Update README.md
Browse files
README.md
CHANGED
|
@@ -173,7 +173,10 @@ Since the dataset used during training is an anime 2D/2.5D model, currently, its
|
|
| 173 |
而β用于保持一致性和高清放大，它对条件图片更敏感。
|
| 174 |
好吧，α是prompt更重要的版本，而β是controlnet更重要的版本。
|
| 175 |
|
| 176 |
-
Currently, two versions, α and β, have been released, corresponding to the usage of 1
|
|
|
|
| 177 |
The α version is used for pose and composition transfer, with strong generalization capabilities that can be combined with other LoRA systems.
|
|
|
|
| 178 |
On the other hand, the β version is used for maintaining consistency and high-definition magnification; it is more sensitive to conditional images.
|
|
|
|
| 179 |
In summary, α is a more important version for prompts while β is a more important version for controlnet.
|
|
|
|
| 173 |
而β用于保持一致性和高清放大，它对条件图片更敏感。
|
| 174 |
好吧，α是prompt更重要的版本，而β是controlnet更重要的版本。
|
| 175 |
|
| 176 |
+
Currently, two versions, α and β, have been released, corresponding to the usage of 1、2 and 1、3 respectively.
|
| 177 |
+
|
| 178 |
The α version is used for pose and composition transfer, with strong generalization capabilities that can be combined with other LoRA systems.
|
| 179 |
+
|
| 180 |
On the other hand, the β version is used for maintaining consistency and high-definition magnification; it is more sensitive to conditional images.
|
| 181 |
+
|
| 182 |
In summary, α is a more important version for prompts while β is a more important version for controlnet.
|