---
license: other
license_name: fair-ai-public-license-1.0-sd
license_link: https://freedevproject.org/faipl-1.0-sd/
language:
- en
library_name: diffusers
pipeline_tag: text-to-image
tags:
- art
- StableDiffusionXLPipeline
---

<h1 align="center"><strong style="font-size: 48px;">Bunny Mint (XL2-V3-NS)</strong></h1>

---

<style>
.image-viewer {
  position: relative;
  width: 100%;
  margin: 0 auto;
  display: flex;
  flex-flow: wrap;
  align-items: center;
  justify-content: center;
}

.image-viewer input[type="radio"] {
  display: none;
}

.image-viewer label {
  padding: 18px;
  background-color: #B398F5;
  background-size: cover;
  background-position: center;
  border: 1px solid #ccc;
  cursor: pointer;
  color: black;
  margin: 9px;
}

.image-viewer label:hover {
  background-color: #4C88F5;
  padding: 21px;
  margin: 6px;
}

.image-viewer input[type="radio"]:checked + label {
  background-color: #6296F5;
  padding: 27px;
  margin: 0px;
}

.image-container {
  position: relative;
  width: 100%;
  height: 50vh;
}

.image-container img {
  position: absolute;
  top: 0;
  left: 0;
  height: 100%;
  width: 100%;
  object-fit: contain;
  opacity: 0;
  transition: opacity 0.5s ease;
}



#image1:checked ~ .image-container img:nth-child(1),
#image2:checked ~ .image-container img:nth-child(2),
#image3:checked ~ .image-container img:nth-child(3),
#image4:checked ~ .image-container img:nth-child(4),
#image5:checked ~ .image-container img:nth-child(5),
#image6:checked ~ .image-container img:nth-child(6),
#image7:checked ~ .image-container img:nth-child(7),
#image8:checked ~ .image-container img:nth-child(8),
#image9:checked ~ .image-container img:nth-child(9)
 {
  opacity: 1;
}

#image1l{
  background-image: url("https://huggingface.co/raingart/BunnyMint_XL2-V3-NS-GGUF/resolve/main/output-samples/1.jpg");
}
#image2l{
  background-image: url("https://huggingface.co/raingart/BunnyMint_XL2-V3-NS-GGUF/resolve/main/output-samples/2.jpg");
}
#image3l{
  background-image: url("https://huggingface.co/raingart/BunnyMint_XL2-V3-NS-GGUF/resolve/main/output-samples/3.jpg");
}
#image4l{
  background-image: url("https://huggingface.co/raingart/BunnyMint_XL2-V3-NS-GGUF/resolve/main/output-samples/4.jpg");
}
#image5l{
  background-image: url("https://huggingface.co/raingart/BunnyMint_XL2-V3-NS-GGUF/resolve/main/output-samples/5.jpg");
}
#image6l{
  background-image: url("https://huggingface.co/raingart/BunnyMint_XL2-V3-NS-GGUF/resolve/main/output-samples/6.jpg");
}
#image7l{
  background-image: url("https://huggingface.co/raingart/BunnyMint_XL2-V3-NS-GGUF/resolve/main/output-samples/7.jpg");
}
#image8l{
  background-image: url("https://huggingface.co/raingart/BunnyMint_XL2-V3-NS-GGUF/resolve/main/output-samples/8.jpg");
}
#image9l{
  background-image: url("https://huggingface.co/raingart/BunnyMint_XL2-V3-NS-GGUF/resolve/main/output-samples/9.jpg");
}

</style>
<div class="image-viewer">
  <input type="radio" id="image1" name="image-switcher" checked>
  <label for="image1" id="image1l"></label>
  <input type="radio" id="image2" name="image-switcher">
  <label for="image2" id="image2l"></label>
  <input type="radio" id="image3" name="image-switcher">
  <label for="image3" id="image3l"></label>
  <input type="radio" id="image4" name="image-switcher" checked>
  <label for="image4" id="image4l"></label>
  <input type="radio" id="image5" name="image-switcher">
  <label for="image5" id="image5l"></label>
  <input type="radio" id="image6" name="image-switcher">
  <label for="image6" id="image6l"></label>
  <input type="radio" id="image7" name="image-switcher" checked>
  <label for="image7" id="image7l"></label>
  <input type="radio" id="image8" name="image-switcher">
  <label for="image8" id="image8l"></label>
  <input type="radio" id="image9" name="image-switcher">
  <label for="image9" id="image9l"></label>


  <div class="image-container">
    <img src="output-samples/1.jpg" alt="Image 1">
    <img src="output-samples/2.jpg" alt="Image 2">
    <img src="output-samples/3.jpg" alt="Image 3">
    <img src="output-samples/4.jpg" alt="Image 4">
    <img src="output-samples/5.jpg" alt="Image 5">
    <img src="output-samples/6.jpg" alt="Image 6">
    <img src="output-samples/7.jpg" alt="Image 7">
    <img src="output-samples/8.jpg" alt="Image 8">
    <img src="output-samples/9.jpg" alt="Image 9">
  </div>
</div>

---

## Introduction
BunnyMint is a Pony model based on two finetunes. The first finetune was trained on 8k randomly selected artist images with score:>99 from danbooru for 10 epochs to improve overall aesthetic.

## Training
```
(8k random artist images score:>99) * 10 Epochs

(20k NAIv3 dataset) * 20 Epochs

Total steps: ~480k
```
## Usage

### Sample prompt
```
score_9, score_8_up, score_7_up, source_anime,
1girl, BREAK

joyful, black skirt, white pantyhose, crop top, double v,inside submarine, legs apart, pleated skirt, jumpsuit,
masterpiece,best quality
```
Negative prompt: 
```
nsfw,censor,extra_fingers,logo,score_4,score_5,score_6,lowres,(bad),text,error,bad hands,fewer,extra,missing,worst quality,jpeg artifacts,low quality,watermark,unfinished,displeasing,oldest,early,chromatic aberration,signature,extra digits,artistic error,username,scan,[abstract]
```

### Settings
```
Steps: 40 
Sampler: Euler a 
Schedule type: Polyexponential 
CFG scale: 6
Size: 624x912
Hires upscale: 1.5
```

**Since the model is Pony-based, anything Pony related should work here as well.**

## License
**This model is licensed under "Fair-AI public license 1.0-SD", please refer to the original License for more information: https://freedevproject.org/faipl-1.0-sd/**

## Source
- [civitai](https://civitai.com/models/520972/bunny-mint)

- [huggingface](https://huggingface.co/lylogummy/BunnyMint)


## Donate the model author
**Finetuning models on personal hardware is pretty costly, so if anyone likes what I do and feels like it, here's my gumroad:**

**https://lylogummy.gumroad.com/l/avhut**

## Support
[buymeacoffee](https://buymeacoffee.com/raingart). Thank you for support!