without having any images of that concept, as well as the ability for natural language to be used.</p>        <p>Wetness indicators are now tagged to help stop the wetness indicators from appearing during pantypooping. You can also go and set up the wetness indicators to any color the model recognizes. The most trained colors are yellow and blue, which are common colors used for diaper wetness indicators, but if you use Neta Lumina, you can also set it to any color it knows.</p>        <ul>        <li>Added handmade natural language captions to <code>diaper</code> and <code>peed diaper</code> concepts images in the dataset.</li>            <ul>                <li>The <code>diaper</code> and <code>peed diaper</code> concepts are hand captioned.</li>                <li>Other images and newer images will use a combination of three VLMs summarized into one caption with tag grounding: JoyCaption Beta 1, MiMo Vision 7B, and Gemma 3 27B. This will be done on V17.</li>                <li>This is to ensure that this LoRA is easily usable on models such as ~~SD3.5~~ Neta Lumina and any other future natural language models.</li>            </ul>        <li>Added artist tags to all identifiable artworks due to an accidental discovery where AIDL also learned artist styles whn there was enough data.</li>        <li>Added new diaper design: <code>merries</code><li>        <li>Tagged <code>wetness indicator</code>s as an attempt to separate wetness indicators from soiling (apparent when doing panty pees/poops).</li>        <li>Redone prints and made sure to catch as many prints as possible, including the use of <code>polka dot diaper</code>, <code>orientation indicator</code>, <code>size indicator</code></li>        <li>Added LoRA Manager metadata</li>        </ul>    </div></div>",
+    "trainedWords": [
+      "diaper",
+      "peed diaper",
+      "poopy diaper",
+      "pull-ups",
+      "peed pull-ups",
+      "pooping self",
+      "poopy underwear",
+      "poopy shorts",
+      "poopy pants",
+      "open diaper",
+      "covered diaper",
+      "diaper peek",
+      "@cakies22, oekaki",
+      "@omulettes",
+      "@mizusoba",
+      "@mogurin",
+      "@kyoju",
+      "@dia75",
+      "@bunnymim",
+      "@gogo \\(201177\\)",
+      "@ararii",
+      "@tokiha \\(ruinluin\\)",
+      "@azure_sunset4",
+      "@shibachaya",
+      "@alkali",
+      "@road again",
+      "@hc68o33",
+      "@stolas \\(lemegeton\\)"
+    ],
+    "customImages": []
+  },
+  "tags": [
+    "diaper",
+    "abdl",
+    "omorashi",
+    "scat"
+  ],
+  "modelDescription": "<style>  .main-div {    background-color: #9999ff; padding: 20px; border-radius: 10px; margin-bottom: 20px;  }  h1 {    color: #24292e;    margin-top: 0;    font-size: 25px;  }  h2 {    color: #24292e;    margin-top: 0;    font-size: 22px;  }  h3 {    color: #24292e;    margin-top: 0;    font-size: 20px;  }  h4 {    color: #24292e;    margin-top: 0;    font-size: 15px;  }  p {    color:#24292e;  }  a {    color: #0366d6;    text-decoration: none;  }  .section-div {    background-color: white;    padding: 15px;    border-radius: 8px;    margin: 15px 0;    box-shadow: 0 2px 4px rgba(0,0,0,0.1);  }  .subsection-div {    background-color: #bbb;    padding: 15px;    border-radius: 8px;    margin: 15px 0;    box-shadow: 0 2px 4px rgba(0,0,0,0.1);  }  ul {    margin-bottom: 0;    color: #24292e;  }  ol {    margin-bottom: 0;    color: #24292e;  }  td {    margin-bottom: 0;    color: #24292e;  }  code {    background-color: #333;    padding: 3px 6px;    border-radius: 4px;  }  table {    color: #24292e;  }</style><div class=\"main-div\">  <h1>AIDL: OmoAIShi</h1>  <div style=\"background-color: #ffff99; padding: 20px; border-radius: 10px; margin-bottom: 20px;\">  <img src=\"docs/Images/v16-thumb.png\">  <h3>V16: Tag Restructure Edition<br>For Lumina 2, Illustrious 2, NoobAI VPred</h3>  <div style=\"background-color: #ff9999; padding: 20px; border-radius: 10px; margin-bottom: 20px;\">  <h3>This model is designed for **NSFW** purposes, trained and tested on DRAWN CHARACTERS ONLY.</h3>  <h3>PUBLIC ALPHA. GENERATIONS DO NOT REPRESENT THE FINAL MODEL.</h3>  </div>    <a href=\"https://gitgud.io/mrpopsalot/aidl-omoaishi\"><img alt=\"Static Badge\" src=\"https://img.shields.io/badge/GitLab-orange?logo=gitlab&logoColor=white&style=for-the-badge\"></a>    <a href=\"https://huggingface.co/mrpopsalot/aidl-omoaishi\"><img alt=\"Static Badge\" src=\"https://img.shields.io/badge/HuggingFace-yellow?logo=huggingface&logoColor=white&style=for-the-badge\"></a>    <a href=\"https://allthefallen.moe/forum/index.php?resources/aidl-omoaishi.7465/\"><img alt=\"Static Badge\" src=\"https://img.shields.io/badge/AllTheFallen-pink?logo=outlook&logoColor=white&style=for-the-badge\"></a>    <img alt=\"GitLab License\" src=\"https://img.shields.io/gitlab/license/mrpopsalot%2Faidl-omoaishi?gitlab_url=http%3A%2F%2Fgitgud.io&style=for-the-badge\">  </div>  <div class=\"section-div\">    <h2>Overview</h2>    <p>OmoAIshi is the most comprehensive multi-concept LoRA for diaper wearing and using, able to comprehend multiple concepts previously unfulfilled by base models and other LoRAs. LyCORIS LoCon is used instead of the regular LoRA format as it allows multiple concepts to be trained within the same model. No more girls in panties!</p>    <ul>      <li><b>Trained Models:</b></li>      <ul>        <li><b>NoobAI-XL VPred:</b> Laxhar/noobai-XL-Vpred-1.0 @ 1024</li>        <li><b>Illustrious 2:</b> OnomaAIResearch/Illustrious-XL-v2.0 @ 1536</li>          <ul>          <li>Also works on 1024px, as well on Illustrious 1, 0.1, and NoobAI EPS</li>          </ul>        <li><b>Lumina Image 2:</b> neta-art/neta-lumina 1.0 @ 1024</li>      </ul>      <li><b>Developed by:</b> Mr Pops Alot</li>      <li><b>Model type:</b> LyCORIS, Full Preset (LoRA for Lumina 2)</li>      <li><b>License:</b> Apache 2.0</li>    </ul><br>    <p>This is the first LoRA of the AIDL series. <b>AIDL: The AI Diaper LyCORIS</b> is intended to a series of LoRAs that teaches models about diapers and other ABDL related concepts.</p>  </div>  <div class=\"section-div\">    <h2>Showcase</h2>    <p><img src=\"docs/Images/EasyGrid_00001_.png\"></p>  </div>  <div class=\"section-div\">    <h2>Features</h2>    <ul>      <li><b>Tape-on diapers:</b> Two and four taped, printed and plain diapers are supported. Diapers from specific brands and designs are also trained when noticed. Note that these are not fully trained and may not be fully accurate.</li>      <li><b>Pull-up diapers:</b> Pull-ups are also trained and can be prompted in various designs.</li>      <li><b>Peed diapers:</b> Wet diapers of various stages, from slightly wet to completely leaking. Speaking of leaks, they now correctly go at the side of the thighs.</li>      <li><b>Diaper and panty pooping:</b> Soiling of various stages, including blowouts have also been trained, as with double pee and poo soiling as well. Pants, shorts, and dress pooping is also covered. Compatibility is not guaranteed (there is less training data). You may see some exposed scat.</li>      <li><b>Open diapers:</b> Open diapers are now possible to do, complete with wetness and mess in the pads if prompted.</li>      <li><b>Consistent results across different character positions:</b> This model has been trained on a variety of styles and poses, ensuring correct generation on many poses and whatever artstyle you want to use, including standing, squatting, lying down, from below upskirts, and more</li>    </ul>  </div>  <div class=\"section-div\">    <h2>How to Use</h2>    <div class=\"subsection-div\">      <h3>Diapers</h3>      <p>Use the general term: <code>diaper</code>, or <code>in a diaper</code>.</p>      <ul>      <li>You can also specify the tape count using <code>two taped</code>, or <code>four taped</code>.</li>      <li>Prompting <code>plain diaper</code> will get you a diaper with no designs, while <code>print diaper</code> will get you a printed diaper.</li>      <li><code>front-print diaper</code> and <code>back-print diaper</code> can also be used to get you a print on the front or back. Use <a href=\"https://danbooru.donmai.us/tags?commit=Search&search%5Bhide_empty%5D=yes&search%5Bname_or_alias_matches%5D=%2A_print&search%5Border%5D=count\">Danbooru's list of prints</a>.</li>      <li>Add in wetness indicators by prompting <code>yellow wetness indicator</code> or <code>blue wetness indicator</code>.</li>      </ul>      <p>Specific diaper styles:</p>      <ul>        <li><code>pampers</code></li>        <li><code>huggies</code></li>        <li><code>luvs</code></li>        <li><code>abuniverse</code></li>        <li><code>merries</code></li>      </ul>    </div>    <div class=\"subsection-div\">      <h3>Pull-Ups</h3>      <p>Use <code>pull-ups</code>. Same prompting style as with diapers, but replace <code>diaper</code> with <code>pull-ups</code>.</p>    </div>    <div class=\"subsection-div\">      <h3>Diaper Soiling</h3>      <p><b>Peed-in diapers:</b> Use the general <code>peed diaper</code> tag to get wet diapers. From there, you can also go and set how soiled the diaper should be. Without it, you might get unexpected diaper blowouts.</p>      <ol>        <li><code>wet diaper</code></li>        <li><code>soaked diaper</code></li>        <li><code>drenched diaper</code></li>        <li><code>leaking diaper</code>, <code>pee on legs</code></li>      </ol>      <br>      <p><b>Poopy diapers:</b> Use the general <code>poopy diaper</code> tag to get messy diapers. From there, you can also go and set how soiled the diaper should be. Without it, you might get unexpected diaper blowouts.</p>      <ol>        <li><code>messy diaper</code></li>        <li><code>packed diaper</code></li>        <li><code>loaded diaper</code></li>        <li><code>diaper blowout</code>, <code>poop on legs</code></li>      </ol>      <br>      <p><code>smell</code> can also be added to your prompt to give off that soiled smell effect.</p>      <p>If you want more soiled diapers, you can increase the weight of the tag to suit your needs. Tags works well between 0.9-1.5 weight.</p>      <img src=\"docs/Images/unidesSoil_00002_.png\">      <img src=\"docs/Images/unidesSoil_00004_.png\">    </div>    <div class=\"subsection-div\">      <h3>Pantypooping</h3>      <p>Use the term <code>pooping self</code>. You can also use the terms <code>poopy underwear</code> or <code>poopy clothes</code> to have either their underwear be soiled or their lower clothes (like their dress or pants) to be soiled.      </p>      <img src=\"docs/Images/unidesSoil_00005_.png\">      <p>Multiple underwear types supported!</p>      <p>For diapers please use the poopy diaper tag. Pooping self can also work but poopy diaper is the recommended tag for diaper pooping.</p>    </div>    <div class=\"subsection-div\">      <h3>Open Diapers</h3>      <p>Use the term <code>open diaper</code> to get open diapers.</p>      <ul>        <li>Add in <code>peed diaper</code> and <code>poopy diaper</code> respectively if you want the diaper to be wet and messy.</li>        <li>As well, add your respective genitals such as <code>pussy</code> or <code>penis</code> and the uncensored tag</li>      </ul>      <img src=\"docs/Images/openDiaper_00000_.png\">    </div>  </div>  <div class=\"section-div\">    <h2>Bias, Risks, and Limitations</h2>    <p>The model currently struggles with the following concepts:</p>    <ul>      <li>Non-printed and colored pull-ups</li>      <li>Open diapers</li>      <ul>        <li>Open diapers do not have as much data as other concepts, and will struggle to have proper diaper structure.</li>      </ul>      <li>Unworn diapers (both clean and used)</li>      <li>Clothespooping</li>      <li>Technical positions such as falling</li>    </ul>    <br>    <p>As well, there may be some limitations with this LoRA:</p>    <ul>      <li>Panty poops may happen unprompted if <code>smell</code> is prompted</li>      <li>Peed diapers may have poopy diaper bulges unless poopy diaper is put in the negatives</li>      <li>There is currently no training data for poopy pull-ups, and is using the fallback pantypooping data.</li>      <li>Poopy diapers may have unprompted blowouts.</li>      <li>In the Lumina 2 LoRA, you need to prompt for \"wet diaper\" as well with \"peed diaper\" to get a pee soaked pad.</li>      <li>Although you can use Rouwei Gemma in the SDXL variants, you'll only get pull-ups</li>    </ul>  <p>Increase the strength of the LoRA if needed to achieve your desired results.</p>  <div style=\"background-color: #ff9999; padding: 20px; border-radius: 10px; margin-bottom: 20px;\">    <p> I am in no way responsible for any content that the user creates with malicious intent while using any of these models. The user assumes complete responsibility for the misuse of these tools and any unethical content created with them. <b>Follow all local, state, and federal laws as well as online rules regarding this content and generations with this LoRA. I am not responsible if you are arrested or banned from an online service for using this.</b></p>    <p><b>This LoRA violates CivitAI's terms of service (their TOS does not allow diapers nor scat). Do not upload generations from AIDL onto CivitAI.</b></p>  </div>  </div>  <div class=\"section-div\">    <h2>Training Details</h2>    <p>Over 1000 images have been used in the dataset. Images used are <b>exclusively drawn 2D</b> art.</p>    <p><b>No synthetic data has been used</b> for the model. Tagging (Danbooru tag style) is <b>all manually done</b>, as automatic taggers do not recognize the concept in question well. Image captioning (NL support) uses a list of manual captioned images and (planned for V17) JoyCaption Beta 1 and Gemma 3 27B outputs with manual Tag grounding.</p>    <div class=\"subsection-div\">      <h3>Training Procedure</h3>      <p>Training configs are provided with the weights, but as a TL;DR:</p>      <h4>SDXL-based (Illustrious, NoobAI)</h4>      <ul>        <li>Program: 67372a's Kohya Easy Scripts</li>        <li>Optimizer: CAME</li>        <li>Scheduler: Rex</li>        <li>UNet LR: 3e-4</li>        <li>LoRA type: LoCon</li>        <li>Steps: 36600</li>        <li>Network Rank (Dim/Alpha): 64/1</li>        <li>Precision: Full BF16</li>        <li>Hardware: 1x RTX 3090 24GB</li>      </ul>      <h4>Lumina 2</h4>      <ul>        <li>Program: Kohya sd-scripts SD3 branch</li>        <li>Optimizer: CAME</li>        <li>Scheduler: Rex</li>        <li>DiT LR: 1e-4</li>        <li>TE LR: None. TE outputs are cached</li>        <li>LoRA type: LoRA Lumina</li>        <ul>          <li>No LoCon needed as they'res no Conv layers.</li>        </ul>        <li>Steps: 36600 (batch 4)</li>        <li>Network Rank (Dim/Alpha): 64/32</li>        <li>Precision: Full BF16</li>        <li>Hardware: 1x RTX 3090 24GB</li>      </ul>    </div>  </div>  <div class=\"section-div\">    <h2>FAQ</h2>    <ul>      <li><b>Will this model be ported to X?</b> This model is planned to have versions trained on NoobAI-XL VPred, Illustrious 2.0 (ILXL2), and Neta Lumina (Lumina 2). More models will come later.      <ul>        <li>Lumina 2 version only works on Neta Lumina AES paths, such as a5nA and 1.0</li>        <li>The Illustrious 2 version works on Illustrious 1, 0.1, and NoobAI-XL Epsilon Pred.</li>        <li>V17 will have a Wan 2.2 5B</li>        <li>No Pony version is planned. Move to NoobXL or ILXL.</li>      </ul></li>      <li><b>Will there be a version for CivitAI?</b> No. I do not trust CivitAI anymore after the release of Illustrious 1.0 and them allowing closed-weight models, not to mention the overbearing censorship against messy diaper content, bad service, and overall greed.      <ul>        <li>V15.1 Update: Definitely not, especially since urine and diaper content have been expressly banned. Oh, and half the time the site crashes when you try to do anything. Good riddance.</li>      </ul></li>      <li><b>Anything else planned?</b>        <ul>          <li>Diaper changes</li>          <li>Open diapers and pull-ups</li>          <li>Diaper covers</li>          <li>Diaper pulls (like panty pulls)</li>          <li>Clean and used unworn diapers</li>          <li>Cloth diapers</li>          <li>Diaper pulls</li>          <li>The rest of the data in my dataset processed and tagged.</li>          <li>Etc.</li>        </ul>      </li>      <ul>    </ul>  </div>  <div class=\"section-div\">    <h2>License</h2>    <p>This LoRA model is provided under the <a href=\"https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md\">Apache License 2.0</a> license.</p>    <!-- <p>Training configurations and dataset will also be released later. You can use these to further train AIDL.</p> -->  </div>  <div class=\"section-div\">    <h2>Special Thanks</h2>    <ul>      <li>DangoKnight for training some of the test versions of this LoRA</li>      <li>Yatogami for contributing to the dataset.</li>      <li>Hugs288, Lopi99, and others in the NoobAI discord to for helping me get my LoRA training settings right.</li>    </ul>  </div>  <div class=\"section-div\">    <h2>Model Card Contact</h2>    <ul>      <p>I can be contacted on:</p>      <li><b>Matrix:</b> @mr_pops_alot:cutefunny.art</li>      <li><b>GitLab:</b> gitgud.io/mrpopsalot</li>      <li><b>All The Fallen:</b> @MrDoesNothingAlot</li>      <li><b>Discord:</b> 474149843724664854</li>    </ul>  </div></div>",
+  "civitai_deleted": false,
+  "favorite": false,
+  "exclude": false,
+  "db_checked": false,
+  "metadata_source": null,
+  "last_checked_at": 0,
+  "usage_tips": "{}"
+}

