|
--- |
|
license: creativeml-openrail-m |
|
tags: |
|
- stable-diffusion |
|
- stable-diffusion-diffusers |
|
- text-to-image |
|
- diffusers |
|
--- |
|
|
|
This model was merged because I wanted a model that I personally liked. It is specifically designed to represent young girls.<br> |
|
<br> |
|
I suggested adding "loli, big eyes," (sometimes with more emphasis) to the prompt.<br> |
|
Other suggestions include "child, child body, kawaii, tareme," etc.<br> |
|
Of course, you can also emphasize "best quality,insanely detailed illustration," etc. to improve the quality.<br> |
|
For the negative, we recommend "(worst quality, low quality:1.4)," as well as TI's EasyNegative and bad_pictures.<br> |
|
If you put "tsurime, smirk," etc. in the negatives, you may be able to express softer expressions.<br> |
|
<br> |
|
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> |
|
In that sense, it is a difficult model to work with.<br> |
|
<br> |
|
<br> |
|
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> |
|
<br> |
|
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> |
|
当然，你也可以强调 "best quality,insanely detailed illustration,"等，以提高质量。<br> |
|
对于底片，我们推荐"(worst quality, low quality:1.4),"，以及TI的EasyNegative和bad_pictures。<br> |
|
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> |
|
<br> |
|
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> |
|
从这个意义上说，它是一个很难操作的模式。<br> |
|
<br> |
|
<br> |
|
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> |
|
<br> |
|
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> |
|
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> |
|
negativeには"(worst quality, low quality:1.4),"とTIのEasyNegative,やbad_pictures,を推奨します。<br> |
|
"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> |
|
<br> |
|
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> |
|
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> |
|
|
|
|
|
--- |
|
# v1300 It will probably be the last model |
|
 |
|
``` |
|
(best quality,insanely detailed:1.2), 1girl, loli, (big eyes), angel, white hair, angel halo, night, cowboy shot, |
|
Negative prompt: (worst quality, low quality:1.4),EasyNegative,bat anatomy, |
|
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 3173364441, Size: 512x768, Model hash: 79eb181c3c, Model: lametta_v1300_fp16 |
|
``` |
|
|
|
--- |
|
# v930 |
|
 |
|
``` |
|
(best quality,insanely detailed:1.2), 1girl, loli, (big eyes), brown eyes, little red riding hood, blonde bob cut, over knee socks, brown lace-up boots, brown corset, neck ribbon, outdoors, picnic basket, sitting, cowboy shot, |
|
Negative prompt: (worst quality, low quality:1.4),EasyNegative,bat anatomy,nsfw, |
|
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 4245979701, Size: 512x768, Model hash: 8c9629b8f5, Model: lametta_v930_fp16 |
|
``` |
|
|
|
--- |
|
# v901 |
|
 |
|
``` |
|
(best quality,insanely detailed:1.2), 1girl, loli, (big eyes), maid, maid apron, maid headdress, puffy sleeves,cowboy shot, |
|
Negative prompt: (worst quality, low quality:1.4),EasyNegative,bat anatomy, |
|
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 4200697050, Size: 512x768, Model hash: 3daae6968f, Model: lametta_v901afp16 |
|
``` |
|
|
|
|
|
--- |
|
# v413 |
|
 |
|
``` |
|
(best quality,insanely detailed:1.2), 1girl, loli, (big eyes), swimsuit, summer, poolside, |
|
Negative prompt: (worst quality, low quality:1.4),EasyNegative,bat anatomy, |
|
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 1007819098, Size: 512x768, Model hash: f48839746f, Model: lametta_v413fp16 |
|
``` |
|
|
|
|
|
--- |
|
# v405 |
|
 |
|
``` |
|
(best quality,insanely detailed:1.2), 1girl, loli, (big eyes), (magical girl:1.2), cat ears, skirt, cowboy shot, |
|
Negative prompt: (worst quality, low quality:1.4),EasyNegative,bat anatomy, |
|
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2891664245, Size: 512x768, Model hash: 9535c0bba7, Model: lametta_v405_fp16 |
|
``` |
|
|
|
|
|
As before, the model number is only given for working purposes, so there is no particular preference. |
|
I have merged and created 13 different models, and I think that v13xx will probably be the final model number, since the rendering has gradually converged. |
