Models>

Hodur | 1mb Aether Gazer | 深空之眼

Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
* This model is available for use and will generate similar character to the ones seen in the images.

Model Description by Creator

Aether Gazer

Hodur

(EN/日本語/中文)

|___________________________________________________________________________________________|

About this LoRA:

Trained with images of the mobile game >Aether Gazer<

Hard to control on 2.5d checkpoints. (I mean by that that the character doesn't really have the typical appearance anymore when used on a 2.5d ckeckpoint.)

___________

>Trained with >CouterfeitV3.0<

___________

>How to use it:

___________

-->Prompts: hoduraether, necktie, black footwear, gloves, double-breasted, armband, buttons, braid, black uniform, glasses, bangs, shirt, black pantyhose, collared shirt, white shirt, black gloves, purple necktie, white hair, military uniform, black pantyhose,

-->Negative: pleated skirt,skirt, dress,cape,coat, hat, (floating hair:1.5), very long hair, absurdely long hair,

___________

-->LoRA strength: 0.8-1

-->Highres fix: Latent

-->Sampler: DPM++ 2M Karras

-->CFG scale: 7~11

________________________________________________________________________________________

Prompt example:

___________

Prompt:

masterpiece, best quality,hoduraether, 1girl, solo, pantyhose, long hair, necktie, (full body:1.5), beach, standing on beach, black footwear, boots, gloves, double-breasted, armband, buttons, braid, black uniform, glasses, breasts, bangs, long sleeves, shirt, black pantyhose, hair between eyes, collared shirt, purple eyes, black miniskirt, white shirt, black gloves, purple necktie, white hair, military uniform, black pantyhose, <lora:HodurAetherGazerV1-000008:0.8>, detailed, standing,

___________

Negative:

EasyNegative, verybadimagenegative_v1.3,illustration, 3d, sepia, painting, cartoons, sketch, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, normal quality, ((monochrome)), ((grayscale)), cut out, cut head,outpaint,pleated skirt,skirt, dress,cape,coat, hat, (floating hair:1.5)

___________

*Important keywords are marked >BOLD<.

*重要なキーワードは >太字< で表記しています。

*重要的关键词被标记为 >粗体字<

________________________________________________________________________________________

このLoRAについて:
___________

モバイルゲーム >エーテルゲイザー< のイメージでトレーニング。

2.5次元のチェックポイントでは操作しにくい。(2.5次元のチェックポイントで使用すると、キャラクターらしい姿が見えなくなる、という意味です)

___________

>CouterfeitV3.0<でトレーニングしました。

___________

>おすすめのせってい:

___________

個人的な推奨チェックポイント:nullV22_nullV22 + clearVAE

___________

-->プロンプト:hoduraether, necktie, black footwear, gloves, double-breasted, armband, buttons, braid, black uniform, glasses, bangs, shirt, black pantyhose, collared shirt, white shirt, black gloves, purple necktie, white hair, military uniform, black pantyhose,

-->ネガチブプロンプト : pleated skirt,skirt, dress,cape,coat, hat, (floating hair:1.5), very long hair, absurdely long hair,

___________

-->LoRA strength: 0.8-1

-->Highres fix: Latent

-->サンプラー DPM++ 2M Karras

-->CFGスケール:7〜11

________________________________________________________________________________________

关于这个LoRA:

___________

用手机游戏>Aether Gazer<的图像进行训练。

在2.5d检查点上难以控制。(我的意思是说,在2.5d检查点上使用时,这个角色其实已经没有典型的外观了)。

___________

>使用>CouterfeitV3.0<进行训练。

___________

>建议:

___________

个人建议检查点:nullV22_nullV22 + clearVAE

___________

-->提示:hoduraether, necktie, black footwear, gloves, double-breasted, armband, buttons, braid, black uniform, glasses, bangs, shirt, black pantyhose, collared shirt, white shirt, black gloves, purple necktie, white hair, military uniform, black pantyhose,

-->负面的: pleated skirt,skirt, dress,cape,coat, hat, (floating hair:1.5), very long hair, absurdely long hair,

___________

-->LoRA强度:0.8-1

-->Highres修复: Latent

-->采样器: DPM++ 2M Karras

-->CFG规模:7~11
_________________________________________________________________________________________

VERSION 1.5:

__________

This version is more of an experimental version.

I have reduced the dataset to only 3 images to see the difference.

The result surprised me. The quality is really good.

__________

このバージョンは、どちらかというと実験的なバージョンです。

違いを見るために、データセットを3枚の画像だけに減らしました。

その結果、私は驚きました。品質が本当に良いのです

__________

这个版本更像是一个实验性的版本。

我把数据集减少到只有3张图片,以观察其差异。

结果令我吃惊。质量真的很好。

Images Generated With This Model

Loading...

Similar Models

甘ブリ Amagi brilliant park:Seiya_Kanie ※not learned”支配人” 転載禁止・無断転載禁止/Do not repost/Civitai Only
V1
甘ブリ Amagi brilliant park:Seiya_Kanie ※not learned”支配人” 転載禁止・無断転載禁止/Do not repost/Civitai Only
(0.00)
0
0 Ratings
Fate: Charlemagne 転載禁止・無断転載禁止/Do not repost/Civitai Only
V1
Fate: Charlemagne 転載禁止・無断転載禁止/Do not repost/Civitai Only
(5.00)
0
2 Ratings
The Idolmaster SideM 【THE 虎牙道】 Takeru Taiga※not learned”虎” 転載禁止・無断転載禁止/Do not repost/Civitai Only
V1
The Idolmaster SideM 【THE 虎牙道】 Takeru Taiga※not learned”虎” 転載禁止・無断転載禁止/Do not repost/Civitai Only
(5.00)
0
1 Ratings
Sendou Asuka (Idol Mahjong Final Romance R) / 千堂 明日香 (アイドル麻雀 ファイナルロマンスR)
V1
Sendou Asuka (Idol Mahjong Final Romance R) / 千堂 明日香 (アイドル麻雀 ファイナルロマンスR)
(5.00)
0
3 Ratings
Mejiro McQueen
V1
Mejiro McQueen
(0.00)
0
0 Ratings
SCARLET NEXUS:Yuito Sumeragi 転載禁止・無断転載禁止/Do not repost/Civitai Only
V1
SCARLET NEXUS:Yuito Sumeragi 転載禁止・無断転載禁止/Do not repost/Civitai Only
(5.00)
0
2 Ratings
北野誠一郎 エンジェル伝説
V1
北野誠一郎 エンジェル伝説
(5.00)
0
2 Ratings
Uruha rushia潤羽るしあテストLoRA 960p
V1
Uruha rushia潤羽るしあテストLoRA 960p
(0.00)
0
0 Ratings
My Hero Academia:Denki Kaminari 転載禁止・無断転載禁止/Do not repost/Civitai Only
V1
My Hero Academia:Denki Kaminari 転載禁止・無断転載禁止/Do not repost/Civitai Only
(0.00)
0
0 Ratings
Uruha rushia潤羽るしあテストLoRA 960p
V1
Uruha rushia潤羽るしあテストLoRA 960p
(0.00)
0
0 Ratings

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.