017.0/NoobAI-RF-F2Vae-1024/aidl-v017-noobai-rf-f2vae-1024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5df616867606e079b8c61c5e94583ebb2b43fda5c8d36e53ee151b7914b1df12
+size 509994656

Changelog.MD

@@ -63,10 +63,170 @@
   table {
     color: #24292e;
   }
+  .table-change-pos {
+    color: #33bb33;
+  }
+  .table-change-neg {
+    color: #bb3333;
+  }
 </style>
 
 <div class="main-div">
     <h1>AIDL: OmoAIShi Changelog</h1>
+    <p>Oh yea, training configs before V15 are written retroactively</p>
+    <!-- <div class="section-div">
+        <h2>V18: 2K Edition</h2>
+    </div> -->
+    <div class="section-div">
+        <h2>V17.1: Qwen3.5 gud Edition</h2>
+        <p>Qwen3.5 is GOOD.</p>
+        <ul>
+            <li>Added natural language captions to all concepts for Anima.</li>
+        </ul>
+    </div>
+    <div class="section-div">
+        <h2>V17: Pee-ka-poo Edition</h2>
+        <p>New update for AIDL: OmoAIShi (the diaper LoRA). Moar data means more better, right? Here's V17, with 725 more images in the dataset with perfectly balanced concepts.
+        <p>Also included are versions for two very new models: Chenkin RF trained at 1024px, and Anima trained at 512px (the model was trained on 512px anyway). Anima is based on Cosmos-Predict2 2B and supports NL and much more compositions than anything SDXL based. There's also the NoobAI RF test LoRAs because I had those ready too. Didn't train a NoobAI VPred or Lumina 2 version and there were too many images to do a run on 1536px (sorry!).</p>
+        <p>A new concept added to the list are covered diapers, where you can have diapered characters under pants and they will have bulges, complete with waistband peeks. There's new data for each of the preexisting concepts too, which makes generation of them better and more accurate to the training data..</p>
+        <ul>
+            <li>Added more data throughout all concepts. Image counts have been curated so that each concept is <i>exactly</i> balanced against the highest count concept.</li>
+            <li>Added new concept: <code>covered diaper</code>. This allows you to have those cute diaper bulges and waistband peeks</li>
+            <!-- <li>Added natural language captions to all images in the dataset.</li>
+                <ul>
+                    <li>The <code>diaper</code> and <code>peed diaper</code> images added pre V16 are hand captioned.</li>
+                    <li>Other images and newer images will use a combination of three VLMs summarized into one caption with tag grounding: JoyCaption Beta 1, MiMo Vision 7B, and Gemma 3 27B.</li>
+                </ul> -->
+            <li>Versions added:</li>
+              <ul>
+              <li>Anima @ 512</li>
+              <li>Chenkin RF @ 1024</li>
+              <li>NoobAI RF EQ-VAE @ 1024</li>
+              <li>NoobAI RF FLUX.2 VAE @ 1024</li>
+              <li>Illustrious 2 @ 1024</li>
+              </ul>
+            <li>Versions Removed:</li>
+              <ul>
+              <li>Lumina 2 @ 1024</li>
+              <li>NoobAI VPred @ 1024</li>
+              <li>Illustrious 2 @ 1536</li>
+              </ul>
+            <li>Replaced NoobAI VPred version with NoobAI RF (Rectified Flow) version</li>
+            <li>Removed <code>messing self</code> tags from <code>pooping in diaper</code> images since a secondary trigger is redundant</li>
+            <li>Removed <code>plain diaper</code> and <code>clean diaper</code> tags (and their pull-up variants). They were detrimental to generation and variations, since ideally a clean plain diaper should be what it defaults to anyway. Should help make <code>x tape diaper</code> and wetness indicators more consistent.</li>
+            <li>Replaced some upscaled Pixiv preview pics with their higher-res Fanbox variants.</li>
+            <li>Included tag and caption droupout for NoobAI, ILXL 2 versions</li>
+            <!-- <li>Removed NL. Not worth it since this was only a release for SDXL and SD1.5.</li> -->
+            <li>Increased Network Alpha to 32 from 1 on SDXL-based models. </li>
+            <li>Added new diaper design: <code>attento</code></li>
+            <li>Remove useless <code>anime</code>, <code>drawing</code> tags which ended up killing artist styles.</li>
+            <li>Fixed artist names to match the Danbooru/Sankaku/ATFBooru names.</li>
+            <ul>
+            <li><code>winopz</code> -> <code>win opz</code></li>
+            <li><code>oolong763</code> -> <code>kyoju</code></li>
+            <li><code>shinobu (appacandy)</code> -> <code>john doe shinobu</code></li>
+            <li><code>azuma (pixiv 38220217)</code> -> <code>azuma (azumapic)</code></li>
+            <li><code>stng_nicchi0609</code> -> <code>ikayaki-san</code></li>
+            <li><code>kamabok0</code> -> <code>akakama</code></li>
+            <li><code>kohaku (pixiv 29695938)</code> -> <code>kohakuwestale</code></li>
+            <li><code>aiueo (air377)</code> -> <code>air377</code></li>
+            <li><code>aonori_sss</code> -> <code>aonori sss</code> (this is mainly a formality of changing underscores to spaces)</li>            
+            </ul>
+            <li>BBCode converted readme for XenForo, Invision-based forums instead of a lazilly done screenshot.</li>
+            <li>This update has made OmoAIshi's image count surpass 1500.</li>
+        </ul>
+        <table>
+        <thead>
+          <th>Concept</th>
+          <th>V15 Count</th>
+          <th>V17 Count</th>
+          <th>Change</th>
+        </thead>
+          <tr>
+            <td>diaper</td>
+            <td>242</td>
+            <td>340</td>
+            <td class="table-change-pos">+98</td>
+          </tr>
+          <tr>
+            <td>pooping self</td>
+            <td>156</td>
+            <td>340</td>
+            <td class="table-change-pos">+184</td>
+          </tr>
+          <tr>
+            <td>poopy diaper</td>
+            <td>190</td>
+            <td>226</td>
+            <td class="table-change-pos">+36</td>
+          </tr>
+          <tr>
+            <td>peed pull-ups</td>
+            <td>99</td>
+            <td>226</td>
+              <td class="table-change-pos">+127</td>
+          </tr>
+          <tr>
+            <td>peed diaper</td>
+            <td>116</td>
+            <td>170</td>
+            <td class="table-change-pos">+54</td>
+          </tr>
+          <tr>
+            <td>pull-ups</td>
+            <td>115</td>
+            <td>170</td>
+            <td class="table-change-pos">+55</td>
+          </tr>
+          <tr>
+            <td>open diaper</td>
+            <td>71</td>
+            <td>170</td>
+            <td class="table-change-pos">+99</td>
+          </tr>
+          <tr>
+            <td>pooping in diaper</td>
+            <td>90</td>
+            <td>98</td>
+            <td class="table-change-pos">+8</td>
+          </tr>
+          <tr>
+            <td>covered diaper</td>
+            <td>----</td>
+            <td>98</td>
+            <td class="table-change-pos">+98</td>
+          </tr>
+          <tr>
+            <td>TOTAL</td>
+            <td>1075</td>
+            <td>1838</td>
+            <td class="table-change-pos">+725</td>
+          </tr>
+        </table>
+    </div>
+    <!-- <div class="section-div">
+        <h2>V16.1</h2>
+        <ul>
+            <li>Replaced NoobAI VPred version with NoobAI RF (Rectified Flow) version</li>
+            <li>Removed <code>messing self</code> tags from <code>pooping in diaper</code> images</li>
+            <li>Replaced some upscaled Pixiv preview pics with their higher-res Fanbox variants.</li>
+            <li>Included tag and caption droupout for NoobAI, ILXL 2, and SD1.5 versions</li>
+            <li>Removed NL. Not worth it since this was only a release for SDXL and SD1.5.</li>
+            <li>Remove useless <code>anime</code>, <code>drawing</code> tags which ended up killing artist styles.</li>
+            <li>Fixed artist names to match the Danbooru/Sankaku/ATFBooru names.</li>
+            <ul>
+            <li><code>winopz</code> -> <code>win opz</code></li>
+            <li><code>oolong763</code> -> <code>kyoju</code></li>
+            <li><code>shinobu (appacandy)</code> -> <code>john doe shinobu</code></li>
+            <li><code>azuma (pixiv 38220217)</code> -> <code>azuma (azumapic)</code></li>
+            <li><code>stng_nicchi0609</code> -> <code>ikayaki-san</code></li>
+            <li><code>kamabok0</code> -> <code>akakama</code></li>
+            <li><code>kohaku (pixiv 29695938)</code> -> <code>kohakuwestale</code></li>
+            <li><code>aiueo (air377)</code> -> <code>air377</code></li>
+            <li><code>aonori_sss</code> -> <code>aonori sss</code> (this is mainly a formality of changing underscores to spaces)</li>            
+            </ul>
+        </ul>
+    </div> -->
     <div class="section-div">
         <h2>V16: Tag Restructure Edition</h2>
         <p>Welcome to V16! Refined tags, another new customizable diaper element, and the new Neta Lumina architecture brings AIDL to the world of Diffusion Transformers. While the Lumina variant is the standout variant of AIDL, the SDXL variants can still hold its weight well. With the Gemma 2 2B TE that Neta Lumina has, such concepts like <code>covered diaper</code> are possible without having any images of that concept, as well as the ability for natural language to be used.</p>

