Update README.md
Browse files
README.md
CHANGED
@@ -7,7 +7,7 @@ tags:
|
|
7 |
pipeline_tag: text-to-image
|
8 |
---
|
9 |
|
10 |
-
**This model intends to be the ultimate uma-musume model where
|
11 |
Ok it's not totally true. Only characters and outfits are trained, ant not locations/objects/running-style(?) or whatever.
|
12 |
|
13 |
|
@@ -154,7 +154,11 @@ Here are two example captions that are used for training
|
|
154 |
|
155 |
**Character specific outfit**
|
156 |
|
157 |
-
Racing suit (勝負服) for most
|
|
|
|
|
|
|
|
|
158 |
|
159 |
|
160 |
#### Styles
|
|
|
7 |
pipeline_tag: text-to-image
|
8 |
---
|
9 |
|
10 |
+
**This model intends to be the ultimate uma-musume model where we try to train as many things about uma-musume as possible into it.**
|
11 |
Ok it's not totally true. Only characters and outfits are trained, ant not locations/objects/running-style(?) or whatever.
|
12 |
|
13 |
|
|
|
154 |
|
155 |
**Character specific outfit**
|
156 |
|
157 |
+
Racing suit (勝負服) for most characters, casual outfit for some, and also other specific costumes if they are tagged by booru.
|
158 |
+
If you use the checkpoint of phase 1, you should prompt directly with something like `character, racing suit`.
|
159 |
+
However, expect good results for only a few characters (mostly those that appear in anime).
|
160 |
+
|
161 |
+
Coming soon...: For checkpoints of phase 2, please use the trained embeddings.
|
162 |
|
163 |
|
164 |
#### Styles
|