218xl / README.md
Enferlain's picture
Update README.md
81a76a9
|
raw
history blame
No virus
10.6 kB
---
license: creativeml-openrail-m
language:
- en
pipeline_tag: text-to-image
tags:
- art
- anime
- stable-diffusion
- SDXL
library_name: safetensors
---
<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: #d6767f;
font-family: 'Roboto', sans-serif;
text-transform: uppercase;
letter-spacing: 0.11em;
padding: 0.218em 0;
background: transparent;
}
.title span {
background: -webkit-linear-gradient(69deg, #130c28, #2a4aee);
-webkit-background-clip: text;
-webkit-text-fill-color: transparent;
}
.custom-table {
table-layout: fixed;
width: 100%;
border-collapse: collapse;
margin-top: 2em;
}
.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-container:hover .custom-image {
opacity: 0
}
.custom-image-container:hover
.hover-image {
opacity: 1;
}
.custom-image {
width: 100%;
height: auto;
object-fit: cover;
border-radius: 10px;
transition: transform .7s, opacity .5s;
margin-bottom: 0em;
}
.hover-image {
position: absolute;
top: 0;
left: 0;
opacity: 0;
transition: opacity .5s;
}
.nsfw-filter {
filter: blur(8px); /* Apply a blur effect */
transition: filter 0.3s ease; /* Smooth transition for the blur effect */
}
.custom-image-container:hover .nsfw-filter {
filter: none; /* Remove the blur effect on hover */
}
.overlay {
position: absolute;
bottom: 0;
left: 0;
right: 0;
color: white;
width: 100%;
height: 40%;
display: flex;
flex-direction: column;
justify-content: center;
align-items: center;
font-size: 1vw;
font-style: bold;
text-align: center;
opacity: 0;
/* Keep the text fully opaque */
background: linear-gradient(0deg, rgba(0, 0, 0, 0.6) 60%, rgba(0, 0, 0, 0) 100%);
transition: opacity .5s;
}
.custom-image-container:hover .overlay {
opacity: 1;
/* Make the overlay always visible */
}
.overlay-text {
background: linear-gradient(45deg, #130c28, #ca76e2);
-webkit-background-clip: text;
color: transparent;
/* Fallback for browsers that do not support this effect */
text-shadow: 2px 2px 4px rgba(0, 0, 0, 0.7);
/* Enhanced text shadow for better legibility */
.overlay-subtext {
font-size: 0.75em;
margin-top: 0.5em;
font-style: italic;
}
.overlay,
.overlay-subtext {
text-shadow: 2px 2px 4px rgba(0, 0, 0, 0.5);
}
</style>
<h1 class="title">
<span>∞ 218xl ∞</span>
</h1>
<table class="custom-table">
<tr>
<td>
<div class="custom-image-container">
<div class="image-wrapper">
<img class="custom-image" src="https://huggingface.co/Enferlain/218xl/resolve/main/images/218xlb1.png" alt="sample1">
<img class="hover-image" src="https://huggingface.co/Enferlain/218xl/resolve/main/images/218xl1.png" alt="sampleb1">
<div class="overlay" style="font-size: 1vw; font-style: bold;"> Merry Christmas <div class="overlay-subtext" style="font-size: 0.75em; font-style: italic;">"by ziyun"</div></div>
</div>
</div>
<div class="custom-image-container">
<div class="image-wrapper">
<img class="custom-image" src="https://huggingface.co/Enferlain/218xl/resolve/main/images/218xlb2.png" alt="sample2">
<img class="hover-image" src="https://huggingface.co/Enferlain/218xl/resolve/main/images/218xll6.png" alt="sampleb2">
<div class="overlay" style="font-size: 1vw; font-style: bold;"> Sunflower <div class="overlay-subtext" style="font-size: 0.75em; font-style: italic;">"by poire"</div></div>
</div>
</td>
<td>
<div class="custom-image-container">
<div class="image-wrapper">
<img class="custom-image" src="https://huggingface.co/Enferlain/218xl/resolve/main/images/218xlb3.png" alt="sample3">
<img class="hover-image" src="https://huggingface.co/Enferlain/218xl/resolve/main/images/218xll5.png" alt="sampleb3">
<div class="overlay" style="font-size: 1vw; font-style: bold;"> Light meal <div class="overlay-subtext" style="font-size: 0.75em; font-style: italic;">"by ziyun"</div></div>
</div>
</div>
<div class="custom-image-container">
<div class="image-wrapper">
<img class="custom-image" src="https://huggingface.co/Enferlain/218xl/resolve/main/images/218xlb4.png" alt="sample4">
<img class="hover-image" src="https://huggingface.co/Enferlain/218xl/resolve/main/images/218xl27.png" alt="sampleb4">
<div class="overlay" style="font-size: 1vw; font-style: bold;"> Rice Shower <div class="overlay-subtext" style="font-size: 0.75em; font-style: italic;">"by ziyun"</div></div>
</td>
<td>
<div class="custom-image-container">
<div class="image-wrapper">
<img class="custom-image" src="https://huggingface.co/Enferlain/218xl/resolve/main/images/218xlb5.png" alt="sample5">
<img class="hover-image" src="https://huggingface.co/Enferlain/218xl/resolve/main/images/218xl37.png" alt="sampleb5">
<div class="overlay" style="font-size: 1vw; font-style: bold;"> Remilia Scarlet <div class="overlay-subtext" style="font-size: 0.75em; font-style: italic;">"by ziyun"</div></div>
</div>
</div>
<div class="custom-image-container">
<div class="image-wrapper">
<img class="custom-image" src="https://huggingface.co/Enferlain/218xl/resolve/main/images/218xlb6.png" alt="sample6">
<img class="hover-image" src="https://huggingface.co/Enferlain/218xl/resolve/main/images/218xll2.png" alt="sampleb6">
<div class="overlay" style="font-size: 1vw; font-style: bold;"> Y-yes? <div class="overlay-subtext" style="font-size: 0.75em; font-style: italic;">"by ask"</div></div>
</div>
</td>
</tr>
</table>
<p align="center", style="font-size: 1.2rem; font-style:bold"><strong><a href="https://huggingface.co/Enferlain/218xl/resolve/main/218xl.safetensors?download=true"</a></strong> Download</p>
# ∞ 218 SDXL aka 'counterproductive illustration' omE
I only recently started dabbling in SDXL models, but I already put a lot of testing into it. Mostly comparisons, testing loras, trying to fix some shortcomings in models I liked.