Changelog.ja.md

@@ -0,0 +1,283 @@
+<style>
+  .main-div {
+    background-color: #9999ff; padding: 20px; border-radius: 10px; margin-bottom: 20px;
+  }
+  h1 {
+    color: #24292e;
+    margin-top: 0;
+    font-size: 25px;
+  }
+  h2 {
+    color: #24292e;
+    margin-top: 0;
+    font-size: 22px;
+  }
+  h3 {
+    color: #24292e;
+    margin-top: 0;
+    font-size: 20px;
+  }
+  h4 {
+    color: #24292e;
+    margin-top: 0;
+    font-size: 15px;
+  }
+  p {
+    color:#24292e;
+  }
+  a {
+    color: #0366d6;
+    text-decoration: none;
+  }
+  .section-div {
+    background-color: white;
+    padding: 15px;
+    border-radius: 8px;
+    margin: 15px 0;
+    box-shadow: 0 2px 4px rgba(0,0,0,0.1);
+  }
+  .subsection-div {
+    background-color: #bbb;
+    padding: 15px;
+    border-radius: 8px;
+    margin: 15px 0;
+    box-shadow: 0 2px 4px rgba(0,0,0,0.1);
+  }
+  ul {
+    margin-bottom: 0;
+    color: #24292e;
+  }
+  ol {
+    margin-bottom: 0;
+    color: #24292e;
+  }
+  td {
+    margin-bottom: 0;
+    color: #24292e;
+  }
+  code {
+    background-color: #333;
+    padding: 3px 6px;
+    border-radius: 4px;
+  }
+  table {
+    color: #24292e;
+  }
+  .table-change-pos {
+    color: #33bb33;
+  }
+  .table-change-neg {
+    color: #bb3333;
+  }
+</style>
+
+<div class="main-div">
+    <h1>AIDL：OmoAIShiの更新履歴</h1>
+    <p>申し訳ありませんが、V16以前の更新履歴はまだ日本語に翻訳されていません。</p>
+    <!-- <div class="section-div">
+        <h2>V18: 2K Edition</h2>
+    </div> -->
+    <div class="section-div">
+        <h2>V17: Pee-ka-poo版</h2>
+        <p>新しいAIDL：OmoAIShi（おむつLoRA）更新です. データが増えれば増えるほど、モデルは良くなるはずでしょう？色々な概念に基づく725枚の画像をデータに組み込んで、V17版は公開しました。</p>
+        <p>Chenkin RFおよびAnimaというモデル向けLoRAバーションもあります。そのLoRA両方は1024pxで訓練されました。AnimaはCosmos-Predict2 2Bに基づいたモデルで、SDXLに基づいたモデルより自然言語を分かるから、色々な概念を生成出来ます。すでに準備したから、NoobAI RFのテストLoRAもあります。NoobAI VPred版やLumina 2版は訓練していなくて、画像の数が多すぎだから1536px版も訓練しなくてすみません！</p>
+        <p>「着ている服の下にあるおむつ」という概念を含めました。見える膨らみや見えるおむつのウエストバンドを含んで、ズボンとか服の下にオムツを穿いているキャラクターの画像を生成出来ます。既存の概念も新しいデータを組み込んだので、生成された画像の質と訓練データの同調は高くなります。</p>
+        <ul>
+            <li>すべての概念についてデータを加えました。各々の概念の画像数は最も数が多い概念に比べたら、バランスはピッタリ正確のために、画像の分量はじっくり調節しました。</li>
+            <li>新しい概念を加えました：<code>covered diaper</code>（着ている服の下にあるおむつ）。この概念を入力したら、見える膨らみとウエストバンドを含んで、着ている服の下にあるオムツを生成出来ます。</li>
+            <!-- <li>Added natural language captions to all images in the dataset.</li>
+                <ul>
+                    <li>The <code>diaper</code> and <code>peed diaper</code> images added pre V16 are hand captioned.</li>
+                    <li>Other images and newer images will use a combination of three VLMs summarized into one caption with tag grounding: JoyCaption Beta 1, MiMo Vision 7B, and Gemma 3 27B.</li>
+                </ul> -->
+            <li>新しいバーション：</li>
+              <ul>
+              <li>Anima @ 512</li>
+              <li>Chenkin RF @ 1024</li>
+              <li>NoobAI RF EQ-VAE @ 1024</li>
+              <li>NoobAI RF FLUX.2 VAE @ 1024</li>
+              <li>Illustrious 2 @ 1024</li>
+              </ul>
+            <li>外したバーション：</li>
+              <ul>
+              <li>Lumina 2 @ 1024</li>
+              <li>NoobAI VPred @ 1024</li>
+              <li>Illustrious 2 @ 1536</li>
+              </ul>
+            <li>NoobAI VPred版はNoobAI RF (Rectified Flow)版に取って代わりました。</li>
+            <li><code>pooping in diaper</code>の画像から<code>messing self</code>というタグは被っているから外しました。</li>
+            <li>パンツタイプのおむつのためにタグを含み、<code>plain diaper</code>というタグおよび<code>clean diaper</code>というタグを外しました。白色でキレイなおむつは普通のはずだから、特にタグが必要がないので、そのタグは生成の質を落としました。<code>x tape diaper</code>と濡れインジケーターの一貫はもっと高くなるはずです。</li>
+            <li>いくつかの画像はPixivからのサンプルは、解像度が高いFanboxからの画像を替えました。</li>
+            <li>NoobAIとILXL 2版はタグとキャプションドロップアウトを加えました。</li>
+            <!-- <li>Removed NL. Not worth it since this was only a release for SDXL and SD1.5.</li> -->
+            <li>SDXLに基づいたモデルのネットワークアルファは１から３２に増やしました。</li>
+            <li>新しいおむつのプリントを加えました：<code>attento</code></li>
+            <li><code>anime</code>というタグおよび<code>drawing</code>というタグは不要で芸術様式を削除してしまうから、そのタグを外しました。</li>
+            <li>芸術家の名はDanbooru/Sankaku/ATFBooruの表記に名を統一しました。</li>
+            <ul>
+            <li><code>winopz</code> -> <code>win opz</code></li>
+            <li><code>oolong763</code> -> <code>kyoju</code></li>
+            <li><code>shinobu (appacandy)</code> -> <code>john doe shinobu</code></li>
+            <li><code>azuma (pixiv 38220217)</code> -> <code>azuma (azumapic)</code></li>
+            <li><code>stng_nicchi0609</code> -> <code>ikayaki-san</code></li>
+            <li><code>kamabok0</code> -> <code>akakama</code></li>
+            <li><code>kohaku (pixiv 29695938)</code> -> <code>kohakuwestale</code></li>
+            <li><code>aiueo (air377)</code> -> <code>air377</code></li>
+            <li><code>aonori_sss</code> -> <code>aonori sss</code>（主に下線は間隔に替えたから）</li>            
+            </ul>
+            <li>この更新で、OmoAIshiの画像数は1500枚以上になりました。</li>
+        </ul>
+        <table>
+        <thead>
+          <th>概念</th>
+          <th>V15に数</th>
+          <th>V17に数</th>
+          <th>差</th>
+        </thead>
+          <tr>
+            <td>diaper（テープタイプのおむつ）</td>
+            <td>242</td>
+            <td>340</td>
+            <td class="table-change-pos">+98</td>
+          </tr>
+          <tr>
+            <td>pooping self（着衣脱糞）</td>
+            <td>156</td>
+            <td>340</td>
+            <td class="table-change-pos">+184</td>
+          </tr>
+          <tr>
+            <td>poopy diaper（ウンチされたテープタイプおむつ）</td>
+            <td>190</td>
+            <td>226</td>
+            <td class="table-change-pos">+36</td>
+          </tr>
+          <tr>
+            <td>peed pull-ups（オシッコされたパンツタイプのおむつ）</td>
+            <td>99</td>
+            <td>226</td>
+              <td class="table-change-pos">+127</td>
+          </tr>
+          <tr>
+            <td>peed diaper（オシッコされたテープタイプのおむつ）</td>
+            <td>116</td>
+            <td>170</td>
+            <td class="table-change-pos">+54</td>
+          </tr>
+          <tr>
+            <td>pull-ups（パンツタイプのおむつ）</td>
+            <td>115</td>
+            <td>170</td>
+            <td class="table-change-pos">+55</td>
+          </tr>
+          <tr>
+            <td>open diaper（開いているおむつ）</td>
+            <td>71</td>
+            <td>170</td>
+            <td class="table-change-pos">+99</td>
+          </tr>
+          <tr>
+            <td>pooping in diaper（おむつにウンチする）</td>
+            <td>90</td>
+            <td>98</td>
+            <td class="table-change-pos">+8</td>
+          </tr>
+          <tr>
+            <td>covered diaper（着ている服の下にあるオムツ）</td>
+            <td>----</td>
+            <td>98</td>
+            <td class="table-change-pos">+98</td>
+          </tr>
+          <tr>
+            <td>総計</td>
+            <td>1075</td>
+            <td>1838</td>
+            <td class="table-change-pos">+725</td>
+          </tr>
+        </table>
+    </div>
+    <!-- <div class="section-div">
+        <h2>V16.1</h2>
+        <ul>
+            <li>Replaced NoobAI VPred version with NoobAI RF (Rectified Flow) version</li>
+            <li>Removed <code>messing self</code> tags from <code>pooping in diaper</code> images</li>
+            <li>Replaced some upscaled Pixiv preview pics with their higher-res Fanbox variants.</li>
+            <li>Included tag and caption droupout for NoobAI, ILXL 2, and SD1.5 versions</li>
+            <li>Removed NL. Not worth it since this was only a release for SDXL and SD1.5.</li>
+            <li>Remove useless <code>anime</code>, <code>drawing</code> tags which ended up killing artist styles.</li>
+            <li>Fixed artist names to match the Danbooru/Sankaku/ATFBooru names.</li>
+            <ul>
+            <li><code>winopz</code> -> <code>win opz</code></li>
+            <li><code>oolong763</code> -> <code>kyoju</code></li>
+            <li><code>shinobu (appacandy)</code> -> <code>john doe shinobu</code></li>
+            <li><code>azuma (pixiv 38220217)</code> -> <code>azuma (azumapic)</code></li>
+            <li><code>stng_nicchi0609</code> -> <code>ikayaki-san</code></li>
+            <li><code>kamabok0</code> -> <code>akakama</code></li>
+            <li><code>kohaku (pixiv 29695938)</code> -> <code>kohakuwestale</code></li>
+            <li><code>aiueo (air377)</code> -> <code>air377</code></li>
+            <li><code>aonori_sss</code> -> <code>aonori sss</code> (this is mainly a formality of changing underscores to spaces)</li>            
+            </ul>
+        </ul>
+    </div> -->
+    <div class="section-div">
+        <h2>V16: Tag Restructure Edition</h2>
+        <p>Welcome to V16! Refined tags, another new customizable diaper element, and the new Neta Lumina architecture brings AIDL to the world of Diffusion Transformers. While the Lumina variant is the standout variant of AIDL, the SDXL variants can still hold its weight well. With the Gemma 2 2B TE that Neta Lumina has, such concepts like <code>covered diaper</code> are possible without having any images of that concept, as well as the ability for natural language to be used.</p>
+        <p>Wetness indicators are now tagged to help stop the wetness indicators from appearing during pantypooping. You can also go and set up the wetness indicators to any color the model recognizes. The most trained colors are yellow and blue, which are common colors used for diaper wetness indicators, but if you use Neta Lumina, you can also set it to any color it knows.</p>
+        <p>Since TA went SFW only, and neither SeaArt and PixAI want to host the Lumina version, so this LoRA will only be on here, HF, and GitLab. I will try getting AIDL on alternative model sources such as LoRA Torrent and Diffusion Arc as well.</p>
+        <ul>
+            <li>Added handmade natural language captions to <code>diaper</code> and <code>peed diaper</code> concepts images in the dataset.</li>
+                <ul>
+                    <li>The <code>diaper</code> and <code>peed diaper</code> concepts are hand captioned.</li>
+                    <li>Other images and newer images will use a combination of three VLMs summarized into one caption with tag grounding: JoyCaption Beta 1, MiMo Vision 7B, and Gemma 3 27B. This will be done on V17.</li>
+                    <li>This is to ensure that this LoRA is easily usable on models such as ~~SD3.5~~ Neta Lumina and any other future natural language models.</li>
+                </ul>
+            <li>Added artist tags to all identifiable artworks due to an accidental discovery where AIDL also learned artist styles whn there was enough data.</li>
+            <li>Added new diaper design: <code>merries</code></li>
+            <li>Tagged <code>wetness indicator</code>s as an attempt to separate wetness indicators from soiling (apparent when doing panty pees/poops).</li>
+            <li>Redone prints and made sure to catch as many prints as possible, including the use of <code>polka dot diaper</code>, <code>orientation indicator</code>, <code>size indicator</code></li>
+            <li>Added LoRA Manager metadata</li>
+        </ul>
+    </div>
+    <div class="section-div">
+        <h2>V15.1</h2>
+        <ul>
+            <li>Added natural language captions to the peed diaper concept.</li>
+            <li>Added new Illustrious 2 variant trained on 1536x1536. This also replaces the Illustrious 1 variant, as it also works on Illustrious 1</li>
+            <li>Switched to training with 67372a's Kohya Easy Scripts instead of bmaltais' kohya_ss</li>
+            <li>Moved internal AIDL stuff to a GitLab group. </li>
+        </ul>
+    </div>
+    <div class="section-div">
+        <h2>V15</h2>
+        <ul>
+            <li>First public alpha of OmoAIShi</li>
+            <li>Added more clean, wet, and messy diaper art</li>
+            <li>Added more clean and wet pull-up art</li>
+            <li>Added new concept: <code>open diaper</code></li>
+            <li>This update has made OmoAIshi's image count surpass 1000.</li>
+        </ul>
+    </div>
+    <div class="section-div">
+        <h2>V14.4</h2>
+        <ul>
+        <li>Added <code>damp diaper</code> tag to help prevent very lightly soiled diapers from being used on the peed diaper tag.</li>
+        <li>Lowered LR to 0.0002 (pre batch scaling)</li>
+        </ul>
+    </div>
+    <div class="section-div">
+        <h2>V14</h2>
+        <ul>
+            <li>Added more clean and wet diaper art. Mainly of the two-taped diaper kind.</li>
+            <li>Added more pantypooping images.</li>
+            <li>Added new tag: <code>medical print</code>. Use for diapers that look like Attends/Abenas/your average adult diaper. Keep in mind that you will still need to use the <code>print diaper</code> tag.</li>
+            <li><code>front-print diaper</code> now has new images for landing zone prints.</li>
+        </li>
+    </div>
+    <div class="section-div">
+        <h2>V13</h2>
+        <ul>
+            <li>Added more pantypooping and pants pooping images.</li>
+            <li>This update has made OmoAIshi's image count surpass 750.</li>
+        </ul>
+    </div>
+</div>

