モデル/veryBadImageNegative - veryBadImageNegative_v13

veryBadImageNegative - veryBadImageNegative_v13

|
10/21/2024
|
7:14:07 AM
| Discussion|
0
Portrait of a handsome young man with wavy blonde hair and blue eyes, wearing elegant beige suit and white shirt, set in a classic interior.
A vibrant anime landscape showing lush greenery-covered mountains under a bright blue sky with clouds, with a split view revealing crystal-clear underwater filled with colorful fish.
Close-up of a voluptuous anime girl with curly black hair and green eyes, wearing a detailed red dress with fantasy-inspired armor, sitting in a desert.
A stylized ink art anime girl standing on a glowing red platform with a large red sun behind her, surrounded by abstract black ink patterns and urban ruins under a blue sky.
Anime girl with orange hair in a school uniform and yellow cardigan sitting in a cozy kitchen with wooden shelves, cooking utensils, and fresh vegetables.
A mature female character with curly black hair, greenish hazel eyes, and a voluptuous figure wearing a maid outfit and jewelry in a sunlit forest setting.
A voluptuous woman with long curly black hair, greenish hazel eyes, and a mischievous smile wearing a white t-shirt and dark mini skirt leaning forward in front of an abandoned school window.
A dark fantasy themed image of a sorrowful female figure surrounded by skulls and roses, illuminated with dramatic Rembrandt lighting and intricate detail.
Anime illustration of a mature female with curly black hair and greenish hazel eyes, smiling while holding a bottle of juice, wearing a tea rose security guard uniform in a vintage garage setting.
Close-up of a fantasy elf character with black curly hair, green eyes, pointed ears, glowing sword, and fairy wings wearing a green outfit
A mature female with thick curly black hair, greenish hazel eyes, wearing a purple velvet gothic lolita dress leans forward beside a spa pool within classical stone pillars.
Voluptuous woman with curly black hair, greenish hazel eyes, and a surprised expression stands in an enchanted forest surrounded by red-capped mushrooms wearing a purple gothic lolita dress.

推奨プロンプト

(((masterpiece,best quality,official art,extremely detailed CG unity 8k wallpaper))),illustration,landscape,solo,1girl,bishojo,beautiful detailed eyes,Student uniforms

推奨ネガティブプロンプト

no prompt

推奨パラメータ

samplers

DPM++ 2M Karras

steps

20

cfg

10

resolution

512x512

other models

AOM3A1B_orangemixs (5493a0ec49), viewer-mix_v1.3-vae (0b6ccf3b97)

推奨ハイレゾパラメータ

upscaler

Latent, Latent (nearest-exact)

upscale

2

steps

20

denoising strength

0.6

ヒント

veryBadImageNegative_v1.2を使用する際、柔軟性を高めるためにウェイトを減らすことができます。例: (veryBadImageNegative_v1.2-6400:0.9)

トレーニングステップの数(1600 ~ 6400)はトレーニング中のステップ数を表しています。理論的にはステップが多ければ多いほど効果が良くなります。

v1.3

veryBadImageNegative_v1.3は新しいトレーニングアトラスを使用し、AOM3やviewer-mix_v1.7で優れた性能を発揮します。

veryBadImageNegative_v1.3 uses a new training atlas and performs well when used in AOM3 and viewer-mix_v1.7.

v1.2

veryBadImageNegativeはviewer-mix_v1.3で生成された特別なアトラスを使用してトレーニングされたネガティブエンベディングです。

したがって、veryBadImageNegativeはviewer-mix_v1.3の専用ネガティブエンベディングです。

他の拡散モデルでも良好な効果があるかもしれませんが、検証が不足しています。

veryBadImageNegative is a negative embedding trained from the special atlas generated by viewer-mix_v1.3.

So veryBadImageNegative is the dedicated negative embedding of viewer-mix_v1.3.

It may also have a good effect in other diffusion models, but it lacks verification.

v1.2について:

画像の質を高め、スタイルを弱めます。

v1.2を使用する際、ウェイトを減らすことで更に良い柔軟性を得ることができます。

例: (veryBadImageNegative_v1.2-6400:0.9)

About v1.2:

Enhance image quality and weaken style.

When using v1.2, you can reduce some weights to obtain better flexibility.

For example: (veryBadImageNegative_v1.2-6400:0.9)

v1.0とv1.1の違いについて:

ほとんど違いはありません。トレーニングに使用されるアトラスは生成パラメータに若干の違いがあります。

1600~6400の差異について:

数字はトレーニングステップ数を表し、理論的にはステップ数が多ければ効果が良くなります。

About the difference between v1.0 and v1.1:

There is almost no difference. The atlas used for training only has some subtle differences in the generation parameters.

About the difference between 1600 ~ 6400:

The number represents the number of training steps. In theory, the more steps, the better the effect.

前の画像
AutismMix SDXL - AutismMix_pony
次の画像
ExpressiveH Hentai LoRa Style - ExpressiveH

モデル詳細

モデルタイプ

TextualInversion

ベースモデル

SD 1.5

モデルバージョン

veryBadImageNegative_v1.3

モデルハッシュ

d70463f870

学習済みワード

verybadimagenegative_v1.3

作成者

ディスカッション

コメントを残すには log in してください。

「veryBadImageNegative - veryBadImageNegative_v13」による画像

ネガティブ画像