Text-to-Image
Diffusers
Safetensors
English
StableDiffusionXLPipeline
stable-diffusion
anime
stable-diffusion-xl
Instructions to use Raelina/Raehoshi-illust-XL-9 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Raelina/Raehoshi-illust-XL-9 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Raelina/Raehoshi-illust-XL-9", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,145 @@
|
|
| 1 |
-
---
|
| 2 |
-
license:
|
| 3 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: sdxl-license
|
| 4 |
+
license_link: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/LICENSE.md
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
tags:
|
| 8 |
+
- text-to-image
|
| 9 |
+
- stable-diffusion
|
| 10 |
+
- safetensors
|
| 11 |
+
- anime
|
| 12 |
+
- stable-diffusion-xl
|
| 13 |
+
---
|
| 14 |
+
<style>
|
| 15 |
+
|
| 16 |
+
body {
|
| 17 |
+
display: flex;
|
| 18 |
+
align-items: center;
|
| 19 |
+
justify-content: center;
|
| 20 |
+
height: 100vh;
|
| 21 |
+
margin: 0;
|
| 22 |
+
font-family: Arial, sans-serif;
|
| 23 |
+
background-color: #f4f4f9;
|
| 24 |
+
overflow: auto;
|
| 25 |
+
}
|
| 26 |
+
|
| 27 |
+
.container {
|
| 28 |
+
display: flex;
|
| 29 |
+
flex-direction: column;
|
| 30 |
+
align-items: center;
|
| 31 |
+
justify-content: center;
|
| 32 |
+
width: 100%;
|
| 33 |
+
padding: 20px;
|
| 34 |
+
}
|
| 35 |
+
|
| 36 |
+
.title-container {
|
| 37 |
+
display: flex;
|
| 38 |
+
flex-direction: column;
|
| 39 |
+
justify-content: center;
|
| 40 |
+
align-items: center;
|
| 41 |
+
padding: 1em;
|
| 42 |
+
border-radius: 10px;
|
| 43 |
+
}
|
| 44 |
+
|
| 45 |
+
.title {
|
| 46 |
+
font-size: 3em;
|
| 47 |
+
font-family: 'Montserrat', sans-serif;
|
| 48 |
+
text-align: center;
|
| 49 |
+
font-weight: bold;
|
| 50 |
+
}
|
| 51 |
+
|
| 52 |
+
.title span {
|
| 53 |
+
background: -webkit-linear-gradient(45deg, #FF9D3D, #AB886D, #CB80AB);
|
| 54 |
+
-webkit-background-clip: text;
|
| 55 |
+
-webkit-text-fill-color: transparent;
|
| 56 |
+
}
|
| 57 |
+
|
| 58 |
+
.gallery {
|
| 59 |
+
display: grid;
|
| 60 |
+
grid-template-columns: repeat(4, 1fr);
|
| 61 |
+
gap: 10px;
|
| 62 |
+
}
|
| 63 |
+
|
| 64 |
+
.gallery img {
|
| 65 |
+
width: 100%;
|
| 66 |
+
height: auto;
|
| 67 |
+
margin-top: 0px;
|
| 68 |
+
margin-bottom: 0px;
|
| 69 |
+
border-radius: 10px;
|
| 70 |
+
box-shadow: 0 4px 8px rgba(0, 0, 0, 0.2);
|
| 71 |
+
transition: transform 0.3s;
|
| 72 |
+
}
|
| 73 |
+
|
| 74 |
+
.gallery img:hover {
|
| 75 |
+
transform: scale(1.05);
|
| 76 |
+
}
|
| 77 |
+
|
| 78 |
+
.note {
|
| 79 |
+
font-size: 1em;
|
| 80 |
+
opacity: 50%;
|
| 81 |
+
text-align: center;
|
| 82 |
+
margin-top: 20px;
|
| 83 |
+
color: #555;
|
| 84 |
+
}
|
| 85 |
+
|
| 86 |
+
</style>
|
| 87 |
+
|
| 88 |
+
<div class="container">
|
| 89 |
+
<div class="title-container">
|
| 90 |
+
<div class="title"><span>Raehoshi illust XL 9</span></div>
|
| 91 |
+
</div>
|
| 92 |