OmoAIShi Documentation.odt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e92b7c46aff2f9b889954e1dfd61e58cc296ae2045d22fe50519b4ebe568e87
+size 4903702

README.booth.md

@@ -0,0 +1,25 @@
+# ENGLISH USERS | 英語のユーザー
+SEE THE LINKS BELOW FOR ENGLISH DOCUMENTATION<br>
+\>>>>>>>>> http://huggingface.co/mrpopsalot/aidl-omoaishi <<<<<<<<<<br>
+\>>>>>>>>> http://gitgud.io/mrpopsalot/aidl-omoaishi <<<<<<<<<
+
+OmoAIshiは他のモデルとLoRAが複数の生成出来ない概念を生成出来て、おむつの着用と使用に関する概念向け、最も包括的な複数概念出来るLoRAです。同じモデルで複数概念を訓練出来るから、普通のLoRA形の代わりにLyCORIS LoConが使っています。パンツを穿いている女の子はおしまい！
+
+## 訓練されたモデル:
+NoobAI-XL RF EQ-VAE: CabalResearch/NoobAI-RectifiedFlow-Experimental/NoobAI-RF-v0.2-Base @ 1024
+NoobAI RF テストモデルとも使用できます。
+NoobAI-XL RF FLUX.2VAE: CabalResearch/NoobAI-Flux2VAE-RectifiedFlow-0.3 @ 1024
+Illustrious 2: OnomaAIResearch/Illustrious-XL-v2.0 @ 1024
+Illustrious 1、 0.1、と NoobAI EPSもはコンパチ。
+
+<h1>Features ・ できること</h1>
+<ul>
+    <li><b>テープタイプのおむつ:</b> 2枚や4枚のテープとプリントと無地なおむつは生成できる.  ブランドおむつと特異的なデサインも練習したも。まだ特異的なデサインは練習はとっぷりないと生成は詳しくないかもしれない。</li>
+    <li><b>ぱんつタイプおむつ:</b> プルアップも練習したもから、いろいろなデサインにプロンプトできる。</li>
+    <li><b>尿もれなおむつ:</b> びしょのおむつはいろいろな濡れ度はできるから、ちょっと湿気っぽいよりびしょぬれと溢れている。「溢れ」 といえば、正しく溢れは腿から。</li>
+    <li><b>おむつとぱんつ脱糞:</b> いろいろなうんち汚れ度は練習した、バーストも、ともにデュアル尿と便漏れにできる 。ズボンやドレスや短パンも。 コンパチは保しないば（トレイニング資料数より小さい ）スカトロは見られかもしれない。</li>
+    <li><b>開いてなおむつ:</b> 今や開いてなおむつは生成できる、プロンプトがあるば潤いと汚れもにある。</li>
+    <li><b>違い姿勢はつじつまが合うの成果:</b> このモデルは多様性の芸スタイルと姿勢に練習したから、多い姿勢とほしいのスタイルに生成しには正しい、ともに立ちも蹲も寝ろも下からアップスカートもなど</li>
+</ul>
+
+# How to Useㅣ 使い方

