Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
tags:
|
| 5 |
+
- stable-diffusion-xl
|
| 6 |
+
- text-to-image
|
| 7 |
+
license: unknown
|
| 8 |
+
inference: true
|
| 9 |
+
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
This unofficial repository hosts a diffusers-compatible float16 checkpoint of the [WDXL](https://huggingface.co/hakurei/waifu-diffusion-xl) base UNet.
|
| 13 |
+
|
| 14 |
+
Usage:
|
| 15 |
+
|
| 16 |
+
```python
|
| 17 |
+
import torch
|
| 18 |
+
from diffusers import UNet2DConditionModel
|
| 19 |
+
|
| 20 |
+
base_unet: UNet2DConditionModel = UNet2DConditionModel.from_pretrained(
|
| 21 |
+
unet_name,
|
| 22 |
+
torch_dtype=torch.float16,
|
| 23 |
+
use_safetensors=True,
|
| 24 |
+
variant='fp16',
|
| 25 |
+
subfolder='unet',
|
| 26 |
+
).eval().to(torch.device('cuda'))
|
| 27 |
+
```
|
| 28 |
+
|
| 29 |
+
### NOTE: The work here is a Work in Progress! Nothing in this repository is final.
|
| 30 |
+
|
| 31 |
+
# waifu-diffusion-xl - Diffusion for Rich Weebs
|
| 32 |
+
|
| 33 |
+
waifu-diffusion-xl is a latent text-to-image diffusion model that has been conditioned on high-quality anime images through fine-tuning StabilityAI's SDXL 0.9 model provided as a research preview.
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
<sub>masterpiece, best quality, 1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, watercolor, night, turtleneck</sub>
|
| 38 |
+
|
| 39 |
+
## Model Description(s)
|
| 40 |
+
|
| 41 |
+
- [wdxl-aesthetic-0.9](https://huggingface.co/hakurei/waifu-diffusion-xl/blob/main/wdxl-aesthetic-0.9.safetensors) is a checkpoint that has been finetuned against our in-house aesthetic dataset which was created with the help of 15k aesthetic labels collected by volunteers. This model also used Stability.AI's [SDXL 0.9 checkpoint](https://huggingface.co/stabilityai/stable-diffusion-xl-base-0.9) as the base model for finetuning.
|
| 42 |
+
|
| 43 |
+
## License
|
| 44 |
+
|
| 45 |
+
This model has been released under the [SDXL 0.9 RESEARCH LICENSE AGREEMENT](https://huggingface.co/hakurei/waifu-diffusion-xl/blob/main/LICENSE.md) due to the repository containing the SDXL 0.9 weights before an official release. We have been given permission to release this model.
|
| 46 |
+
|
| 47 |
+
## Downstream Uses
|
| 48 |
+
|
| 49 |
+
This model can be used for entertainment purposes and as a generative art assistant.
|
| 50 |
+
|
| 51 |
+
## Team Members and Acknowledgements
|
| 52 |
+
|
| 53 |
+
This project would not have been possible without the incredible work by Stability AI and Novel AI.
|
| 54 |
+
|
| 55 |
+
- [Haru](https://github.com/harubaru)
|
| 56 |
+
- [Salt](https://github.com/sALTaccount/)
|
| 57 |
+
- [closertodeath](https://huggingface.co/closertodeath)
|
| 58 |
+
- [Kudo](https://negotiator.itch.io/)
|
| 59 |
+
|
| 60 |
+
In order to reach us, you can join our [Discord server](https://discord.gg/touhouai).
|
| 61 |
+
|
| 62 |
+
[](https://discord.gg/touhouai)
|