Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,7 @@ tags:
|
|
| 5 |
- diffusers
|
| 6 |
- controlnet
|
| 7 |
- controlnet-canny-sdxl-1.0
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
# ***Drawing like Midjourney! Come on!***
|
|
@@ -199,4 +200,4 @@ The data consists of many sources, including midjourney, laion 5B, danbooru, and
|
|
| 199 |
|
| 200 |
In our evaluation, the model got better aesthetic score in real images compared with stabilityai/stable-diffusion-xl-base-1.0, and comparable performance in cartoon sytle images.
|
| 201 |
The model is better in control ability when test with perception similarity due to more strong data augmentation and more training steps.
|
| 202 |
-
Besides, the model has lower rate to generate abnormal images which tend to include some abnormal human structure.
|
|
|
|
| 5 |
- diffusers
|
| 6 |
- controlnet
|
| 7 |
- controlnet-canny-sdxl-1.0
|
| 8 |
+
pipeline_tag: text-to-image
|
| 9 |
---
|
| 10 |
|
| 11 |
# ***Drawing like Midjourney! Come on!***
|
|
|
|
| 200 |
|
| 201 |
In our evaluation, the model got better aesthetic score in real images compared with stabilityai/stable-diffusion-xl-base-1.0, and comparable performance in cartoon sytle images.
|
| 202 |
The model is better in control ability when test with perception similarity due to more strong data augmentation and more training steps.
|
| 203 |
+
Besides, the model has lower rate to generate abnormal images which tend to include some abnormal human structure.
|