Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
license_name: faipl
|
4 |
+
license_link: https://freedevproject.org/faipl-1.0-sd
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
tags:
|
8 |
+
- text-to-image
|
9 |
+
- stable-diffusion
|
10 |
+
- safetensors
|
11 |
+
- stable-diffusion-xl
|
12 |
+
base_model: OnomaAIResearch/Illustrious-xl-early-release-v0
|
13 |
+
widget:
|
14 |
+
- text: >-
|
15 |
+
1girl, green hair, sweater, looking at viewer, upper body, beanie,
|
16 |
+
outdoors, night, turtleneck, masterpiece, best quality
|
17 |
+
parameter:
|
18 |
+
negative_prompt: >-
|
19 |
+
nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers,
|
20 |
+
extra digit, fewer digits, cropped, worst quality, low quality, normal
|
21 |
+
quality, jpeg artifacts, signature, watermark, username, blurry, artist
|
22 |
+
name
|
23 |
+
example_title: 1girl
|
24 |
+
---
|
25 |
+
<style>
|
26 |
+
.title-container {
|
27 |
+
display: flex;
|
28 |
+
justify-content: center;
|
29 |
+
align-items: center;
|
30 |
+
height: 100vh; /* Adjust this value to position the title vertically */
|
31 |
+
}
|
32 |
+
|
33 |
+
.title {
|
34 |
+
font-size: 2.5em;
|
35 |
+
text-align: center;
|
36 |
+
color: #333;
|
37 |
+
font-family: 'Helvetica Neue', sans-serif;
|
38 |
+
text-transform: uppercase;
|
39 |
+
letter-spacing: 0.1em;
|
40 |
+
padding: 0.5em 0;
|
41 |
+
background: transparent;
|
42 |
+
}
|
43 |
+
|
44 |
+
.title span {
|
45 |
+
background: -webkit-linear-gradient(45deg, #ffffff, #000000);
|
46 |
+
-webkit-background-clip: text;
|
47 |
+
-webkit-text-fill-color: transparent;
|
48 |
+
}
|
49 |
+
|
50 |
+
.custom-table {
|
51 |
+
table-layout: fixed;
|
52 |
+
width: 100%;
|
53 |
+
border-collapse: collapse;
|
54 |
+
margin-top: 2em;
|
55 |
+
}
|
56 |
+
|
57 |
+
.custom-table td {
|
58 |
+
width: 50%;
|
59 |
+
vertical-align: top;
|
60 |
+
padding: 10px;
|
61 |
+
box-shadow: 0px 0px 0px 0px rgba(0, 0, 0, 0.15);
|
62 |
+
}
|
63 |
+
.custom-image-container {
|
64 |
+
position: relative;
|
65 |
+
width: 100%;
|
66 |
+
margin-bottom: 0em;
|
67 |
+
overflow: hidden;
|
68 |
+
border-radius: 10px;
|
69 |
+
transition: transform .7s;
|
70 |
+
/* Smooth transition for the container */
|
71 |
+
}
|
72 |
+
.custom-image-container:hover {
|
73 |
+
transform: scale(1.05);
|
74 |
+
filter: none;
|
75 |
+
/* Scale the container on hover */
|
76 |
+
}
|
77 |
+
.custom-image {
|
78 |
+
width: 100%;
|
79 |
+
height: auto;
|
80 |
+
object-fit: cover;
|
81 |
+
border-radius: 10px;
|
82 |
+
transition: transform .7s;
|
83 |
+
margin-bottom: 0em;
|
84 |
+
}
|
85 |
+
.nsfw-filter {
|
86 |
+
filter: blur(8px); /* Apply a blur effect */
|
87 |
+
transition: filter 0.3s ease; /* Smooth transition for the blur effect */
|
88 |
+
}
|
89 |
+
|
90 |
+
.overlay {
|
91 |
+
position: absolute;
|
92 |
+
bottom: 0;
|
93 |
+
left: 0;
|
94 |
+
right: 0;
|
95 |
+
color: white;
|
96 |
+
width: 100%;
|
97 |
+
height: 40%;
|
98 |
+
display: flex;
|
99 |
+
flex-direction: column;
|
100 |
+
justify-content: center;
|
101 |
+
align-items: center;
|
102 |
+
font-size: 1vw;
|
103 |
+
font-style: bold;
|
104 |
+
text-align: center;
|
105 |
+
opacity: 0;
|
106 |
+
/* Keep the text fully opaque */
|
107 |
+
background: linear-gradient(0deg, rgba(0, 0, 0, 0.8) 60%, rgba(0, 0, 0, 0) 100%);
|
108 |
+
transition: opacity .5s;
|
109 |
+
}
|
110 |
+
.custom-image-container:hover .overlay {
|
111 |
+
opacity: 1;
|
112 |
+
}
|
113 |
+
.overlay-text {
|
114 |
