Kanbara commited on
Commit
127ad27
1 Parent(s): 2899f35

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -18
README.md CHANGED
@@ -1,12 +1,11 @@
1
  ---
2
- ---
3
  license: creativeml-openrail-m
4
  ---
5
 
6
 
7
  # Doll Series by Kbr
8
 
9
- The 'Doll-Series' is a set of LORA focused on realistic Asian faces, with impractical levels of beauty and aesthetics.
10
 
11
  My Pixiv: https://www.pixiv.net/en/users/92373922
12
 
@@ -18,16 +17,16 @@ My Twitter: https://twitter.com/KbrLoras
18
 
19
  - [License](#license)
20
  - [Disclaimer](#disclaimer)
21
- - [Used Models](#use-models)
22
- - [LORA Detail](#model-detail)
23
- - [KoreanDollLikeness](#KoreanDollLikeness)
24
- - [v10](#v10)
25
- - [v15](#v15)
26
- - [v20 (v2.0)](#v20)
27
- - [JapaneseDollLikeness](#JapaneseDollLikeness)
28
- - [v10](#v10)
29
- - [TaiwanDollLikeness](#TaiwanDollLikeness)
30
- - [v15](#v15)
31
  - [FAQ](#faq)
32
 
33
 
@@ -43,7 +42,7 @@ The CreativeML OpenRAIL License specifies:
43
  3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully)
44
  (Full license here: https://huggingface.co/spaces/CompVis/stable-diffusion-license)
45
 
46
- Additional Add-ons to license/notes
47
  1. You shall take full responsibility for any creative work that uses this model
48
  2. Refrain from using this model for malicious intent, harm, defamation, scam or political usages. It may impair and discourage the author from producing more works.
49
 
@@ -63,7 +62,7 @@ Additional Add-ons to license/notes
63
 
64
  - https://civitai.com/models/6424/chilloutmix
65
 
66
- ---
67
  # How to use and recommended settings:
68
  - VAE: vae-ft-mse-840000-ema-pruned (For realistic models)
69
 
@@ -73,10 +72,11 @@ Additional Add-ons to license/notes
73
  - Upscaler : Latent (bicubic antialiased)
74
  - CFG Scale : 5 to 9
75
  - Denoise strength for img2img: 0.4 to 0.7
 
 
76
  ---
77
-
78
  # LORA Detail
79
-
80
  ## KoreanDollLikeness
81
 
82
  The first version that is widely used by many authors/AI artist/creators
@@ -99,6 +99,8 @@ The first version that is widely used by many authors/AI artist/creators
99
 
100
  <img src="https://files.catbox.moe/thehrt.png" widht="" height="">
101
 
 
 
102
  ## JapaneseDollLikeness
103
 
104
  The Japanese variant version, subjected for v15 in the future
@@ -109,6 +111,8 @@ The Japanese variant version, subjected for v15 in the future
109
 
110
  <img src="https://files.catbox.moe/cfypot.png" width="" height="">
111
 
 
 
112
  ## TaiwanDollLikeness
113
 
114
  The Taiwan variant version, I have decided to discontinue v10, it is still out there somewhere in the internet, you may still find it.
@@ -119,11 +123,10 @@ The Taiwan variant version, I have decided to discontinue v10, it is still out t
119
 
120
  <img src="https://files.catbox.moe/5vr2z4.png" width="" height="">
121
 
122
-
123
  ---
124
  # FAQ
125
  - # Q: Why can't I produce the same pictures as you?
126
- - A: Sorry I don't share my full prompt, you may check the recommended settings, but you may ask me for advice on Twitter or Pixiv
127
 
128
  - # Q: What is the difference of each version upgrade?
129
  - A: Version upgrade does not mean it will fix hands or legs, it is mainly difference of the face of the LORA, newer versions have wider range of faces.
 
1
  ---
 
2
  license: creativeml-openrail-m
3
  ---
4
 
5
 
6
  # Doll Series by Kbr
7
 
8
+ The 'Doll-Series' is a set of LORA focused on realistic Asian faces, with incredible levels of beauty and aesthetics.
9
 
10
  My Pixiv: https://www.pixiv.net/en/users/92373922
11
 
 
17
 
18
  - [License](#license)
19
  - [Disclaimer](#disclaimer)
20
+ - [Used Models](#used-models)
21
+ - [LORA Detail](#lora-detail)
22
+ - [KoreanDollLikeness](#koreandolllikeness)
23
+ - [KoreanDollLikeness_v10](#koreandolllikeness_v10)
24
+ - [KoreanDollLikeness_v15](#koreandolllikeness_v15)
25
+ - [KoreanDollLikeness_v20](#koreandolllikeness_v20)
26
+ - [JapaneseDollLikeness](#japanesedolllikeness)
27
+ - [JapaneseDollLikeness_v10](#japanesedolllikeness_v10)
28
+ - [TaiwanDollLikeness](#taiwandolllikeness)
29
+ - [TaiwanDollLikeness_v15](#taiwandollikeness_v15)
30
  - [FAQ](#faq)
31
 
32
 
 
42
  3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully)
43
  (Full license here: https://huggingface.co/spaces/CompVis/stable-diffusion-license)
44
 
45
+ # Additional Add-ons to license/notes
46
  1. You shall take full responsibility for any creative work that uses this model
47
  2. Refrain from using this model for malicious intent, harm, defamation, scam or political usages. It may impair and discourage the author from producing more works.
48
 
 
62
 
63
  - https://civitai.com/models/6424/chilloutmix
64
 
65
+
66
  # How to use and recommended settings:
67
  - VAE: vae-ft-mse-840000-ema-pruned (For realistic models)
68
 
 
72
  - Upscaler : Latent (bicubic antialiased)
73
  - CFG Scale : 5 to 9
74
  - Denoise strength for img2img: 0.4 to 0.7
75
+
76
+
77
  ---
 
78
  # LORA Detail
79
+ ---
80
  ## KoreanDollLikeness
81
 
82
  The first version that is widely used by many authors/AI artist/creators
 
99
 
100
  <img src="https://files.catbox.moe/thehrt.png" widht="" height="">
101
 
102
+ ---
103
+
104
  ## JapaneseDollLikeness
105
 
106
  The Japanese variant version, subjected for v15 in the future
 
111
 
112
  <img src="https://files.catbox.moe/cfypot.png" width="" height="">
113
 
114
+ ---
115
+
116
  ## TaiwanDollLikeness
117
 
118
  The Taiwan variant version, I have decided to discontinue v10, it is still out there somewhere in the internet, you may still find it.
 
123
 
124
  <img src="https://files.catbox.moe/5vr2z4.png" width="" height="">
125
 
 
126
  ---
127
  # FAQ
128
  - # Q: Why can't I produce the same pictures as you?
129
+ - A: Sorry I don't share my prompt, you may check the recommended settings, but you may ask me for advice on Twitter or Pixiv
130
 
131
  - # Q: What is the difference of each version upgrade?
132
  - A: Version upgrade does not mean it will fix hands or legs, it is mainly difference of the face of the LORA, newer versions have wider range of faces.