README.ja.md

@@ -0,0 +1,449 @@
+---
+tags:
+- text-to-image
+- stable-diffusion
+- lora
+- diaper
+- abdl
+- scat
+- omorashi
+- concept
+- diffusers
+- not-for-all-audiences
+license: apache-2.0
+base_model:
+- ChenkinRF/ChenkinNoob-XL-v0.2-Rectified-Flow
+- Laxhar/noobai-XL-Vpred-1.0
+- OnomaAIResearch/Illustrious-XL-v2.0
+- neta-art/neta-lumina
+---
+<style>
+  .main-div {
+    background-color: #9999ff; padding: 20px; border-radius: 10px; margin-bottom: 20px;
+  }
+  h1 {
+    color: #24292e;
+    margin-top: 0;
+    font-size: 25px;
+  }
+  h2 {
+    color: #24292e;
+    margin-top: 0;
+    font-size: 22px;
+  }
+  h3 {
+    color: #24292e;
+    margin-top: 0;
+    font-size: 20px;
+  }
+  h4 {
+    color: #24292e;
+    margin-top: 0;
+    font-size: 15px;
+  }
+  p {
+    color:#24292e;
+  }
+  a {
+    color: #0366d6;
+    text-decoration: none;
+  }
+  .section-div {
+    background-color: white;
+    padding: 15px;
+    border-radius: 8px;
+    margin: 15px 0;
+    box-shadow: 0 2px 4px rgba(0,0,0,0.1);
+  }
+  .subsection-div {
+    background-color: #bbb;
+    padding: 15px;
+    border-radius: 8px;
+    margin: 15px 0;
+    box-shadow: 0 2px 4px rgba(0,0,0,0.1);
+  }
+  ul {
+    margin-bottom: 0;
+    color: #24292e;
+  }
+  ol {
+    margin-bottom: 0;
+    color: #24292e;
+  }
+  td {
+    margin-bottom: 0;
+    color: #24292e;
+  }
+  code {
+    background-color: #333;
+    padding: 3px 6px;
+    border-radius: 4px;
+  }
+  table {
+    color: #24292e;
+  }
+</style>
+<div class="main-div">
+  <h1>AIDL: OmoAIShi</h1>
+  <div style="background-color: #ffff99; padding: 20px; border-radius: 10px; margin-bottom: 20px;">
+  <img src="docs/Images/v017-thumb-JA.png">
+  <h3>V17: Pee-ka-poo Edition<br>Anima, Chenkin RF, NoobAI RF EQ-VAE, NoobAI RF FLUX.2 Vae, Illustrious 2向け</h3>
+  <div style="background-color: #ff9999; padding: 20px; border-radius: 10px; margin-bottom: 20px;">
+  <h3>このモデルは**NSFW**画像向け、＊二次元のキャラ＊しか訓練していません.</h3>
+  <h3>公開のアルファ版です. 生成された画像は最終的なモデルを表すものではありません.</h3>
+  </div>
+    <a href="https://gitgud.io/mrpopsalot/aidl-omoaishi"><img alt="Static Badge" src="https://img.shields.io/badge/GitLab-orange?logo=gitlab&logoColor=white&style=for-the-badge"></a>
+    <a href="https://huggingface.co/mrpopsalot/aidl-omoaishi"><img alt="Static Badge" src="https://img.shields.io/badge/HuggingFace-yellow?logo=huggingface&logoColor=white&style=for-the-badge"></a>
+    <a href="https://allthefallen.moe/forum/index.php?resources/aidl-omoaishi.7465/"><img alt="Static Badge" src="https://img.shields.io/badge/AllTheFallen-pink?logo=outlook&logoColor=white&style=for-the-badge"></a>
+    <img alt="GitLab License" src="https://img.shields.io/gitlab/license/mrpopsalot%2Faidl-omoaishi?gitlab_url=http%3A%2F%2Fgitgud.io&style=for-the-badge">
+  </div>
+  <div class="section-div">
+    <h2>概要</h2>
+    <p>OmoAIshiは他のモデルとLoRAが複数の生成出来ない概念を生成出来て、おむつの着用と使用に関する概念向け、最も包括的な複数概念出来るLoRAです。同じモデルで複数概念を訓練出来るから、普通のLoRA形の代わりにLyCORIS LoConが使っています。パンツを穿いている女の子はおしまい！</p>
+    <ul>
+      <li><b>訓練されたモデル:</b></li>
+      <ul>
+        <li><b>Anima:</b> circlestone-labs/Anima @ 1024</li>
+        <li><b>Chenkin RF:</b> ChenkinRF/ChenkinNoob-XL-v0.2-Rectified-Flow @ 1024</li>
+        <li><b>NoobAI-XL RF EQ-VAE:</b> CabalResearch/NoobAI-RectifiedFlow-Experimental/NoobAI-RF-v0.2-Base @ 1024</li>
+          <ul>
+          <li>NoobAI RF テストモデルとも使用できます。</li>
+          </ul>
+        <li><b>NoobAI-XL RF FLUX.2VAE:</b> CabalResearch/NoobAI-Flux2VAE-RectifiedFlow-0.3 @ 1024</li>
+        <!-- <li><b>NoobAI-XL VPred:</b> Laxhar/noobai-XL-Vpred-1.0 @ 1024</li>
+          <ul>
+          <li>Also works on the NoobAI RF test models.</li>
+          </ul> -->
+        <li><b>Illustrious 2:</b> OnomaAIResearch/Illustrious-XL-v2.0 @ 1024</li>
+          <ul>
+          <li>Illustrious 1、 0.1、と NoobAI EPSもはコンパチ。</li>
+          </ul>
+        <!-- <li><b>Lumina Image 2:</b> neta-art/neta-lumina 1.0 @ 1024</li> -->
+      </ul>
+      <li><b>開発元:</b> Mr Pops Alotさん</li>
+      <li><b>モデルタイプ:</b> LyCORIS LoCon</li>
+      <li><b>ライセンス:</b> Apache 2.0</li>
+    </ul><br>
+    <p>これはAIDLシリーズの最初のLoRAです。<b>「AIDL: The AI Diaper LyCORIS」</b> はモデルにオムツやその他のABDLに関する概念を教えるLoRAのシリーズを目的としています。</p>
+    <a href="https://gitgud.io/mrpopsalot/aidl-omoaishi"><img src="https://img.shields.io/badge/OmoAIShi-blue?style=for-the-badge&label=おむつ"></a>
+    <a href="https://huggingface.co/mrpopsalot/aidl-mini"><img src="https://img.shields.io/badge/Mini-brown?style=for-the-badge&label=おむつ%20(試験的!)"></a>
+    <a href="https://gitgud.io/pops-aidl/sd-beginners-guide"><img src="https://img.shields.io/badge/SD駆け出しのガイド (英語)-yellow?style=for-the-badge&label=はじめの？"></a>
+    <a href="https://gitgud.io/pops-aidl/lora-training-guide"><img src="https://img.shields.io/badge/LoRAトレーニングのガイド　(英語)-teal?style=for-the-badge"></a>
+  </div>
+  <div class="section-div">
+    <h2>ショーケース</h2>
+    <p><img src="docs/Images/aidl-v017-showcase.webp"></p>
+  </div>
+  <div class="section-div">
+    <h2>機能</h2>
+    <ul>
+      <li><b>テープタイプのおむつ：</b> ２枚テープ式、４枚テープ式、プリント柄、無地のおむつは生成出来ます。ブランドと特定のデサインのおむつの概念も訓練されました。しかし、この特定のデサインはまだ完全に訓練されていないからモデルの生成は詳しくないかもしれません。</li>
+      <li><b>パンツタイプのおむつ：</b> パンツタイプのおむつも訓練されて、色々なデサインに生成出来ます。</li>
+      <li><b>小便されたおむつ：</b> シットリからオシッコがあふれているまで、色々のお漏らし加減のおむつを生成出来ます。あふれているオシッコは太もものそばからきちんと現れます。</li>
+      <li><b>おむつとパンツに脱糞（着衣脱糞）：</b> あふれているうんちを含んで、色々の脱糞加減で、または同時にオシッコとうんちお漏らしの概念を訓練されました。ズボンやショーツやドレスに脱糞の概念も訓練されました。しかし、訓練データは少ないから生成の性能は完全ではないかもしれません。たまに溢れたうんちが現れる。</li>
+      <li><b>開いているおむつ：</b> 開いているおむつは今や生成出来ます。プロンプトしたら、オムツにウンチやオシッコも生成出来ます。</li>
+      <li><b>着ている服の下にあるおむつ：</b> 見える膨らみとウエストバンドを含んで、着ている服の下にあるオムツを生成出来ます。今やおむつを穿いている子は目立たない様におむつを見せられます。</li>
+      <li><b>姿勢が違っても一貫した生成出来ます：</b> どんな姿勢や芸術様式が欲しがっていても生成が一貫するために、モデルは様々の姿勢と芸術様式に訓練されました。例えば立っている人でも、しゃがんでいる人でも、横たわっている人でも、アップスカートのアングルでも、生成出来ます。</li>
+    </ul>
+  </div>
+  <div class="section-div">
+    <h2>使い方</h2>
+    <div class="subsection-div">
+      <h3>テープタイプのおむつを生成する方法</h3>
+      <p>下記の英語の用語を入力して：<code>diaper</code>（テープタイプのおむつ）、あるいは<code>in a diaper</code>（テープタイプのおむつを穿いている）。</p>
+      <ul>
+      <li>テープの数を選択ために、下記の英語の用語を入力して：<code>two taped diaper</code>（２枚テープ式のおむつ）、あるいは<code>four tape diaper</code>（４枚テープ式のおむつ）。</li>
+      <li><code>print diaper</code>（プリント柄のおむつ）を入力したら、柄があるおむつを生成します。<code>print diaper</code>を入力しなくて、柄がない無地のおむつを生成されます。</li>
+      <li><code>front-print diaper</code>（前側にプリント柄のおむつ）と<code>back-print diaper</code>（後ろ側にプリント柄のおむつ）も入力して、柄の位置を選択出来ます。<a href="https://danbooru.donmai.us/tags?commit=Search&search%5Bhide_empty%5D=yes&search%5Bname_or_alias_matches%5D=%2A_print&search%5Border%5D=count">Danbooruのプリントの表</a>を参考にして使って下さい.</li>
+      <li><code>yellow wetness indicator</code>（黄色の濡れインジケーター）、あるいは<code>blue wetness indicator</code>（青色濡れインジケーター）を入力したら、濡れインジケーターがあるおむつを生成出来ます。</li>
+      </ul>
+      <p>プリント柄おむつの例え (特定の訓練をされていないから、生成出来るかどうかは不明です）：</p>
+      <ul>
+        <li><code>pampers</code>（パンパース）</li>
+        <li><code>huggies</code></li>
+        <li><code>luvs</code></li>
+        <li><code>abuniverse</code>（ABU)</li>
+        <li><code>merries</code></li>
+        <li><code>attento</code>（アテント）</li>
+      </ul>
+    </div>
+    <div class="subsection-div">
+      <h3>パンツタイプのおむつを生成する方法</h3>
+      <p><code>pull-ups</code>（パンツタイプのおむつ）という英語の用語を入力したら、パンツタイプのおむつの画像を生成出来ます。テープタイプのおむつと同じくけれど、<code>diaper</code>の代わりに<code>pull-ups</code>を入力して下さい。</p>
+    </div>
+    <div class="subsection-div">
+      <h3>汚れたおむつ</h3>
+      <p><b>小便されたおむつ：</b><code>peed diaper</code>（オシッコされたおむつ）という英語の用語を入力したら、小便されたおむつの画像を生成出来ます。さらに、おむつの濡れの加減を調節出来ます。もし調節しなければ、たまたまにオシッコであふれているオムツを生成されています。</p>
+      <ol>
+        <li><code>wet diaper</code>（濡れたおむつ）</li>
+        <li><code>soaked diaper</code>（ビショビショなおむつ）</li>
+        <li><code>drenched diaper</code>（すごくビショビショなおむつ）</li>
+        <li><code>leaking diaper</code>（オシッコであふれているオムツ）、<code>pee on legs</code>（脚にオシッコ）</li>
+      </ol>
+      <br>
+      <p><b>大便されたおむつ：</b> <code>poopy diaper</code>（ウンチされたおむつ）という英語の用語を入力したら、大便されたおむつの画像を生成出来ます。さらに、おむつの汚さの加減を調節出来ます。もし調節しなければ、たまたまにウンチであふれているオムツを生成されています。</p>
+      <ol>
+        <li><code>messy diaper</code>（大きいウンチされたおむつ）</li>
+        <li><code>packed diaper</code>（超大きいウンチされたおむつ）</li>
+        <li><code>loaded diaper</code>（すごく超大きいウンチされたおむつ）</li>
+        <li><code>diaper blowout</code>（ウンチであふれているオムツ）、<code>poop on legs</code>（脚にウンチ）</li>
+      </ol>
+      <br>
+      <p>さらに、<code>smell</code>（臭い）を入力したら、ウンチからの臭いガスも生成出来ます。</p>
+      <p>もっと汚れたおむつが欲しがっているなら、入力されたタグの重みの加減を調節出来ます。0.9から1.5までの重みは普段に効きます。</p>
+      <table>
+        <th>テープタイプのおむつ</th>
+        <th>パンツタイプのおむつ</th>
+        <tr>
+        <td><img src="docs/Images/unidesSoil_00016_.png"></td>
+        <td><img src="docs/Images/pullUpSoil_00001_.png"></td>
+        </tr>
+      </table>
+      <p>あふれているオムツも生成出来ます：</p>
+      <table>
+        <th>小便</th>
+        <th>大便</th>
+        <tr>
+        <td><img src="docs/Images/diaperLeak_00001_.png"></td>
+        <td><img src="docs/Images/diaperBlowout_00002_.png"></td>
+        </tr>
+      </table>
+    </div>
+    <div class="subsection-div">
+      <h3>着衣脱糞</h3>
+      <p><code>pooping self</code>（ウンチお漏らし）という英語の用語を入力したら、着衣脱糞の画像を生成出来ます。さらに、<code>poopy underwear</code>（ウンチで汚れた下着）と<code>poopy clothes</code>（ウンチで汚れた服）という英語の用語を入力したら、汚れているパンツと他の穿いている服（ズボンとかドレスとか）を生成出来ます。
+      </p>
+      <img src="docs/Images/unidesSoil_00017_.png">
+      <p>多種の下着を生成出来ます！</p>
+      <img src="docs/Images/pantyPoops_2025-06-19-224722.webp">
+      <p>おむつの画像を生成するために、<code>poopy diaper</code>（ウンチされたおむつ）という英語の用語を入力して下さい。<code>pooping self</code>（ウンチお漏らし）という英語の用語も効くかもしれないけれど、<code>poopy diaper</code>（ウンチされたおむつ）の効果が高いです。</p>
+    </div>
+    <div class="subsection-div">
+      <h3>開いているおむつ</h3>
+      <p><code>open diaper</code>（開いているおむつ）という英語の用語を入力したら、開いているおむつの画像を生成出来ます。</p>
+      <ul>
+        <li>さらに、汚れたおむつを生成するために、<code>peed diaper</code>（オシッコされたおむつ）または<code>poopy diaper</code>（ウンチされたおむつ）という英語の用語も入力出来ます。</li>