+
<div class="gallery">
|
| 93 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64b24543eec33e27dc9a6eca/4DpkwdZd8cuTUWz0w5szt.png" alt="Image 1">
|
| 94 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64b24543eec33e27dc9a6eca/b4D9JSg3AY8WCRMTCrDbz.png" alt="Image 2">
|
| 95 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64b24543eec33e27dc9a6eca/9rq_4Y7DjpZZ85AJXkBjp.png" alt="Image 3">
|
| 96 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64b24543eec33e27dc9a6eca/OotAUN8cWWxQBFxbKwMGC.png" alt="Image 4">
|
| 97 |
+
</div>
|
| 98 |
+
</div>
|
| 99 |
+
|
| 100 |
+
## Overview
|
| 101 |
+
Introducing **Raehoshi illust XL 9** , an enhanced iteration built upon the Illustrious XL model. It aims to elevate the visual style by addressing some of the limitations in the original, such as oversaturation and artifact noise. While these issues are not entirely eliminated, noticeable improvements have been made. The goal is to deliver a more polished, balanced output while staying true to the strengths of the base model.
|
| 102 |
+
|
| 103 |
+
## Model Details
|
| 104 |
+
- **Developed by**: [Raelina](https://civitai.com/user/Raelina)
|
| 105 |
+
- **Model type**: Diffusion-based text-to-image generative model
|
| 106 |
+
- **Finetuned from**: [Illustrious XL v1.1](https://huggingface.co/OnomaAIResearch/Illustrious-XL-v1.1)
|
| 107 |
+
- **Prompt style**: Booru tags
|
| 108 |
+
|
| 109 |
+
## Character List
|
| 110 |
+
List of character that has been trained now available at [Character List](https://rentry.org/xbbfsdua)
|
| 111 |
+
|
| 112 |
+
## Recommended settings
|
| 113 |
+
|
| 114 |
+
- **Positive prompts:**
|
| 115 |
+
|
| 116 |
+
```
|
| 117 |
+
masterpiece, best quality, absurdres
|
| 118 |
+
```
|
| 119 |
+
|
| 120 |
+
- **Negative prompts:**
|
| 121 |
+
```
|
| 122 |
+
bad quality, worst quality, poorly drawn, sketch, multiple views, bad anatomy, bad hands, signature, watermark
|
| 123 |
+
```
|
| 124 |
+
|
| 125 |
+
- **CFG:** 5-7
|
| 126 |
+
- **Sampling steps:** 20+
|
| 127 |
+
- **Sampler:** DPM++2M Karras
|
| 128 |
+
- **Standard Resolution:**
|
| 129 |
+
```
|
| 130 |
+
832 x 1216, 1216 x 832, 1152 x 896, 896 x 1152, 1344 x 768, 768 x 1344, 1024 x 1024
|
| 131 |
+
```
|
| 132 |
+
- **High Resolution:**
|
| 133 |
+
```
|
| 134 |
+
1024 x 1536, 896 x 1536, 1536 x 1024, 1536 x 896
|
| 135 |
+
```
|
| 136 |
+
|
| 137 |
+
## Hires.fix Setting
|
| 138 |
+
- **Upscaler:** [4x_Remacri](https://openmodeldb.info/models/4x-Remacri)
|
| 139 |
+
- **Hires step:** 10-15
|
| 140 |
+
- **Denoising:** 0.1-0.3
|
| 141 |
+
|
| 142 |
+
## Support
|
| 143 |
+
If you’d like to support this project or my other developments, you can buy me a coffee on [Ko-Fi](https://ko-fi.com/raelina)
|
| 144 |
+
|
| 145 |
+
For the list of updated knowledge, please check my [Civitai](https://civitai.com/models/846917/raehoshi-illust-xl) release
|