All Images Here Are Generated By AI.

All Models

>

Japanese mascot. ゆるキャラ

Japanese mascot. ゆるキャラ

white background, no humans, pokemon \(creature\), cat <lora:yuru_kyara:1.0>
white background, no humans, pokemon \(creature\), cat <lora:yuru_kyara:1.0>
1boy, solo, male focus, white background, chibi, kimono <lora:yuru_kyara:1.0>
1boy, solo, male focus, white background, chibi, kimono <lora:yuru_kyara:1.0>
white background, no humans, pokemon \(creature\), apple <lora:yuru_mean:1.0>
white background, no humans, pokemon \(creature\), apple <lora:yuru_mean:1.0>

Generate AI Images. Simple and Easy

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

Model Description by Creator

Prompt

  • No activation word, some helper words

  • girl・女性: white background, solo, 1girl, chibi, ...

  • guy・男性:white background, solo, male focus, 1boy, chibi, ...

  • animal and fruit・動物と果物: white background, solo, no humans, pokemon \(creature\), ...

Notes:

  • data is easy to find: https://chocotabi-saitama.jp/yurutama/ , https://www.homemate.co.jp/chara/ , tagged data available 。 データをアップロードしました

  • it is impossible to make a textual inversion, because the lines are too thick, the text inversion will become 'thick line, thick line, thick line' and look like pixel art 。Text Inversionは難しいです、太い線のせいで、「線、線、線、」になって、キュビスム又はピクセルアートが出ます。

  • you need the helper word 'chibi' or the humans will not converge as fast as the animals during training 。「チビ」を加えると、人間人物と動物人物は同時に収束します

  • I used helper word 'pokemon \(creature\)' because there are 100k images on Danbooru。段ボールでポケモンの画像十万枚ありまして、手伝います。「マスコット」の画像は千枚ありますし、いつもコスプレ、ぬいぐるみ、キーチェーンです。

  • I used simplified tagging for training, because if the apple character has a flower, 'no humans, apple, flower', could also mean a flower character with an apple, which changes the drawing completely。「no humans, apple, flower」は曖昧です(リンゴモチーフ、花を持つか、花モチーフ、リンゴを持つか)、だから数タッグだけを使いました。

  • Other possible helper word that have not been used: straight-on, flat_color, furry. Still need to traina Lora to have a character with the head of a vegetable. ほかのHelper wordも次の学習に加えられる。ですが、人物の頭は野菜・果物に代わりたい場合は、Loraは必要と思います、プロンプトだけでで出来ないと思います(試したことがありません)

  • Trained on AnyLora

Try Full Demo
Quick Generate
Image quality might not be as good as what you can achieve with our full generation tool.
Placeholder
Choose A Style, Type What You Want In The Image And Click Generate
Placeholder
Choose A Style, Type What You Want In The Image 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.
Train Your Own Model

Images Generated With This Model

Loading...

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.