+        <li>生殖器を生成するために、<code>pussy</code>（おまんこ）または<code>penis</code>（おちんちん）という英語の用語も入力出来ます。</li>
+      </ul>
+      <img src="docs/Images/openDiaper_00001_.png">
+    </div>
+    <div class="subsection-div">
+      <h3>着ている服の下にあるオムツ</h3>
+      <p><code>covered diaper</code>（着ている服の下にあるオムツ）という英語の用語を入力したら、見える膨らみを含んで着ている服の下にあるオムツの画像を生成出来ます。と、着ている服の下にあるオムツを生成出来ます。他の服より、ズボンとショーツの下になら効果が高いです。</p>
+      <ul>
+        <li>さらに、<code>diaper peek</code>��見えるおむつ）という英語の用語を入力したら、見えるおむつのウエストバンドを含む画像を生成出来ます。おむつの色も選択出来ます。</li>
+      </ul>
+      <img src="docs/Images/coveredDiaper_00002_.png">
+    </div>
+  </div>
+  <div class="section-div">
+    <h2>偏見、危険、制限</h2>
+    <p>今、モデルは下記の概念で困難されています：</p>
+    <ul>
+      <li>柄と色がないパンツタイプのおむつ。</li>
+      <li>開いているおむつ</li>
+      <ul>
+        <li>他の概念に比べたら、開いているおむつのデータが足りないから、生成された開いているおむつの形はあまり正しくないです。</li>
+      </ul>
+      <li>きれいでも汚れているでも、穿いていないおむつ。</li>
+      <li>おむつにぱんつに以外の着衣脱糞。</li>
+      <li>レオタードとボディスーツの下にあるおむつ。</li>
+      <li>ケモノ</li>
+      <li>落ちているとかの複雑なポーズ。</li>
+    </ul>
+    <br>
+    <p>さらに、このLoRAには制限があります：</p>
+    <ul>
+      <li>特に着衣脱糞についての用語を入力しなくても、<code>smell</code>（臭い）を入力したら、着衣脱糞の画像を生成されてしまうかもしれません。</li>
+      <li><code>poopy diaper</code>（ウンチされたおむつ）を「negatives」に入力しなければ、ウンチがないオシッコされたおむつにはウンチの膨らみが見えるかもしれません。</li>
+      <li>今、ウンチされたパンツタイプのおむつのデータがないから、モデルはウンチで汚れた下着のデータで訓練されています。</li>
+      <li><code>diaper blowout</code>（ウンチであふれているオムツ）または<code>poop on legs</code>（脚にウンチ）を入力しなくても、ウンチされたおむつからウンチがあふれるかもしれません。</li>
+      <li>前側にプリント柄のおむつとか、いくつかのプリント柄にあってウンチされたおむつの画像の質が高くないです。</li>
+      <ll>いくつかの芸術様式によると、ウンチされたおむつと着衣脱糞の生成された画像の質が高くないかもしれません。</li>
+      <!-- <li>In the Lumina 2 LoRA, you need to prompt for "wet diaper" as well with "peed diaper" to get a pee soaked pad.</li> -->
+      <li>「Rouwei Gemma」というSDXL異型を使ってもいいが、パンツタイプのおむつしか生成出来ません。</li>
+    </ul>
+  <p>もし生成された画像の質が高くないなら、LoRAの重みを増加して下さい。</p>
+  <div style="background-color: #ff9999; padding: 20px; border-radius: 10px; margin-bottom: 20px;">
+    <p> このLoRAの作者はユーザーからの悪意の生成でも責任をどうにも取れません。ユーザーは非道徳的な生成を含め、すべての生成について責任を取ります。<b>このLoRAを使っている際にすべての法規および利用規約を守らなければなりません。このLoRAの使用後にサイトからBANされるとか逮捕されるとかの場合は、作者は責任を取りません。</b></p>
+    <p><b>CivitAIの利用規約はオムツやスカトロを禁止されているから、このLoRAはCivitAIの利用規約を反します。AIDLからの生成された画像をCiviAIに投稿しないで下さい。</b></p>
+  </div>
+  </div>
+  <div class="section-div">
+    <h2>訓練について</h2>
+    <p>訓練データのために、1800以上の画像を含められます。<b>二次元の画像しか含められませんでした。</b></p>
+    <p>モデルには<b>人工のデータは含められません</b>。自動的にタグを割り当てるソフトはこの概念をよく出来ないから、ダンボールの様式のタグは<b>すべて手動的にされました</b>。自然言語処理のために画像キャプションは手動的で作成されて、V17は公開される際にJoyCaption Beta 1とGemma 3 27Bの出力も含める予定です。</p>
+    <div class="subsection-div">
+      <h3>訓練の手順</h3>
+      <p>訓練の設定はモデルの重みと共にあるが、要するに：</p>
+      <h4>NoobAI RF EQ-VAE</h4>
+      <ul>
+        <li>ソフト：Kohya sd-scripts Bluvoll fork</li>
+        <li>オプティマイザ：CAME</li>
+        <li>スケジューラ：Constant</li>
+        <li>UNetの学習率：2e-4</li>
+        <li>TE1の学習率：7e-5</li>
+        <li>TE2の学習率：3.5e-5</li>
+        <li>LoRAのタイプ：LoCon</li>
+        <li>エポックの数：16</li>
+        <li>ネットワークのランク(次元/アルファ)：64/1</li>
+        <li>精度：Full BF16</li>
+        <li>ハードウェア：1x RTX 3090 24GB</li>
+      </ul>
+      <h4>NoobAI RF FLUX.2 VAE</h4>
+      <ul>
+        <li>ソフト：Kohya sd-scripts Bluvoll fork</li>
+        <li>オプティマイザ：CAME</li>
+        <li>スケジューラ：Constant</li>
+        <li>UNetの学習率：3e-4</li>
+        <li>TE1の学習率：7e-5</li>
+        <li>TE2の学習率：3.5e-5</li>
+        <li>LoRAのタイプ：LoCon</li>
+        <li>エポックの数：16</li>
+        <li>ネットワークのランク(次元/アルファ)：64/1</li>
+        <li>精度：Full BF16</li>
+        <li>ハードウェア：1x RTX 3090 24GB</li>
+      </ul>
+      <h4>Illustrious 2</h4>
+      <ul>
+        <li>ソフト：Kohya sd-scripts Bluvoll fork</li>
+        <li>オプティマイザ：CAME</li>
+        <li>スケジューラ：Constant</li>
+        <li>UNetの学習率：2e-4</li>
+        <li>TE1の学習率：7e-5</li>
+        <li>TE2の学習率：3.5e-5</li>
+        <li>LoRAのタイプ：LoCon</li>
+        <li>エポックの数：10</li>
+        <li>ネットワークのランク(次元/アルファ)：64/1</li>
+        <li>精度：Full BF16</li>
+        <li>ハードウェア：1x RTX 3090 24GB</li>
+      </ul>
+      <h4>Chenkin RF</h4>
+      <ul>
+        <li>ソフト：Kohya sd-scripts Bluvoll fork</li>
+        <li>オプティマイザ：CAME</li>
+        <li>スケジューラ：Constant</li>
+        <li>UNetの学習率：1e-4</li>
+        <li>TE1の学習率：7e-5</li>
+        <li>TE2の学習率：3.5e-5</li>
+        <li>LoRAのタイプ：LoCon</li>
+        <li>エポックの数：10</li>
+        <li>ネットワークのランク(次元/アルファ)：64/1</li>
+        <li>精度：Full BF16</li>
+        <li>ハードウェア：1x RTX 3090 24GB</li>
+      </ul>
+      <h4>Anima</h4>
+      <ul>
+        <li>ソフト：LoRA Easy Training Scripts CLI</li>
+        <li>オプティマイザ：CAME</li>
+        <li>スケジューラ：Constant</li>
+        <li>DiTの学習率：4e-6</li>
+        <li>LoRAのタイプ：LoKr フル行列</li>
+        <li>エポックの数：20</li>
+        <li>解像度: 512px</li>
+        <li>ネットワークのランク (次元/アルファ/因数分解): 512/1/4</li>
+        <li>精度：Full BF16</li>
+        <li>ハードウェア：1x RTX 3090 24GB</li>
+      </ul>
+      <!-- No lumina version trained -->
+      <!-- <h4>Lumina 2</h4>
+      <ul>
+        <li>Program: Kohya sd-scripts SD3 branch</li>
+        <li>Optimizer: CAME</li>
+        <li>Scheduler: Rex</li>
+        <li>DiT LR: 1e-4</li>
+        <li>TE LR: None. TE outputs are cached</li>
+        <li>LoRA type: LoRA Lumina</li>
+        <ul>
+          <li>No LoCon needed as they'res no Conv layers.</li>
+        </ul>
+        <li>Steps: 36600 (batch 4)</li>
+        <li>Network Rank (Dim/Alpha): 64/32</li>
+        <li>Precision: Full BF16</li>
+        <li>Hardware: 1x RTX 3090 24GB</li>
+      </ul> -->
+    </div>
+  </div>
+  <div class="section-div">
+    <h2>FAQ</h2>
+    <ul>
+      <li><b>このモデルは他のモデル向けのバーションも生み出す予定ですか？</b>今はこのモデルはNoobAI-XL RF (EQとFLUX.2 VAE)やIllustrious 2.0 (ILXL2)やAnimaに訓練されたバーションがあります。他のモデル向けのバーションも予定です。
+      <ul>
+        <!-- <li>Lumina 2向けのバーションは、a5naとか1.0とか、Neta Lumina AES pathsしか使用出来ません。</li> -->
+        <li>Illustrious 2向けのバーションはIllustrious 1と0.1とNoobAI-XL Epsilon Predと使用出来ます。</li>
+        <li>Pony向けのバーションは予定ではありません。NoobAI-XLあるいはILXLを使って下さい。</li>
+      </ul></li>
+      <li><b>CivitAI向けのバーションも生み出す予定ですか？</b> 予定ではありません。Illustrious 1.0の公開後で、クローズドソースのモデルの重みを許すから、特にCivitAIはウンチされたオムツの画像を強引に検閲しているから、質の低いサービスだから、欲張りが高すぎだから、CivitAIにはもう信用出来ません。
+      <ul>
+        <li>V15.1のアップデート：おもらしとオムツの画像は特に検閲されているから、絶対にムリです。しかも、頻りにサイトはどうにもしようとする、クラッシュが起こってしまいます。いい厄介払いです。</li>
+      </ul></li>
+      <li><b>他の予定がありますか？</b>
+        <ul>
+          <li>おむつを替える</li>
+          <li>おむつのカバー</li>
+          <li>食い込みパンツの様、食い込みオムツ</li>
+          <li>キレイでまだ穿いていないおむつ</li>
+          <li>布おむつ</li>
+          <li>残りの訓練データを処理してタグします。</li>
+          <li>その他</li>
+        </ul>
+      </li>
+      <ul>
+    </ul>
+  </div>
+  <div class="section-div">
+    <h2>ライセンス</h2>
+    <p>このLoRAモデルは<a href="https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md">Apache License 2.0</a>の下で公開されています。</p>
+    <!-- <p>Training configurations and dataset will also be released later. You can use these to further train AIDL.</p> -->
+  </div>
+  <div class="section-div">
+    <h2>スペシャル・サンクス</h2>
+    <ul>
+      <li>DangoKnight様はこのLoRAのいくらかのテストバーションを訓練してくれました。</li>
+      <li>Yatogami様は訓練データのいくらかの画像を提供して、このREADMEを日本語にしました。</li>
+      <li>Hugs288様やLopi99様や他のNoobAIのDiscordサーバーの方々はLoRAの訓練設定を調節してくれました。</li>
+    </ul>
+  </div>
+  <div class="section-div">
+    <h2>連絡先</h2>
+    <ul>
+      <p>作者の連絡先は</p>
+      <li><b>Matrix：</b> @mr_pops_alot:cutefunny.art</li>
+      <li><b>GitLab：</b> gitgud.io/mrpopsalot</li>
+      <li><b>All The Fallen：</b> @MrDoesNothingAlot</li>
+      <li><b>Discord：</b> 474149843724664854</li>
+    </ul>
+  <div class="subsection-div">
+  <p>もし作品がすきなら、御応援になることが出来ます。このモデルはいつまでも無料でオープンソースです。ペイウォールとか隠れた料金とか拠金をしないとアクセス出来ないとかコンテンツがずっとに一切ありません。</p>
+
+  <table>
+      <tbody>
+          <tr>
+              <td><b>応援のオプション</b></td>
+              <td colspan="4"><table>
+                  <tbody>
+                      <tr>
+                          <td><b>標準オプション</b></td>
+                          <td style="width:150px;height:50px;"><a href="https://ci-en.dlsite.com/creator/25153"><img src="https://img.shields.io/badge/Ci%20en-brown?style=for-the-badge&logo=dlsite&logoColor=white"></a></td>
+                          <td style="width:150px;height:50px;"><a href="https://mrpopsalot.fanbox.cc/"><img src="https://img.shields.io/badge/FANBOX-grey?style=for-the-badge&logo=pixiv&logoColor=white"></a></td>
+                          <td style="width:150px;height:50px;"><a href="https://boosty.to/mrpopsalot"><img src="https://img.shields.io/badge/Boosty-orange?style=for-the-badge&logo=boosty&logoColor=white"></a></td>
+                      </tr>
+                      <tr>
+                          <td><b>クリプトカレンシー</b></td>
+                          <td style="width:150px;height:50px;"><a href="https://backed.by/mrpopsalot"><img src="https://img.shields.io/badge/BackedBy-pink?style=for-the-badge&logoColor=pink"></a></td>
+                      </tr>
+                  </tbody>
+              </table></td>
+          </tr>
+          <tr>
+              <td><b>通信</b></td>
+              <td style="width:150px;height:50px;"><a href="https://matrix.cutefunny.art/#/#eracorrection:cutefunny.art"><img src="https://img.shields.io/badge/Matrix-green?style=for-the-badge&logo=matrix&logoColor=white"></a></td>
+              <td style="width:150px;height:50px;"><a href="https://discord.gg/4sXWzwHUBQ"><img src="https://img.shields.io/badge/Discord-blue?style=for-the-badge&logo=discord&logoColor=white"></a></td>
+              <td style="width:150px;height:50px;"><a href="https://rvlt.gg/NDbCd53j"><img src="https://img.shields.io/badge/Revolt-red?style=for-the-badge&logo=revolt.chat&logoColor=white"></a></td>
+          </tr>
+      </tbody>
+  </table>
+  <p>SubscribeStarのアカウントを許可したがっていないから、SubscribeStarのアカウントを持っていません。Patreonは屁理屈のBANとNSFWの作者に攻撃して悪名高いから、Patreonのアカウントを持っていません。もしよければ、上記のサイトでご応援になるます。</p>
+  </div>
+  </div>
+</div>

