Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,57 @@
|
|
1 |
---
|
2 |
license: creativeml-openrail-m
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: creativeml-openrail-m
|
3 |
+
language:
|
4 |
+
- ja
|
5 |
---
|
6 |
+
Nakagin Capsule Tower Building Lora File
|
7 |
+
|
8 |
+
We are learning three parts: the building exterior, the room, and the bathroom.
|
9 |
+
Please use the value of Lora at about 0.8 to 1.2
|
10 |
+
If adding elements to the image weakens Lora's expression, increase Lora's number to ~1.2 or add tags for the elements included in the data to reinforce it
|
11 |
+
|
12 |
+
Here are the calling and additional tags for each scene:
|
13 |
+
room
|
14 |
+
Invocation tag: nkr room
|
15 |
+
Additional tags:
|
16 |
+
indoors, realistic photo background
|
17 |
+
window, console, bed, CRT TV
|
18 |
+
|
19 |
+
exterior
|
20 |
+
call tag: nkg building
|
21 |
+
additional tag:
|
22 |
+
outdoors, realistic, photo background
|
23 |
+
road, city,
|
24 |
+
|
25 |
+
Bathroom
|
26 |
+
Invocation tag:
|
27 |
+
nkb, bathroom
|
28 |
+
Additional tags:
|
29 |
+
indoors, realistic photo background
|
30 |
+
toilet, sink, mirror, bathtub, etc.
|
31 |
+
|
32 |
+
中銀カプセルタワービルのLoraファイルです
|
33 |
+
ビル外観、部屋、バスルームの三か所を学習しています
|
34 |
+
Loraの数値は0.8~1.2程度で使用して下さい
|
35 |
+
画像に要素を追加することでLoraの表現が弱くなる場合、Loraの数値を~1.2に上げるかデータに含まれる要素のタグを加えて補強してください
|
36 |
+
各シーンの呼び出しタグと追加タグは次のとおりです
|
37 |
+
|
38 |
+
部屋
|
39 |
+
呼び出しタグ:nkr room
|
40 |
+
追加タグ:
|
41 |
+
indoors,realistic, photo background
|
42 |
+
window, console, bed, CRT TV
|
43 |
+
|
44 |
+
外観
|
45 |
+
呼び出しタグ:nkg, building,
|
46 |
+
追加タグ:
|
47 |
+
outdoors, realistic, photo background
|
48 |
+
road, city
|
49 |
+
|
50 |
+
バスルーム
|
51 |
+
呼び出しタグ:
|
52 |
+
nkb, bathroom
|
53 |
+
追加タグ:
|
54 |
+
indoors,realistic, photo background
|
55 |
+
toilet, sink, mirror,bathtubなど
|
56 |
+
|
57 |
+
学習元はNAIとchilloutです
|