Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,7 @@ tags:
|
|
| 5 |
- controlnet
|
| 6 |
- text_to_image
|
| 7 |
- controlnet-scribble-sdxl-1.0
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
# ***Make everyone an anime painter, even you don't know anything about drawing.***
|
|
@@ -210,5 +211,4 @@ Note: The values are caculated when save in webp format, when save in png the ae
|
|
| 210 |
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 211 |
|
| 212 |
In our evaluation, the model got better aesthetic score in anime images compared with lllyasviel/control_v11p_sd15_scribble, we want to compare with other sdxl-1.0-scribble model but find nothing, The model is better in control ability when test with perception similarity due to bigger base model and complex data augmentation.
|
| 213 |
-
Besides, the model has lower rate to generate abnormal images which tend to include some abnormal human structure.
|
| 214 |
-
|
|
|
|
| 5 |
- controlnet
|
| 6 |
- text_to_image
|
| 7 |
- controlnet-scribble-sdxl-1.0
|
| 8 |
+
pipeline_tag: text-to-image
|
| 9 |
---
|
| 10 |
|
| 11 |
# ***Make everyone an anime painter, even you don't know anything about drawing.***
|
|
|
|
| 211 |
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 212 |
|
| 213 |
In our evaluation, the model got better aesthetic score in anime images compared with lllyasviel/control_v11p_sd15_scribble, we want to compare with other sdxl-1.0-scribble model but find nothing, The model is better in control ability when test with perception similarity due to bigger base model and complex data augmentation.
|
| 214 |
+
Besides, the model has lower rate to generate abnormal images which tend to include some abnormal human structure.
|
|
|