Update README.md

README.md

@@ -8,12 +8,12 @@ pipeline_tag: text-to-image
 ---
 
 **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.**  
-Ok it's not totally true. Only characters and outfits are trained, ant not locations/objects/running-style(?) or whatever.
+Ok it's not true. Only characters and outfits are trained, ant not locations/objects/running-style(?) or whatever.
 
 
 ## Example Generations
 
-Comming soon... (Still training)
+See https://civitai.com/models/13543/umamusume
 
 
 ## Usage
@@ -23,9 +23,6 @@ You don't need to use the model as is. Treat it as lora and do either
 - **Your favorite model + w * (umamusume model - ACertainty/Nai)**
 - or **Umamusume model + w * (your favorite model - ACertainty/Nai)**
 
-#### Embeddings
-
-For character specific outfit you'd better download embeddings from (coming soon...)
 
 #### How to prompt
 
@@ -33,7 +30,7 @@ Here are two example captions that are used for training
 
 > AgnesDigital; CurrenChan, tracen school uniform; fanart; 2girls, horse girl, multiple girls, character doll, phone, beads, bangs, bow, blush, animal ears, school uniform, holding phone, two side up, heart in mouth, one eye closed, white background, sweat, tracen school uniform, selfie, red bow, shirt, sailor collar, open mouth, simple background, heart, horse ears, holding, purple shirt, purple skirt, skirt, long sleeves
 
-> CurrenChan; SmartFalcon, SmartFalcon-racing-suit; fanart; 2girls, horse girl, multiple girls, dress, diamond (shape), party, nail polish, red bow, see-through, teeth, frilled dress, upper teeth only, balloon, blurry, frilled collar, animal ears, timestamp, ring, black bow, pink dress, border, gem, short sleeves, puffy sleeves, heart hands, pink nails, strap, bow, lace-trimmed sleeves, black headband, chromatic aberration, white border, black dress, writing on wall, headband, frills, horse tail, chain, horse ears, puffy short sleeves, bracelet, tail, bangs, open mouth, collar, black nails, multicolored dress, multicolored clothes, depth of field, heart
+> CurrenChan; SmartFalcon, racing suit; fanart; 2girls, horse girl, multiple girls, dress, diamond (shape), party, nail polish, red bow, see-through, teeth, frilled dress, upper teeth only, balloon, blurry, frilled collar, animal ears, timestamp, ring, black bow, pink dress, border, gem, short sleeves, puffy sleeves, heart hands, pink nails, strap, bow, lace-trimmed sleeves, black headband, chromatic aberration, white border, black dress, writing on wall, headband, frills, horse tail, chain, horse ears, puffy short sleeves, bracelet, tail, bangs, open mouth, collar, black nails, multicolored dress, multicolored clothes, depth of field, heart
 
 ## Concepts
 
@@ -155,10 +152,7 @@ Here are two example captions that are used for training
 **Character specific outfit**
 
 Racing suit (勝負服) for most characters, casual outfit for some, and also other specific costumes if they are tagged by booru.
-If you use the checkpoint of phase 1, you should prompt directly with something like `character, racing suit`.
-However, expect good results for only a few characters (mostly those that appear in anime).
-
-Coming soon...: For checkpoints of phase 2, please use the trained embeddings.
+You should prompt directly with something like `character, racing suit` and you may need other trigger words for better results.
 
 
 #### Styles
@@ -197,6 +191,8 @@ Total steps x batch is around 1.1M
 
 **The second phase is trained with [naifu trainer](https://github.com/AdjointOperator/naifu-diffusion)**
 
-The goal is to train embeddings for character-specific outfits.
-Both unets and embeddings are trained.
-This phase does not use the anime screenshots nor the regularization images.
+The goal is to train embeddings for character specific outfits.
+Both unets and embeddings are trained but not text encoders.
+This phase does not use the anime screenshots nor the regularization images.
+In the end, it turns out that although the model is not further trained for "charactar, racing suit" this acutally gets improved and gives more satisfying results than the embeddings.
+This is really mysterious and worths more investigation.