Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,16 @@ tags:
|
|
| 10 |
inference: true
|
| 11 |
---
|
| 12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
|
| 15 |
|
|
|
|
| 10 |
inference: true
|
| 11 |
---
|
| 12 |
|
| 13 |
+
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 |
+
Thanks Microsoft for providing GPU for training ❤️
|
| 18 |
+
|
| 19 |
+
Trained on LAION Improved Aesthetics 6plus.
|
| 20 |
+
|
| 21 |
+
Want to collaborate on open source together with me? Send me a message: kopyloleh@gmail.com / telegram @kopyl
|
| 22 |
+
|
| 23 |
|
| 24 |
|
| 25 |
|