Lasorco commited on
Commit
71b40a1
1 Parent(s): 529a69a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -6
README.md CHANGED
@@ -8,38 +8,51 @@ tags:
8
  ---
9
 
10
  This model was merged because I wanted a model that I personally liked. It is specifically designed to represent young girls.<br>
11
- <br>
12
  I suggested adding "loli, big eyes," (sometimes with more emphasis) to the prompt.<br>
13
  Other suggestions include "child, child body, kawaii, tareme," etc.<br>
14
  Of course, you can also emphasize "best quality,insanely detailed illustration," etc. to improve the quality.<br>
15
  For the negative, we recommend "(worst quality, low quality:1.4)," as well as TI's EasyNegative and bad_pictures.<br>
16
  If you put "tsurime, smirk," etc. in the negatives, you may be able to express softer expressions.<br>
17
- <br>
18
  LoRA and the others don't work well. It might be better if merged with the mainstream mode, but we don't know yet because we haven't tried it.<br>
19
  In that sense, it is a difficult model to work with.<br>
 
 
 
 
20
  <br>
21
  <br>
 
22
  这个模型之所以被合并,是因为我想要一个我个人喜欢的模型。它是专门为代表年轻女孩而设计的。<br>
23
- <br>
24
  我建议在提示中加入 "loli, big eyes,"(有时更强调)。其他建议包括 "child, child body, kawaii, tareme,"等。<br>
25
  当然,你也可以强调 "best quality,insanely detailed illustration,"等,以提高质量。<br>
26
  对于底片,我们推荐"(worst quality, low quality:1.4),",以及TI的EasyNegative和bad_pictures。<br>
27
  如果你在底片中放上"tsurime, smirk"等,也许能表现出更柔和的表情。<br>
28
- <br>
29
  LoRA和其他的效果并不好。如果与主流模式合并,可能会更好,但我们还不知道,因为我们还没有试过。<br>
30
  从这个意义上说,它是一个很难操作的模式。<br>
 
 
 
 
31
  <br>
32
  <br>
 
33
  個人的に好みの絵柄が欲しくてマージしたモデルです。幼い女の子を描写するのに特化しています。<br>
34
- <br>
35
  promptには"loli, big eyes,"を(ときにはさらに強調して)入れることを推奨します。他"child, child body, kawaii, tareme,"などもおすすめです。<br>
36
  もちろんクオリティアップとして"best quality,insanely detailed illustration,"なども強調して入れてください。<br>
37
  negativeには"(worst quality, low quality:1.4),"とTIのEasyNegative,やbad_pictures,を推奨します。<br>
38
  "tsurime, smirk,"などをnegativeに入れればより優しい表情を表現できるかもしれません。<br>
39
- <br>
40
  LoRAなどの効き目は良くありません。主流なモデルとマージすれば良化するかもしれませんが試していないので未知数です。<br>
41
  そういう意味では扱いにくいモデルと言えるでしょう。<br>
42
 
 
 
 
43
 
44
  ---
45
  # v1300 It will probably be the last model
 
8
  ---
9
 
10
  This model was merged because I wanted a model that I personally liked. It is specifically designed to represent young girls.<br>
11
+
12
  I suggested adding "loli, big eyes," (sometimes with more emphasis) to the prompt.<br>
13
  Other suggestions include "child, child body, kawaii, tareme," etc.<br>
14
  Of course, you can also emphasize "best quality,insanely detailed illustration," etc. to improve the quality.<br>
15
  For the negative, we recommend "(worst quality, low quality:1.4)," as well as TI's EasyNegative and bad_pictures.<br>
16
  If you put "tsurime, smirk," etc. in the negatives, you may be able to express softer expressions.<br>
17
+
18
  LoRA and the others don't work well. It might be better if merged with the mainstream mode, but we don't know yet because we haven't tried it.<br>
19
  In that sense, it is a difficult model to work with.<br>
20
+
21
+ Oops, I forgot to mention that VAE is not internalized, so use whatever you like.<br>
22
+ All samples use "anything-v4.0.vae".<br>
23
+ I think ClearVAE is nice and the others are attractive.<br>
24
  <br>
25
  <br>
26
+
27
  这个模型之所以被合并,是因为我想要一个我个人喜欢的模型。它是专门为代表年轻女孩而设计的。<br>
28
+
29
  我建议在提示中加入 "loli, big eyes,"(有时更强调)。其他建议包括 "child, child body, kawaii, tareme,"等。<br>
30
  当然,你也可以强调 "best quality,insanely detailed illustration,"等,以提高质量。<br>
31
  对于底片,我们推荐"(worst quality, low quality:1.4),",以及TI的EasyNegative和bad_pictures。<br>
32
  如果你在底片中放上"tsurime, smirk"等,也许能表现出更柔和的表情。<br>
33
+
34
  LoRA和其他的效果并不好。如果与主流模式合并,可能会更好,但我们还不知道,因为我们还没有试过。<br>
35
  从这个意义上说,它是一个很难操作的模式。<br>
36
+
37
+ 哎呀,我忘了说,VAE不是内化的,所以使用你喜欢的东西。<br>
38
+ 所有样本都使用 "anything-v4.0.vae"。<br>
39
+ 我认为ClearVAE很好,其他的也很有吸引力。<br>
40
  <br>
41
  <br>
42
+
43
  個人的に好みの絵柄が欲しくてマージしたモデルです。幼い女の子を描写するのに特化しています。<br>
44
+
45
  promptには"loli, big eyes,"を(ときにはさらに強調して)入れることを推奨します。他"child, child body, kawaii, tareme,"などもおすすめです。<br>
46
  もちろんクオリティアップとして"best quality,insanely detailed illustration,"なども強調して入れてください。<br>
47
  negativeには"(worst quality, low quality:1.4),"とTIのEasyNegative,やbad_pictures,を推奨します。<br>
48
  "tsurime, smirk,"などをnegativeに入れればより優しい表情を表現できるかもしれません。<br>
49
+
50
  LoRAなどの効き目は良くありません。主流なモデルとマージすれば良化するかもしれませんが試していないので未知数です。<br>
51
  そういう意味では扱いにくいモデルと言えるでしょう。<br>
52
 
53
+ おっと忘れていましたVAEは内包していないので好きなものを使用してください。<br>
54
+ サンプルはすべて”anything-v4.0.vae”を使用しています。<br>
55
+ ClearVAEも素敵だと思いますし、他のものも魅力的ですね。<br>
56
 
57
  ---
58
  # v1300 It will probably be the last model