Rina_Arisugawa_AnimagineV31_DORA

---

license: cc

<style> td pre { white-space: pre-wrap; } table { margin-top: 0; margin-bottom: 0; } </style> <table style="border-collapse: separate; border-spacing: 10px; width:100%"> <tr> <td style="vertical-align: top"> <img src="./Examples/01.png" alt="SchoolGirl01" width="100%"/> </td> <td style="vertical-align: top;"> <img src="./Examples/02.png" alt="SchoolGirl02" width="100%"/> </td> </tr> </table>

Overview

A DORA for Animagine XL V3.1. Trained using OneTrainer.

Note: Since there aren't many avaliable images of the character, I generated synthetic data with my previous models to expand the dataset. I uplaoded the models that were used to generate the synthetic data, in case you want to try them instead.

Usage

• Trigger keywords: 1girl, arisugawa rina
• Recommended keywords: blue eyes, blonde hair, twintails, blunt bangs
• Recommended strength: 0.5 ~ 0.7

Examples

Note: All examples in the repo were produced with AUTOMATIC1111 without any edits. You download them and load all their settings from the metadata to reproduce similar results.

Highres fix details:

<pre>Denoising strength: 0.3, Hires upscale: 1.5, Hires upscaler: 4x_NMKD-YandereNeoXL_200k</pre> <table style="border-collapse: separate; border-spacing: 10px; width:100%;"> <tr> <td style="vertical-align: top"> <img src="./Examples/03.png" width="100%"/> </td> <td style="vertical-align: top;"> <img src="./Examples/04.png" width="100%"/> </td> <td style="vertical-align: top;"> <img src="./Examples/05.png"width="100%"/> </td> </tr> </table>