I decided on a model called ReproductionXL because it looked the most similar to what I was used to, but better.
After that I merged CounterfeitXL because Counterfeit aesthetics are still one of if not the best.
Then I merged that result with Anime Illust Diffusion XL as I found the idea of being able to use different artstyles with tags fun -- and it is a lot of fun.
This took around 2 days of manual scoring and guidance through a Bayesian process, usually 500 samples per merge, which I did about 7 times total to arrive here.
Also merged a LoRA trained on 18000 images at .4 weight into the final result, aimed at fixing sdxl models' lack of knowledge about the 4 letter word.
And so there you have it, that's the current point in time.
Onwards I'm looking to see how I can use Lynn's Animagine XL 2 and upgrade the main ingredients with their latest updates.
I'm looking to add multiple characters (animagine should help with that) and more styles that aren't currently present within the model.
<hr>
<details id="Dropdown">
<summary style="font-size: 1.10em"><strong> Changelogs </strong> (click to open the dropdown)</summary>
### 11 29 2023
- Yoinked layout
- Added images
- Uploaded 218xl
</details>
<hr>
# ∞ Usage
So this is a bit different compared to usual models. You can still prompt as normal, but there is a fun quirk thanks to Anime Illust Diffusion.
There is a [wildcard text file](https://huggingface.co/Enferlain/218xl/blob/main/artistsAI.txt) in the repo that contains all the tags that call for their respective artstyles, try and play around with that.
You can call it with ```__artistsAI__```
There is also a [wildcard](https://huggingface.co/Enferlain/218xl/blob/main/artists218.txt) with artists that I personally liked in this model, ```__artists218__```, but this is a work in progress.
Artist xyzs thanks to [b74](https://huggingface.co/b74444) from the Touhou [discord](https://discord.com/invite/touhouai)
[One](https://huggingface.co/b74444/style1/blob/main/list1.png)
[Two](https://huggingface.co/b74444/style1/blob/main/list2.png)
#### Embeddings Downloads
- [**aidxlv05_neg**](https://civitai.com/models/144327/negative-embedding-for-sdxl-based-anime-models), [Direct download](https://civitai.com/api/download/models/195614)
- [**unaestheticXL_Sky3.1**](https://civitai.com/models/119032?modelVersionId=175819), [Direct download](https://civitai.com/api/download/models/175819?type=Model&format=SafeTensor)
#### VAE
- [**sdxl_vae**](https://huggingface.co/stabilityai/sdxl-vae/blob/main/sdxl_vae.safetensors), [Direct download](https://huggingface.co/stabilityai/sdxl-vae/resolve/main/sdxl_vae.safetensors?download=true)
# ∞ Credits
- Checkpoints
- [**ReproductionXL v8.7**](https://civitai.com/models/118729?modelVersionId=199943)
- [**CounterfeitXL v1.0**](https://civitai.com/models/118406?modelVersionId=146761)
- [**Anime Illust Diffusion v0.52**](https://civitai.com/models/124189/anime-illust-diffusion-xl?modelVersionId=238771)
- Lynn for layout and future juice
- [**Animagine XL 2**](https://huggingface.co/Linaqruf/animagine-xl-2.0)
- Ashtaka Aha Oof for taking my spam on discord EZ Clap
- [**Ahnn**](https://huggingface.co/AshtakaOOf/Ahnn)
- Tools
- [**Bayesian merger by s1dlx**](https://github.com/s1dlx/sd-webui-bayesian-merger/)
- [**LoRA_Easy_Training_Scripts by Derrian**](https://github.com/derrian-distro/LoRA_Easy_Training_Scripts)
## ∞ Legal deez
```
You are free to use this model locally but
1. You aren't allowed to redistribute on another platform. (like CivitAI or Tensor.Art)
2. I am not responsible for how this model is used to generate images.
```