Update README.md
Browse files
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
|
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](#
|
22 |
-
- [LORA Detail](#
|
23 |
-
- [KoreanDollLikeness](#
|
24 |
-
- [
|
25 |
-
- [
|
26 |
-
- [
|
27 |
-
- [JapaneseDollLikeness](#
|
28 |
-
- [
|
29 |
-
- [TaiwanDollLikeness](#
|
30 |
-
- [
|
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
|
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.
|