README.md

@@ -3,10 +3,16 @@ tags:
 - text-to-image
 - stable-diffusion
 - lora
+- diaper
+- abdl
+- scat
+- omorashi
+- concept
 - diffusers
 - not-for-all-audiences
 license: apache-2.0
 base_model:
+- ChenkinRF/ChenkinNoob-XL-v0.2-Rectified-Flow
 - Laxhar/noobai-XL-Vpred-1.0
 - OnomaAIResearch/Illustrious-XL-v2.0
 - neta-art/neta-lumina
@@ -80,8 +86,8 @@ base_model:
 <div class="main-div">
   <h1>AIDL: OmoAIShi</h1>
   <div style="background-color: #ffff99; padding: 20px; border-radius: 10px; margin-bottom: 20px;">
-  <img src="docs/Images/v16-thumb.png">
-  <h3>V16: Tag Restructure Edition<br>For Lumina 2, Illustrious 2, NoobAI VPred</h3>
+  <img src="docs/Images/v017-thumb-EN.png">
+  <h3>V17: Pee-ka-poo Edition<br>For Anima, Chenkin RF, NoobAI RF EQ-VAE, NoobAI RF FLUX.2 Vae, Illustrious 2</h3>
   <div style="background-color: #ff9999; padding: 20px; border-radius: 10px; margin-bottom: 20px;">
   <h3>This model is designed for **NSFW** purposes, trained and tested on DRAWN CHARACTERS ONLY.</h3>
   <h3>PUBLIC ALPHA. GENERATIONS DO NOT REPRESENT THE FINAL MODEL.</h3>
@@ -89,6 +95,7 @@ base_model:
     <a href="https://gitgud.io/mrpopsalot/aidl-omoaishi"><img alt="Static Badge" src="https://img.shields.io/badge/GitLab-orange?logo=gitlab&logoColor=white&style=for-the-badge"></a>
     <a href="https://huggingface.co/mrpopsalot/aidl-omoaishi"><img alt="Static Badge" src="https://img.shields.io/badge/HuggingFace-yellow?logo=huggingface&logoColor=white&style=for-the-badge"></a>
     <a href="https://allthefallen.moe/forum/index.php?resources/aidl-omoaishi.7465/"><img alt="Static Badge" src="https://img.shields.io/badge/AllTheFallen-pink?logo=outlook&logoColor=white&style=for-the-badge"></a>
+    <a href="https://mrpopsalot.booth.pm/items/7895981"><img alt="Static Badge" src="https://img.shields.io/badge/Booth-red?logoColor=white&style=for-the-badge"></a>
     <img alt="GitLab License" src="https://img.shields.io/gitlab/license/mrpopsalot%2Faidl-omoaishi?gitlab_url=http%3A%2F%2Fgitgud.io&style=for-the-badge">
   </div>
   <div class="section-div">
@@ -97,31 +104,50 @@ base_model:
     <ul>
       <li><b>Trained Models:</b></li>
       <ul>
-        <li><b>NoobAI-XL VPred:</b> Laxhar/noobai-XL-Vpred-1.0 @ 1024</li>
-        <li><b>Illustrious 2:</b> OnomaAIResearch/Illustrious-XL-v2.0 @ 1536</li>
+        <li><b>Anima:</b> circlestone-labs/Anima @ 1024</li>
           <ul>
-          <li>Also works on 1024px, as well on Illustrious 1, 0.1, and NoobAI EPS</li>
+          <li>Note that the base model is also trained on 512px.</li>
           </ul>
-        <li><b>Lumina Image 2:</b> neta-art/neta-lumina 1.0 @ 1024</li>
+        <li><b>Chenkin RF:</b> ChenkinRF/ChenkinNoob-XL-v0.2-Rectified-Flow @ 1024</li>
+        <li><b>NoobAI-XL RF EQ-VAE:</b> CabalResearch/NoobAI-RectifiedFlow-Experimental/NoobAI-RF-v0.2-Base @ 1024</li>
+          <ul>
+          <li>Also works on the NoobAI RF test models and VPred.</li>
+          </ul>
+        <li><b>NoobAI-XL RF FLUX.2VAE:</b> CabalResearch/NoobAI-Flux2VAE-RectifiedFlow-0.3 @ 1024</li>
+        <!-- <li><b>NoobAI-XL VPred:</b> Laxhar/noobai-XL-Vpred-1.0 @ 1024</li>
+          <ul>
+          <li>Also works on the NoobAI RF test models.</li>
+          </ul> -->
+        <li><b>Illustrious 2:</b> OnomaAIResearch/Illustrious-XL-v2.0 @ 1024</li>
+          <ul>
+          <li>Also works on  on Illustrious 1, 0.1, and NoobAI EPS</li>
+          </ul>
+        <!-- <li><b>Lumina Image 2:</b> neta-art/neta-lumina 1.0 @ 1024</li> -->
       </ul>
       <li><b>Developed by:</b> Mr Pops Alot</li>
-      <li><b>Model type:</b> LyCORIS, Full Preset (LoRA for Lumina 2)</li>
+      <li><b>Model type:</b> LyCORIS LoCon</li>
+      <!-- <li><b>Model type:</b> LyCORIS LoCon, Full Preset (LoRA for Lumina 2)</li> -->
       <li><b>License:</b> Apache 2.0</li>
     </ul><br>
-    <p>This is the first LoRA of the AIDL series. <b>AIDL: The AI Diaper LyCORIS</b> is intended to a series of LoRAs that teaches models about diapers and other ABDL related concepts.</p>
+    <p>This is the first LoRA of the AIDL series. <b>AIDL: The AI Diaper LyCORIS</b> is intended to be a series of LoRAs that teaches models about diapers and other ABDL related concepts.</p>
+    <a href="https://gitgud.io/mrpopsalot/aidl-omoaishi"><img src="https://img.shields.io/badge/OmoAIShi-blue?style=for-the-badge&label=Diapers"></a>
+    <a href="https://huggingface.co/mrpopsalot/aidl-mini"><img src="https://img.shields.io/badge/Mini-brown?style=for-the-badge&label=Diapers%20(experimental!)"></a>
+    <a href="https://gitgud.io/pops-aidl/sd-beginners-guide"><img src="https://img.shields.io/badge/SD Beginners Guide-yellow?style=for-the-badge&label=New Here?"></a>
+    <a href="https://gitgud.io/pops-aidl/lora-training-guide"><img src="https://img.shields.io/badge/Lora Training Guide-teal?style=for-the-badge"></a>
   </div>
   <div class="section-div">
     <h2>Showcase</h2>
-    <p><img src="docs/Images/aidl-v016-showcase.webp"></p>
+    <p><img src="docs/Images/aidl-v017-showcase.webp"></p>
   </div>
   <div class="section-div">
     <h2>Features</h2>
     <ul>
-      <li><b>Tape-on diapers:</b> Two and four taped, printed and plain diapers are supported. Diapers from specific brands and designs are also trained when noticed. Note that these are not fully trained and may not be fully accurate.</li>
+      <li><b>Tape-on diapers:</b> Two- and four-taped, printed and plain diapers are supported. Some diapers from specific brands and designs have also been trained. Note that these are not fully trained and may not be fully accurate.</li>
       <li><b>Pull-up diapers:</b> Pull-ups are also trained and can be prompted in various designs.</li>
-      <li><b>Peed diapers:</b> Wet diapers of various stages, from slightly wet to completely leaking. Speaking of leaks, they now correctly go at the side of the thighs.</li>
-      <li><b>Diaper and panty pooping:</b> Soiling of various stages, including blowouts have also been trained, as with double pee and poo soiling as well. Pants, shorts, and dress pooping is also covered. Compatibility is not guaranteed (there is less training data). You may see some exposed scat.</li>
+      <li><b>Peed diapers:</b> Wet diapers of various stages, from slightly wet to completely leaking. Leaks now correctly go at the side of the thighs.</li>
+      <li><b>Diaper and panty pooping:</b> Soiling of various stages (including blowouts), as well as both pee and poo soiling, have also been trained. Pants, shorts, and dress pooping is also covered. Compatibility is not guaranteed (there is less training data). You may see some exposed scat.</li>
       <li><b>Open diapers:</b> Open diapers are now possible to do, complete with wetness and mess in the pads if prompted.</li>
+      <li><b>Covered diapers:</b> Diapers covered by pants along with their bulges and waistband peeks can be done. Now your diapered girls can show off their padding in a more discreet way.</li>
       <li><b>Consistent results across different character positions:</b> This model has been trained on a variety of styles and poses, ensuring correct generation on many poses and whatever artstyle you want to use, including standing, squatting, lying down, from below upskirts, and more</li>
     </ul>
   </div>
@@ -131,18 +157,19 @@ base_model:
       <h3>Diapers</h3>
       <p>Use the general term: <code>diaper</code>, or <code>in a diaper</code>.</p>
       <ul>
-      <li>You can also specify the tape count using <code>two taped</code>, or <code>four taped</code>.</li>
-      <li>Prompting <code>plain diaper</code> will get you a diaper with no designs, while <code>print diaper</code> will get you a printed diaper.</li>
+      <li>You can also specify the tape count using <code>two tape diaper</code>, or <code>four tape diaper</code>.</li>
+      <li>Prompting nothing else will get you a diaper with no designs, while <code>print diaper</code> will get you a printed diaper.</li>
       <li><code>front-print diaper</code> and <code>back-print diaper</code> can also be used to get you a print on the front or back. Use <a href="https://danbooru.donmai.us/tags?commit=Search&search%5Bhide_empty%5D=yes&search%5Bname_or_alias_matches%5D=%2A_print&search%5Border%5D=count">Danbooru's list of prints</a>.</li>
       <li>Add in wetness indicators by prompting <code>yellow wetness indicator</code> or <code>blue wetness indicator</code>.</li>
       </ul>
-      <p>Specific diaper styles:</p>
+      <p>Specific diaper styles (may or may not work, they have not been trained specifically):</p>
       <ul>
         <li><code>pampers</code></li>
         <li><code>huggies</code></li>
         <li><code>luvs</code></li>
         <li><code>abuniverse</code></li>
         <li><code>merries</code></li>
+        <li><code>attento</code></li>
       </ul>
     </div>
     <div class="subsection-div">
@@ -151,7 +178,7 @@ base_model:
     </div>
     <div class="subsection-div">
       <h3>Diaper Soiling</h3>
-      <p><b>Peed-in diapers:</b> Use the general <code>peed diaper</code> tag to get wet diapers. From there, you can also go and set how soiled the diaper should be. Without it, you might get unexpected diaper blowouts.</p>
+      <p><b>Peed-in diapers:</b> Use the general <code>peed diaper</code> tag to get wet diapers. From there, you can also go and set how soiled the diaper should be. Without it, you might get unexpected leaks.</p>
       <ol>
         <li><code>wet diaper</code></li>
         <li><code>soaked diaper</code></li>
@@ -168,15 +195,30 @@ base_model:
       </ol>
       <br>
       <p><code>smell</code> can also be added to your prompt to give off that soiled smell effect.</p>
-      <p>If you want more soiled diapers, you can increase the weight of the tag to suit your needs. Tags works well between 0.9-1.5 weight.</p>
-      <img src="docs/Images/unidesSoil_00002_.png">
-      <img src="docs/Images/unidesSoil_00004_.png">
+      <p>If you want more soiled diapers, you can increase the weight of the tag to suit your needs. Tags work well with weights between 0.9–1.5.</p>
+      <table>
+        <th>Diaper</th>
+        <th>Pull-Up</th>
+        <tr>
+        <td><img src="docs/Images/unidesSoil_00016_.png"></td>
+        <td><img src="docs/Images/pullUpSoil_00001_.png"></td>
+        </tr>
+      </table>
+      <p>Want leaks and blowouts? Those can be done too</p>
+      <table>
+        <th>Pee</th>
+        <th>Poop</th>
+        <tr>
+        <td><img src="docs/Images/diaperLeak_00001_.png"></td>
+        <td><img src="docs/Images/diaperBlowout_00002_.png"></td>
+        </tr>
+      </table>
     </div>
     <div class="subsection-div">
       <h3>Pantypooping</h3>
       <p>Use the term <code>pooping self</code>. You can also use the terms <code>poopy underwear</code> or <code>poopy clothes</code> to have either their underwear be soiled or their lower clothes (like their dress or pants) to be soiled.
       </p>
-      <img src="docs/Images/unidesSoil_00005_.png">
+      <img src="docs/Images/unidesSoil_00017_.png">
       <p>Multiple underwear types supported!</p>
       <img src="docs/Images/pantyPoops_2025-06-19-224722.webp">
       <p>For diapers please use the poopy diaper tag. Pooping self can also work but poopy diaper is the recommended tag for diaper pooping.</p>
@@ -186,9 +228,17 @@ base_model:
       <p>Use the term <code>open diaper</code> to get open diapers.</p>
       <ul>
         <li>Add in <code>peed diaper</code> and <code>poopy diaper</code> respectively if you want the diaper to be wet and messy.</li>
-        <li>As well, add your respective genitals such as <code>pussy</code> or <code>penis</code> and the uncensored tag</li>
+        <li>As well, add your respective genitals such as <code>pussy</code> or <code>penis</code> and the <code>uncensored</code> tag</li>
       </ul>
-      <img src="docs/Images/openDiaper_00000_.png">
+      <img src="docs/Images/openDiaper_00001_.png">
+    </div>
+    <div class="subsection-div">
+      <h3>Covered Diapers</h3>
+      <p><code>covered diaper</code> is the main term used for diaper bulges. Works best on pants or shorts.</p>
+      <ul>
+        <li>You can add <code>diaper peek</code> for waistband peeks. The color of the diaper may be chosen too.</li>
+      </ul>
+      <img src="docs/Images/coveredDiaper_00002_.png">
     </div>
   </div>
   <div class="section-div">
@@ -202,17 +252,22 @@ base_model:
       </ul>
       <li>Unworn diapers (both clean and used)</li>
       <li>Clothespooping</li>
+      <li>Covered diapers on leotards and bodysuits</li>
+      <li>Furry</li>
       <li>Technical positions such as falling</li>
     </ul>
     <br>
     <p>As well, there may be some limitations with this LoRA:</p>
     <ul>
-      <li>Panty poops may happen unprompted if <code>smell</code> is prompted</li>
-      <li>Peed diapers may have poopy diaper bulges unless poopy diaper is put in the negatives</li>
+      <li>Panty poops and soiled diapers may happen unprompted if <code>smell</code> is prompted.</li>
+      <li>Peed diapers may have poopy diaper bulges unless poopy diaper is put in the negatives.</li>
       <li>There is currently no training data for poopy pull-ups, and is using the fallback pantypooping data.</li>
       <li>Poopy diapers may have unprompted blowouts.</li>
-      <li>In the Lumina 2 LoRA, you need to prompt for "wet diaper" as well with "peed diaper" to get a pee soaked pad.</li>
-      <li>Although you can use Rouwei Gemma in the SDXL variants, you'll only get pull-ups</li>
+      <li>Soiling may not be great on some diaper print types such as front-print.</li>
+      <li>Some artist styles may show worse soiling.</li>
+      <!-- <li>In the Lumina 2 LoRA, you need to prompt for "wet diaper" as well with "peed diaper" to get a pee soaked pad.</li> -->
+      <li>Although you can use Rouwei Gemma in the SDXL variants, it will generate only pull-ups.</li>
+      <li>Don't prompt <code>two tape diaper</code> or <code>four tape diaper</code> on Anima if the character's position would not show the diaper's tapes, or else it may generate them in awkward places.</li>
     </ul>
   <p>Increase the strength of the LoRA if needed to achieve your desired results.</p>
   <div style="background-color: #ff9999; padding: 20px; border-radius: 10px; margin-bottom: 20px;">
@@ -222,24 +277,83 @@ base_model:
   </div>
   <div class="section-div">
     <h2>Training Details</h2>
-    <p>Over 1000 images have been used in the dataset. Images used are <b>exclusively drawn 2D</b> art.</p>
+    <p>Over 1800 images have been used in the dataset. Images used are <b>exclusively drawn 2D</b> art.</p>
     <p><b>No synthetic data has been used</b> for the model. Tagging (Danbooru tag style) is <b>all manually done</b>, as automatic taggers do not recognize the concept in question well. Image captioning (NL support) uses a list of manual captioned images and (planned for V17) JoyCaption Beta 1 and Gemma 3 27B outputs with manual Tag grounding.</p>
     <div class="subsection-div">
       <h3>Training Procedure</h3>
       <p>Training configs are provided with the weights, but as a TL;DR:</p>
-      <h4>SDXL-based (Illustrious, NoobAI)</h4>
+      <h4>NoobAI RF EQ-VAE</h4>
       <ul>
-        <li>Program: 67372a's Kohya Easy Scripts</li>
+        <li>Program: Kohya sd-scripts Bluvoll fork</li>
         <li>Optimizer: CAME</li>
-        <li>Scheduler: Rex</li>
+        <li>Scheduler: Constant</li>
+        <li>UNet LR: 2e-4</li>
+        <li>TE1 LR: 7e-5</li>
+        <li>TE2 LR: 3.5e-5</li>
+        <li>LoRA type: LoCon</li>
+        <li>Epochs: 16</li>
+        <li>Network Rank (Dim/Alpha): 64/1</li>
+        <li>Precision: Full BF16</li>
+        <li>Hardware: 1x RTX 3090 24GB</li>
+      </ul>
+      <h4>NoobAI RF FLUX.2 VAE</h4>
+      <ul>
+        <li>Program: Kohya sd-scripts Bluvoll fork</li>
+        <li>Optimizer: CAME</li>
+        <li>Scheduler: Constant</li>
         <li>UNet LR: 3e-4</li>
+        <li>TE1 LR: 7e-5</li>
+        <li>TE2 LR: 3.5e-5</li>
+        <li>LoRA type: LoCon</li>
+        <li>Epochs: 16</li>
+        <li>Network Rank (Dim/Alpha): 64/1</li>
+        <li>Precision: Full BF16</li>
+        <li>Hardware: 1x RTX 3090 24GB</li>
+      </ul>
+      <h4>Illustrious 2</h4>
+      <ul>
+        <li>Program: Kohya sd-scripts Bluvoll fork</li>
+        <li>Optimizer: CAME</li>
+        <li>Scheduler: Constant</li>
+        <li>UNet LR: 2e-4</li>
+        <li>TE1 LR: 7e-5</li>
+        <li>TE2 LR: 3.5e-5</li>
         <li>LoRA type: LoCon</li>
-        <li>Steps: 36600</li>
+        <li>Epochs: 10</li>
         <li>Network Rank (Dim/Alpha): 64/1</li>
         <li>Precision: Full BF16</li>
         <li>Hardware: 1x RTX 3090 24GB</li>
       </ul>
-      <h4>Lumina 2</h4>
+      <h4>Chenkin RF</h4>
+      <ul>
+        <li>Program: Kohya sd-scripts Bluvoll fork</li>
+        <li>Optimizer: CAME</li>
+        <li>Scheduler: Constant</li>
+        <li>UNet LR: 1e-4</li>
+        <li>TE1 LR: 7e-5</li>
+        <li>TE2 LR: 3.5e-5</li>
+        <li>LoRA type: LoCon</li>
+        <li>Epochs: 10</li>
+        <li>Network Rank (Dim/Alpha): 64/1</li>
+        <li>Precision: Full BF16</li>
+        <li>Hardware: 1x RTX 3090 24GB</li>
+      </ul>
+      <h4>Anima</h4>
+      <ul>
+        <!-- <li>Program: Diffusion Pipe Bluvoll fork</li> -->
+        <li>Program: LoRA Easy Training Scripts CLI</li>
+        <li>Optimizer: CAME</li>
+        <li>DiT LR: 4e-6</li>
+        <li>Scheduler: Constant</li>
+        <li>LoRA type: LoKr Full Matrix</li>
+        <li>Epochs: 20</li>
+        <li>Resolution: 512px</li>
+        <li>Network Rank (Dim/Alpha/Factor): 512/1/4</li>
+        <li>Precision: Full BF16</li>
+        <li>Hardware: 1x RTX 3090 24GB</li>
+      </ul>
+      <!-- No lumina version trained -->
+      <!-- <h4>Lumina 2</h4>
       <ul>
         <li>Program: Kohya sd-scripts SD3 branch</li>
         <li>Optimizer: CAME</li>
@@ -254,18 +368,17 @@ base_model:
         <li>Network Rank (Dim/Alpha): 64/32</li>
         <li>Precision: Full BF16</li>
         <li>Hardware: 1x RTX 3090 24GB</li>
-      </ul>
+      </ul> -->
     </div>
   </div>
   <div class="section-div">
     <h2>FAQ</h2>
     <ul>
-      <li><b>Will this model be ported to X?</b> This model is planned to have versions trained on NoobAI-XL VPred, Illustrious 2.0 (ILXL2), and Neta Lumina (Lumina 2). More models will come later.
+      <li><b>Will this model be ported to X?</b> This model is planned to have versions trained on NoobAI-XL RF (EQ and FLUX.2 VAE), Illustrious 2.0 (ILXL2), and Anima. More models will come later.
       <ul>
-        <li>Lumina 2 version only works on Neta Lumina AES paths, such as a5nA and 1.0</li>
+        <!-- <li>Lumina 2 version only works on Neta Lumina AES paths, such as a5nA and 1.0</li> -->
         <li>The Illustrious 2 version works on Illustrious 1, 0.1, and NoobAI-XL Epsilon Pred.</li>
-        <li>V17 will have a Wan 2.2 5B</li>
-        <li>No Pony version is planned. Move to NoobXL or ILXL.</li>
+        <li>No Pony version is planned. Move to NoobAI-XL or ILXL.</li>
       </ul></li>
       <li><b>Will there be a version for CivitAI?</b> No. I do not trust CivitAI anymore after the release of Illustrious 1.0 and them allowing closed-weight models, not to mention the overbearing censorship against messy diaper content, bad service, and overall greed.
       <ul>
@@ -274,12 +387,10 @@ base_model:
       <li><b>Anything else planned?</b>
         <ul>
           <li>Diaper changes</li>
-          <li>Open diapers and pull-ups</li>
           <li>Diaper covers</li>
           <li>Diaper pulls (like panty pulls)</li>
           <li>Clean and used unworn diapers</li>
           <li>Cloth diapers</li>
-          <li>Diaper pulls</li>
           <li>The rest of the data in my dataset processed and tagged.</li>
           <li>Etc.</li>
         </ul>
@@ -296,7 +407,7 @@ base_model:
     <h2>Special Thanks</h2>
     <ul>
       <li>DangoKnight for training some of the test versions of this LoRA</li>
-      <li>Yatogami for contributing to the dataset.</li>
+      <li>Yatogami for contributing to the dataset and for translating the readme to Japanese.</li>
       <li>Hugs288, Lopi99, and others in the NoobAI discord to for helping me get my LoRA training settings right.</li>
     </ul>
   </div>
@@ -309,5 +420,37 @@ base_model:
       <li><b>All The Fallen:</b> @MrDoesNothingAlot</li>
       <li><b>Discord:</b> 474149843724664854</li>
     </ul>
+  <div class="subsection-div">
+  <p>Like my work? Support me by giving me a tip. This model will always be free, and open source. There will never be any paywalls, hidden fees, or any content locked behind a subscription.</p>
+
+  <table>
+      <tbody>
+          <tr>
+              <td><b>Support</b></td>
+              <td colspan="4"><table>
+                  <tbody>
+                      <tr>
+                          <td><b>Regular options</b></td>
+                          <td style="width:150px;height:50px;"><a href="https://ci-en.dlsite.com/creator/25153"><img src="https://img.shields.io/badge/Ci%20en-brown?style=for-the-badge&logo=dlsite&logoColor=white"></a></td>
+                          <td style="width:150px;height:50px;"><a href="https://mrpopsalot.fanbox.cc/"><img src="https://img.shields.io/badge/FANBOX-grey?style=for-the-badge&logo=pixiv&logoColor=white"></a></td>
+                          <td style="width:150px;height:50px;"><a href="https://boosty.to/mrpopsalot"><img src="https://img.shields.io/badge/Boosty-orange?style=for-the-badge&logo=boosty&logoColor=white"></a></td>
+                      </tr>
+                      <tr>
+                          <td><b>Crypto</b></td>
+                          <td style="width:150px;height:50px;"><a href="https://backed.by/mrpopsalot"><img src="https://img.shields.io/badge/BackedBy-pink?style=for-the-badge&logoColor=pink"></a></td>
+                      </tr>
+                  </tbody>
+              </table></td>
+          </tr>
+          <tr>
+              <td><b>Chat</b></td>
+              <td style="width:150px;height:50px;"><a href="https://matrix.cutefunny.art/#/#eracorrection:cutefunny.art"><img src="https://img.shields.io/badge/Matrix-green?style=for-the-badge&logo=matrix&logoColor=white"></a></td>
+              <td style="width:150px;height:50px;"><a href="https://discord.gg/4sXWzwHUBQ"><img src="https://img.shields.io/badge/Discord-blue?style=for-the-badge&logo=discord&logoColor=white"></a></td>
+              <td style="width:150px;height:50px;"><a href="https://rvlt.gg/NDbCd53j"><img src="https://img.shields.io/badge/Revolt-red?style=for-the-badge&logo=revolt.chat&logoColor=white"></a></td>
+          </tr>
+      </tbody>
+  </table>
+  <p>I do not have a SubscribeStar, as they do not seem to want to approve my account. I have never and will never open up a Patreon, as they are infamous for their ban waves and attacks against the NSFW community. Please support me on these alternative services.</p>
+  </div>
   </div>
 </div>

