README.md

---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- not-for-all-audiences
license: apache-2.0
base_model:
- Laxhar/noobai-XL-Vpred-1.0
---
<style>
  .title-container {
    display: flex;
    justify-content: center;
    align-items: center;
    height: 100vh; /* Adjust this value to position the title vertically */
  }
  
  .title {
    font-size: 2.5em;
    text-align: center;
    color: #333;
    font-family: "lucida sans unicode", "lucida grande", sans-serif;
    font-style: italic;
    font-weight: bold;
    font-variant: small-caps;
    letter-spacing: 0.05em;
    padding: 0.5em 0;
    background: transparent;
  }
  
  .title span {
    background: -webkit-linear-gradient(45deg, #fffa00, #01688f);
    -webkit-background-clip: text;
    -webkit-text-fill-color: transparent;
  }

  .content-warning {
    font-size: 1.5em;
    text-align: center;
    color: #333;
    font-weight: bold;
    font-variant: small-caps;
    letter-spacing: 0.05em;
    padding: 0.5em 0;
    background: transparent;
  }

  .content-warning span {
    background: -webkit-linear-gradient(45deg, #ff9999, #FF5C95);
    -webkit-background-clip: text;
    -webkit-text-fill-color: transparent;
  }

  .custom-table {
    table-layout: fixed;
    width: 100%;
    border-collapse: collapse;
    margin-top: 0em;
  }
  
  .custom-table td {
    width: 50%;
    vertical-align: top;
    padding: 10px;
    box-shadow: 0px 0px 0px 0px rgba(0, 0, 0, 0.15);
  }
  .custom-image-container {
    position: relative;
    width: 100%;
    margin-bottom: 0em;
    overflow: hidden;
    border-radius: 10px;
    transition: transform .7s;
    /* Smooth transition for the container */
  }
  .custom-image-container:hover {
    transform: scale(1.05);
    /* Scale the container on hover */
  }
  .custom-image {
    width: 100%;
    height: auto;
    object-fit: cover;
    border-radius: 10px;
    transition: transform .7s;
    margin-bottom: 0em;
  }
  .custom-button {
    width: auto;
    height: 100px;
    object-fit: cover;
    border-radius: 10px;
    transition: transform .7s;
    margin-bottom: 0em;
    display: block;
    margin-left: auto;
    margin-right: auto;
  }
</style>
<h1 class="title">
  <span>AIDL: OmoAIshi</span>
  <br>The AI Diaper LyCORIS
</h1>

This is the first LoRA of the AIDL series. AIDL is intended to a series of LoRAs/LyCORIS LoCons that teaches models about diapers and other ABDL related concepts.

<h3 class="content-warning">
  <span>This model is designed for **NSFW** purposes, trained and tested on DRAWN CHARACTERS ONLY.</span><br>
  <span>PUBLIC ALPHA. GENERATIONS DO NOT REPRESENT THE FINAL MODEL.</span>
</h4>

## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->

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!


- **Developed by:** Mr Pops Alot
- **Model type:** LyCORIS, Full
- **License:** Apache 2.0
### Model Sources

<!-- Provide the basic links for the model. -->

- **Gitlab:** https://gitgud.io/mrpopsalot/aidl-omoaishi
- **HuggingFace:** https://huggingface.co/mrpopsalot/aidl-omoaishi
- **TensorArt:** https://tensor.art/models/830604266810032950

## Showcase

<table>
<tr>
    <td>
      <p style="text-align:center">
      <img src="docs/Images/2025-02-17-115522_noobaiXLNAIXL_vPred10Version_1043616970529185.png">
      <br>
      Clean Diapers</p>
    </td>
    <td>
      <p style="text-align:center">
      <img src="docs/Images/ComfyUI_temp_auzbc_00030_.png">
      <br>
      Wet Diapers</p>
    </td>
    <td>
      <p style="text-align:center">
      <img src="docs/Images/ComfyUI_temp_hfiui_00042_.png">
      <br>
      Messy Diapers</p>
    </td>
</tr>
    <td>
      <p style="text-align:center">
      <img src="docs/Images/1951-noobaiXLNAIXL_vPred10Version-976014750.png">
      <br>
      Clean Pull-Ups</p>
    </td>
    <td>
      <p style="text-align:center">
      <img src="docs/Images/2355-noobaiXLNAIXL_vPred10Version-415564518746996.png">
      <br>
      Wet Pull-Ups</p>
    </td>
    <td>
      <p style="text-align:center">
      <img src="docs/Images/ComfyUI_temp_spvaj_00006_.png">
      <br>
      Messy Pull-Ups</p>
    </td>
<tr>
</tr>
<tr>
    <td>
      <p style="text-align:center">
      <img src="docs/Images/2345-noobaiXLNAIXL_vPred10Version-67837478276856.png">
      <br>
      Wet and Messy Diapers</p>
    </td>
    <td>
      <p style="text-align:center">
      <img src="docs/Images/1953-noobaiXLNAIXL_vPred10Version-99067439.png">
      <br>
      Wet and Messy Pull-Ups</p>
    </td>
    <td>
      <p style="text-align:center">
      <img src="docs/Images/1942-noobaiXLNAIXL_vPred10Version-1657678900.png">
      <br>
      Pantypooping</p>
    </td>
</tr>
<tr>
    <td>
      <p style="text-align:center">
      <img src="docs/Images/ComfyUI_temp_uagpq_00003_.png">
      <br>
      Open Diapers (No Scat)</p>
    </td>
    <td>
      <p style="text-align:center">
      <img src="docs/Images/ComfyUI_temp_ibxrn_00031_.png">
      <br>
      Open Diapers (Scat)</p>
    </td>
    <td>
</tr>
</table>

## Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

### Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

Here is a list of concepts that OmoAIshi has been trained on:
- Tape-on diapers (duh)
  - Two and four taped diapers.
- Pull-up diapers
- Wet diapers of various stages, from slightly wet to completely leaking
  - Speaking of leaks, they now correctly go at the side of the thighs.
- Diaper and panty pooping of various stages, including blowouts.
  - Pants, shorts, and dress pooping is also covered. Compatibility is not guaranteed (there is less training data) you may see some exposed scat.
- Open diapers!
- Diapers from specific brands!


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.

#### Diapers
Use the general term: `diaper`, or `in a diaper`. You can also specify the tape count using `two taped`, `four taped`

Pull-ups: `pull-up diaper`

Specific diaper styles:
  - `pampers`
  - `huggies`
  - `luvs`
  - `abuniverse`
  - `merries`


#### Soiling
Peed-in diapers: Use the general `peed diaper` 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.
1. `wet diaper`
2. `soaked diaper`
3. `drenched diaper`
4. `leaking diaper`, `pee on legs`

Poopy diapers: Use the general `poopy diaper` tag to get messy diapers. From there, you can also go and set how soiled the diaper should be.
1. `messy diaper`
2. `packed diaper`
3. `loaded diaper`
4. `diaper blowout`, `poop on legs`

Pantypooping: Use the term `pooping self`.

Use the term "open diaper" to get open diapers.

## Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

<h3 class="content-warning">
  <span>OmoAIShi IS IN A PUBLIC ALPHA. GENERATIONS DO NOT REPRESENT THE FINAL MODEL.</span>
</h4>

The model currently struggles with the following concepts:
- Pull-ups (NoobAI only)
- Open diapers
  - Open diapers do not have as much data as other concepts, and will struggle to have proper diaper structure.
- Unworn diapers (both clean and used)
- Clothespooping

Increase the strength of the LoRA if needed to achieve your desired results.

There is currently no training data for poopy pull-ups, and is using the fallback pantypooping data.

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. **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.**

**This LoRA violates CivitAI's terms of service (their TOS does not allow diapers nor scat). Do not upload generations from AIDL onto CivitAI.**

## Training Details
Over 1000 images have been used in the dataset. Images used are exclusively drawn 2D art. No synthetic data has been used for the model.

Tagging is all manually done, as automatic taggers and VLMs do not recognize the concept in question well.

### Training Procedure
The following LoRAs have been trained on the following models.

- NoobAI-XL: Trained on Laxhar/noobai-XL-Vpred-1.0 @ 1024
- ILXL2: Trained on OnomaAIResearch/Illustrious-XL-v2.0 @ 1536

Training has been done with 67372a's Kohya Easy Scripts using full BF16 training with the CAME optmizer and Rex scheduler for 36600 steps on 1 RTX 3090 24GB.

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
- And more

## FAQ
  
Q: Will this model be ported to X?
- A: This model is planned to have versions trained on NoobAI-XL VPred (NoobVP) and Illustrious 2.0 (ILXL2). The Illustrious 2 version works on Illustrious 1 and 0.1. More models will come later.
- Note: No Pony version is planned. Move to NoobXL or ILXL.


Q: Will there be a version for CivitAI?
- A: 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.
- V15.1 Update: Defenitely 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.

Q: Anything else planned?
- A:
    - Diaper changes
    - Open diapers
    - Open pull-ups
    - Diaper covers
    - Unworn diapers
    - Used diapers
    - The rest of the data in my dataset processed and tagged.
    - A couple of more things

## License

This LoRA model is provided under the [Apache License 2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) license.

## Special Thanks

- DangoKnight for training some of the test versions of this LoRA
- Yatogami for contributing to the dataset.

## Model Card Contact

I can be contacted on Matrix @mr_pops_alot:cutefunny.art