sdxl_noob / README.md
NebulaeWis's picture
Update README.md
1aaedb0 verified
---
{}
---
# New Image Generation Model - Early Access
This is an image generation model based on training from Illustrious-xl.
It utilizes the latest full Danbooru and e621 datasets for training, with native tags caption.
**Note:** The model name and other details are subject to change.
# This model is still undergoing training!!!
# This model is still undergoing training!!!
# This model is still undergoing training!!!
## Important Information
- No official authorization or guarantees can be provided at this stage.
- This page is for informational purposes only.
- Detailed technical specifications and usage terms will be disclosed at a later date.
- Any sublicensing or redistribution of this model's usage rights to third parties is strictly prohibited without explicit authorization.
- Model download is restricted to approved and authorized users only, and must be done exclusively through the official link provided on this page.
- The model owner retains the right to modify the terms of use or terminate access at any time.
## Current Status
This is an early test version intended for internal use. However, we are considering allowing limited external testing.
## Datasets
- Latest Danbooru images up to the training date
- E621 images [e621-2024-webp-4Mpixel](https://huggingface.co/datasets/NebulaeWis/e621-2024-webp-4Mpixel) dataset on Hugging Face
## Caption
```
<1girl/1boy/1other/...>, <character>, <series>, <artists>, <special tags>, <general tags>
```
## Quality Tags
The quality tags are assigned based on percentile ranges of rating scores from various data sources, which are normalized and time-weighted to prioritize recent ratings.
| Percentile Range | Quality Tags |
|:-----------------|:------------------|
| > 95th | masterpiece |
| > 85th, <= 95th | best quality |
| > 60th, <= 85th | good quality |
| > 30th, <= 60th | normal quality |
| <= 30th | worst quality |
## How to Apply
If you're interested in early access testing:
1. Please contact us through our official channels (e.g., QQ group).
2. Applications will be reviewed on a case-by-case basis.