docs/HowToUse.md

@@ -0,0 +1,52 @@
+# How To Use
+
+# Introduction
+
+<p style="color:#f99">First of all, this model is for AB/DL (Adult Baby, Diaper Lover), Scat, and Omorashi (Japanese for “(I) peed/poop myself”) fetish purposes and is not for anyone under the age of majority of the jurisdiction that you are in.</p>
+
+<p style="color:#f99; font-size:24px; text-align:center">And especially if you can’t distinguish between fiction and reality.</p>
+
+Much of the information in this MarkDown document is duplicated in the readme. If you prefer an abbreviated version of the documentation, refer to 「README.md」.
+
+Also, please view this page in a proper MarkDown reader like VS Code. Gitlab can't do this page justice.
+
+----
+
+OmoAIshi is the most comprehensive multi-concept LoRA for diaper wearing and using, able to comprehend multiple concepts previously unfulfilled by base models and other LoRAs.
+
+Such concepts trained include clean, peed in, and pooped in diapers of the pull-up and tape-on variety, pantypooping, open diapers, and now diapers covered by outer garments such as pants and shorts. No more girls in panties!
+
+Most models have data on clean diapers assuming they are trained on Danbooru or E621. However such tagging is awful and do not replicate the concept to a good degree.  Often most times prompting a diaper on a Danbooru trained model like Anima or ILXL will get you a white pull-up looking underwear. Scat (poop play) is also banned from Danbooru, so even if Danbooru decided to step up their ABDL game, it’ll be able to gen clean and peed tape-ons and that’s it. Some other models like FLUX.2 or Z-Image try generating them, but they also look very off.
+
+This entire spectrim of fetishes right here can be generated easilly by propreitary models such as NovelAI 4.5 Full, thanks to their vast datasets including NL captioned Pixiv and Sankaku, however most local models often use curated booru datasets which do not have this data, or have the data but badly captioned. This lead me to learning how to train my own models and create guides to teach others the same for the sake of being able to generated my own fetish.
+
+While CivitAI’s crackdowns on most extreme fetish models on April 2025 affected most model creators, with most of them not sharing any more models, as well as their ban waves and zero tollerance policies when it comes to rule breaking, AIDL would’ve never had any chance of being on there because it already broke CivitAI’s rules of banned content before said rule changes. Nethertheless, the main reason why I don’t interact with CivitAI is due to them selling out to coprorate models and no longer making every model a model that you can download.
+
+The biggest issue of most local models are the lack of post installation documentation, which can leave you stranded if you did not scrape the CivitAI metadata via a program like LoRA Manager or Stability Matrix. **I hope to rectify this for my models by giving vast documentation in readmes, supplying Stability Matrix and LoRA Manager metadata, and actually filling out the SafeTensors metadata fields.**
+
+# Model Variants
+There are several models that AIDL: OmoAIShi has been trained upon, including SD1.X based, SDXL based, and DiT based models such as Lumina 2 and Anima. The LoRA type trained will depend on the model that it’s trained for.
+- For SD1.x and SDXL-based models, LyCORIS LoCon is used instead of the regular LoRA LierLA format as it allows multiple concepts to be trained within the same model. Convolution layers generally learn better other layers, especially for multi concept training
+- Most DiTs are trained on GLoRA, LoKr or LierLA depending on the training program used. Musubi Tuner and SD-Scripts allows for such formats, whole Diffusion Pipe is limited to just LierLA.
+
+# License
+<p style="font-size:32px; text-align:center">Apache License 2.0</p>
+If you paid someone for access to this information or the model and source files within, you got ripped off.  This model was released on the following channels, and for free:
+
+- https://gitgud.io/mrpopsalot/aidl-omoaishi
+- https://huggingface.co/mrpopsalot/aidl-omoaishi
+- https://allthefallen.moe/forum/index.php?resources/ilxl2-noobai-lumina-2-aidl-omoaishi.7465/ 
+- https://mrpopsalot.booth.pm/items/7895981
+
+Like our legal system, individual intellectual property is a joke.  Copyright does not help any "little guys", unless the "little guy" has enough money to enforce it in court - hundreds of thousands of dollars to just piss away - or if he is a lawyer himself. Public defenders are not assigned to civil cases, and good luck finding someone to handle a copyright lawsuit pro bono.  AND, the only things a court can do for you are make people stop doing things, or make them pay you.  People not doing things and not having money are typically not conducive to drawing paintings of girls shitting themselves.
+
+If this was a game, program, or any other software project, this would be licensed under GPLv3 or LGPLv3 depending on if I used any propreitary software, but in AI, “source code” is a very murky term with different interpretations for different people. For me, open source in AI means open dataset and open training configuration files. If I cannot compile (train) a version of a program (LoRA) to work for my operating system (base model), then it’s not open source, but closed source software with a permissive license (open weight).
+
+# Legal
+Although this LoRA, supported models, generation tools, and image scraping for AI training are unconditionally legal to possess and commit in the United States, some places require licensure or registration (aka “age verfication”), or are illegal in other places. I recommend at minimum following these rules for responsible image generation, regardless of any particular legalities:
+- Shut the fuck up. Don't tell anyone about what you've generated. Do not show it to your guests, neighbors or family. Do not brag about it, certainly don’t make threats with it. Some employers and many ill-informed family members disapprove of such fetish content, and may punish you in ways the state can't. If you follow this rule, it's impossible to break the others.
+- Mark your generations as AI generated if you can’t. Share generations in primarilly fetish communites, spoiler them if you’re going to share them in a more “neutral” space, and mark your images as AI generated. You’ll be doing a bunch of favors for everyone else.
+- Don't start selling generations. Most copyright holders typically pursues legal actions only when it's with intent to distribute, as with the state with drugs. Selling generations and models behind a paywall is a great way to have some kind of corpo’s legal department kicking your door in.
+- Don't commit actual crime. An "actual crime" is one with a victim. You will be pursued primarily for whatever actual harm you've caused – not because anyone cares that you can generate porn with a click. Doing this presents a danger to the society around you. Please don't hurt innocent people.
+
+Beyond this, I can offer little. Be smart. Measure risks. Don't underestimate your enemies, and know your enemies from your collaborators. Many people hate AI already for a variety of reasons. Don’t be the next reason why they hate us so much.

docs/The AIDL Family.md

@@ -1,14 +1,47 @@
 # The AIDL Family
 *The AI Diaper LyCORIS*
 
-# OmoAIShi
+<b>AIDL: The AI Diaper LyCORIS</b> is intended to be a series of LoRAs that teaches models about diapers and other ABDL related concepts.</p>
+
+# Released Models
+
+## OmoAIShi
 Diaper LoRA with support for clean and soiled diapers, pull-ups, and pantypooping.
 
-# Big Baby's Model Lounge (BBML)
+Applicable concepts:
+- Tape-on diapers
+- Pull-up diapers
+- Pantypooping
+- Open diapers
+- Diaper covers
+- Cloth diapers
+- Covered diapers
+- Leotards and diaper changing stuff
+
+## Mini
+Mini version of OmoAIShi with 80 images instead of the multi-thousand image dataset.
+
+# Planned Models
+
+These models aren't out yet, but will be soon.
+
+## Outside Action
+Open Scat, pooping in pee pads, just pooping in general. Some peeing stuff included too that's out of scope for OmoAIShi. While technically outside of the ABDL space that AIDL covers, it is still in the excreton niche.
+
+Applicable concepts:
+- Open defecation
+- Different poop types, solid, constipated, diarrhea
+- Toilet use
+- Poop play, eating, scat sex, etc.
+
+## Big Baby's Model Lounge (BBML)
 LoRA for Cribs, changing tables, diaper pails, many ABDL-related furniture
 
-# Regressed Armory
+## Regressed Armory
 LoRA for toys, onesies and etc.
 
-# The AIDols
-Separate artist LoRAs for those that just want the style of their favorite ABDL artist.
+## The AIDols
+Separate artist LoRAs for those that just want the style of their favorite ABDL artist.
+
+## AIDLMix
+Combination of OmoAIShi and Outside Action for an all-in-one excretion-based checkpoint that can also be ported to with different names.