Agreene5 commited on
Commit
3061301
1 Parent(s): 29a69bc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -57,10 +57,10 @@
57
  training_hardware: RTX 3090
58
  training_time: ~1.5 hours (I don't remember exactly)
59
  #### Version 1.1 Improvements:
60
- -**Better style consistency**: The model generates in a style closer to the Rhythm Heaven series much more consistently.
61
  1.0 generated a bit more of a detailed style though so if that's what you want you should use that one.
62
- -**Removed "rhythm_heaven" trigger**: Seems like a style trigger isn't really necessary, removing it just saves a bit of token length.
63
- -**Less unprompted black and white generations**: This one isn't as big but I manually added color to some of the training images to get more variety
64
  which consequently means you'll get less black and white generations.
65
  ## Model Description
66
  Trained on humanoid characters from the Rhythm Heaven series (and some from Wario Ware) using AnyLoRA.
 
57
  training_hardware: RTX 3090
58
  training_time: ~1.5 hours (I don't remember exactly)
59
  #### Version 1.1 Improvements:
60
+ **Better style consistency**: The model generates in a style closer to the Rhythm Heaven series much more consistently.
61
  1.0 generated a bit more of a detailed style though so if that's what you want you should use that one.
62
+ **Removed "rhythm_heaven" trigger**: Seems like a style trigger isn't really necessary, removing it just saves a bit of token length.
63
+ **Less unprompted black and white generations**: This one isn't as big but I manually added color to some of the training images to get more variety
64
  which consequently means you'll get less black and white generations.
65
  ## Model Description
66
  Trained on humanoid characters from the Rhythm Heaven series (and some from Wario Ware) using AnyLoRA.