Models>

Semi-closed eyes / 極細の眼

<lora:hosome_v100:1>
(cleavage:-1.5),insanely detailed, absurdres, ultra-highres, ultra-detailed, best quality, 1girl, solo, 16 years old, nice hands, perfect hands, BREAK, (wearing school uniform), happy smile, laugh, closed mouth, cute pose, cowboy shot, BREAK, slender, kawaii, perfect symmetrical face, ultra cute girl, ultra cute face, ultra detailed eyes, ultra detailed hair, ultra cute, ultra beautiful, BREAK, in harajuku, shibuya, tokyo, street, crowd, cityscape, medium breasts BREAK, (white medium hair, dark red eyes), hair between eyes
insanely detailed, absurdres, ultra-highres, ultra-detailed, best quality, 1 girl, solo, 16 years old, nice hands, perfect hands, BREAK, wearing sweater, happy smile, laugh, closed mouth, sitting, 45 angle, cowboy shot, looking at viewer, BREAK, slender, kawaii, perfect symmetrical face, ultra cute girl, ultra cute face, ultra detailed eyes, ultra detailed hair, ultra cute, ultra beautiful, by Canon EOS, SIGMA Art Lens 35mm F1.4, ISO 200 Shutter Speed 2000, BREAK, indoors, in coffee shop, medium large breasts,,black hair, long hair, black eyes <lora:flat2:-0.3>

<lora:hosome_v100:1>
<lora:hosome_v100:1.5>

(cleavage:-1.5), insanely detailed, absurdres, ultra-highres, ultra-detailed, best quality, 1girl, solo, nice hands, perfect hands, BREAK, (wearing houndstooth pattern dress), happy smile, laugh, closed mouth, dynamic pose, from below, cowboy shot, BREAK, slender, kawaii, perfect symmetrical face, ultra cute girl, ultra cute face, ultra detailed eyes, ultra detailed hair, ultra cute, ultra beautiful, BREAK, in forest, BREAK, elf girl, blonde hair, elf ear, pink eyes, large breasts, cleavage
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

(日本語説明は後半にあります)

Reproduces semi-closed (very thin) eyes, or widely open eyes (by minus LoRA weight).

Usage

Suitable for anime-style models. With most photorealistic models, it won't work well.

Just enable LoRA to activate. No extra prompts are needed.

Eye openness can be adjusted LoRA strength for some extent (up to 1.5). Minus weight (limited to approx. -0.3) makes wider eyes.

It is possible to customize eye shapes by using with Eye collection series(on HuggingFace) simultaneously. If use multipe eye LoRA simultaneously, set each weight halved(e.g. 0.5 ~ 0.75).

About file name: "hosome" is Japanese word, meaning "hoso (thin)" - "me (eye)".

On my HuggingFace repo, you can download more various other LoRAs. please check it out.

https://huggingface.co/JujoHotaru/lora


閉じかけ、極細の眼を再現できます。マイナス適用すると広く開いた眼にもできます。

細目キャラクターのほか、まばたきアニメーションの中間状態の作成にも使用できます。

使い方

アニメ系のデータモデル向きです。写真系のデータモデルではほとんどの場合うまく動作しません。

LoRAを有効にするだけで発動します。

眼の閉じ具合は、LoRA適用強度(1.5くらいまで)で調整することができます。強度をマイナスにすると逆に眼を見開くことができますが、その場合の強度は-0.3くらいまでとします。それより下げると瞳が濁ります。

アイコレクション(HuggingFaceで公開中) など、当方公開の他の眼LoRAと同時に適用することで眼の形をさらにカスタマイズすることもできます。この場合、それぞれのLoRAの強度は応分(2つなら0.5ずつにするなど)してください。

HuggingFaceリポジトリでは、他にもさまざまなLoRAを公開しています。

https://huggingface.co/JujoHotaru/lora

Images Generated With This Model

Loading...

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.