+
background: linear-gradient(45deg, #7ed56f, #28b485);
|
115 |
+
-webkit-background-clip: text;
|
116 |
+
color: transparent;
|
117 |
+
text-shadow: 2px 2px 4px rgba(0, 0, 0, 0.7);
|
118 |
+
|
119 |
+
.overlay-subtext {
|
120 |
+
font-size: 0.75em;
|
121 |
+
margin-top: 0.5em;
|
122 |
+
font-style: italic;
|
123 |
+
}
|
124 |
+
|
125 |
+
.overlay,
|
126 |
+
.overlay-subtext {
|
127 |
+
text-shadow: 2px 2px 4px rgba(0, 0, 0, 0.5);
|
128 |
+
}
|
129 |
+
|
130 |
+
</style>
|
131 |
+
<h1 class="title">
|
132 |
+
<span>irAsu v1.0</span>
|
133 |
+
</h1>
|
134 |
+
<table class="custom-table">
|
135 |
+
<tr>
|
136 |
+
<td>
|
137 |
+
<div class="custom-image-container">
|
138 |
+
<img class="custom-image" src="https://cdn-uploads.huggingface.co/production/uploads/64333a074521083b9d2aab3b/Ej3wPocmIYE9d2ns7uFsY.png" alt="sample1">
|
139 |
+
</div>
|
140 |
+
</td>
|
141 |
+
<td>
|
142 |
+
<div class="custom-image-container">
|
143 |
+
<img class="custom-image" src="https://cdn-uploads.huggingface.co/production/uploads/64333a074521083b9d2aab3b/i3LHDbkUgzPkp6tS3ACQb.png" alt="sample2">
|
144 |
+
</div>
|
145 |
+
</td>
|
146 |
+
</tr>
|
147 |
+
</table>
|
148 |
+
|
149 |
+
**irAsu** is a second-stage finetune of Illustrious XL 0.1, which fixes the coloring, anatomy, and background of the images generated by the model.
|
150 |
+
|
151 |
+
## Standard Prompting Guidelines
|
152 |
+
The model is finetuned from Illustrious XL v0.1. However, there is a little bit changes on dataset captioning, therefore there is some different default prompt used:
|
153 |
+
|
154 |
+
**Default prompt**:
|
155 |
+
```
|
156 |
+
1girl/1boy, character name, from what series, everything else in any order, best quality, amazing quality, very aesthetic.
|
157 |
+
```
|
158 |
+
|
159 |
+
Note: The quality tag `masterpiece` has been replaced with `best quality` due to reports that it often caused unwanted side effects.
|
160 |
+
|
161 |
+
**Default negative prompt**:
|
162 |
+
```
|
163 |
+
lowres, (bad), text, error, fewer, extra, missing, worst quality, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, extra digits, artistic error, username, scan, [abstract],
|
164 |
+
```
|
165 |
+
|
166 |
+
**Default configuration:**
|
167 |
+
|
168 |
+
Default configuration: Euler a with around 25-30 steps, CFG 3.5-5, and ENSD set to 31337. Sweet spot is around **28 steps** and **CFG 4**.
|
169 |
+
|
170 |
+
## Training Configurations
|
171 |
+
|
172 |
+
- Finetuned from: [Illustrious XL v0.1](https://huggingface.co/OnomaAIResearch/Illustrious-xl-early-release-v0)
|
173 |
+
|
174 |
+
**Pretraining:** N/A
|
175 |
+
|
176 |
+
**Finetuning:**
|
177 |
+
|
178 |
+
- Dataset size: 3,140 images
|
179 |
+
|
180 |
+
- GPU: 1xA100
|
181 |
+
|
182 |
+
- Optimizer: AdaFactor
|
183 |
+
|
184 |
+
- Unet Learning Rate: 3e-6
|
185 |
+
|
186 |
+
- Text Encoder Learning Rate: - (Train TE set to False)
|
187 |
+
|
188 |
+
- Batch Size: 16
|
189 |
+
|
190 |
+
- Gradient Accumulation: 3
|
191 |
+
|
192 |
+
- Warmup steps: 5%
|
193 |
+
|
194 |
+
- Min SNR Gamma: 5
|
195 |
+
|
196 |
+
- Epoch: 10 (epoch 9 is used)
|
197 |
+
|
198 |
+
- Noise Offset: 0.0357
|
199 |
+
|
200 |
+
- Random Cropping: True
|
201 |
+
|
202 |
+
- Loss: Huber
|
203 |
+
|
204 |
+
- Huber Schedule: SNR
|
205 |
+
|
206 |
+
- Huber C: 0.1
|
207 |
+
|
208 |
+
## License
|
209 |
+
**irAsu v1.0** falls under the **[Fair AI Public License 1.0-SD](https://freedevproject.org/faipl-1.0-sd/)** license.
|