Create README.md
#1
by
patrickvonplaten
- opened
README.md
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- stable-diffusion
|
| 5 |
+
- stable-diffusion-diffusers
|
| 6 |
+
inference: false
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# Watermarked (extreme) VAE for SDXL
|
| 10 |
+
|
| 11 |
+
You can use this watermarked VAE for your existing SDXL image generation pipelines
|
| 12 |
+
to make sure generated images are watermarked.
|
| 13 |
+
|
| 14 |
+
## Usage
|
| 15 |
+
|
| 16 |
+
```py
|
| 17 |
+
from diffusers.models import AutoencoderKL
|
| 18 |
+
from diffusers import StableDiffusionXLPipeline
|
| 19 |
+
|
| 20 |
+
model = "stabilityai/sdxl-turbo"
|
| 21 |
+
|
| 22 |
+
vae = AutoencoderKL.from_pretrained("imatag/stable-signature-bzh-sdxl-vae-extreme")
|
| 23 |
+
|
| 24 |
+
pipe = StableDiffusionXLPipeline.from_pretrained(model, vae=vae)
|
| 25 |
+
```
|
| 26 |
+
|
| 27 |
+
For more information, please have a look at [the official demo](https://huggingface.co/spaces/imatag/stable-signature-bzh)
|