Update README.md
Browse files
README.md
CHANGED
|
@@ -14,10 +14,8 @@ Motivation:
|
|
| 14 |
SDXL is a great model, especially for fine-tuning, but fine-tuning on SDXL's standard size is expensive, so i made a model which can generate images of 256x256px size.
|
| 15 |
It allows faster and cheaper training experimentation and can improve a creative process through much faster inference time.
|
| 16 |
|
| 17 |
-
<img src="https://cdn-uploads.huggingface.co/production/uploads/63ae45e642fd3b8dbaee59ce/cDXdU6JkTLyNjNfv3WhuT.png?width=20" width="128"/>
|
| 18 |
|
| 19 |
-
|
| 20 |
-
Huuuuge thanks to Microsoft for providing GPU for training ❤️
|
| 21 |
|
| 22 |
Trained on LAION Improved Aesthetics 6plus.
|
| 23 |
|
|
|
|
| 14 |
SDXL is a great model, especially for fine-tuning, but fine-tuning on SDXL's standard size is expensive, so i made a model which can generate images of 256x256px size.
|
| 15 |
It allows faster and cheaper training experimentation and can improve a creative process through much faster inference time.
|
| 16 |
|
|
|
|
| 17 |
|
| 18 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/63ae45e642fd3b8dbaee59ce/cDXdU6JkTLyNjNfv3WhuT.png?width=20" width="40"/> Huuuuge thanks to Microsoft for providing GPU for training ❤️
|
|
|
|
| 19 |
|
| 20 |
Trained on LAION Improved Aesthetics 6plus.
|
| 21 |
|