Models>

Mirishita Game Card Style LoRA | MILLION LIVE!/ミリオンライブ/ミリシタ

mirishita style, (best quality, 8K, masterpiece, ultra detailed:1.2), night, light particles, blurry, blurry background, blurry foreground, sparkle, neon lights, crowded street, starry sky, constellation, 
1girl, solo, skirt, smile, looking at viewer, white sailor collar, blue shirt, sailor collar, blue skirt, pleated skirt, short sleeves, :d, shirt, school uniform, blush, serafuku, collarbone, bow, ribbon, blue bow
mirishita style, (best quality, 8K, masterpiece, ultra detailed:1.2), night, light particles, blurry, blurry background, blurry foreground, sparkle, neon lights, crowded street, starry sky, constellation,
1girl, solo, skirt, smile, looking at viewer, white sailor collar, blue shirt, sailor collar, blue skirt, pleated skirt, short sleeves, :d, shirt, school uniform, blush, serafuku, collarbone, bow, ribbon, blue bow
pregnant, drunk, sleepy, blush, light smile
mirishita style, (best quality, 8K, masterpiece, ultra detailed:1.2), night, light particles, blurry, blurry background, blurry foreground, sparkle, neon lights, crowded street, starry sky, constellation, 
1girl, solo, skirt, smile, looking at viewer, white sailor collar, blue shirt, sailor collar, blue skirt, pleated skirt, short sleeves, :d, shirt, school uniform, blush, serafuku, collarbone, bow, ribbon, blue bow
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

Preface: I made a LoHa model of MLTD game card style on May 26, 2023. Later, I trained the art style LoRA with the help of PixAI. This model is trained on Anything V5, with higher resolution, more materials (100 game cards), and the performance seems better. Feel free to try out this model and share your artworks on PixAI: https://pixai.art/model/1652809153949156019.

The trigger word is mirishita style.

The LoRA weight of sample is 0.95; you can try other weights.

Colorful and high saturation VAE e.g. kl-f8-anime2 is recommended.

I'll appreciate it if you're willing to use this LoHa model and share AI arts to other people. My models and illustrations are free for everyone, and if you like them, please support me at Patreon or 爱发电.

——————

写在最前:2023年5月26日,我制作了MLTD游戏卡面风格的LoHa模型。后来,我在PixAI的帮助下训练了艺术风格LoRA,本模型在Anything V5基础上训练,分辨率更高、素材更多(100张游戏卡面),表现看起来也更好。 欢迎试用此模型并分享您的作品:https://pixai.art/model/1652809153949156019

模型的触发词为 mirishita style

示例图的权重为0.95,您也可以尝试其他权重值

推荐使用诸如kl-f8-anime2这样鲜艳和高对比度的VAE

如果您愿意使用本模型并将作品分享给其他人,本人将不胜感激。本人制作的所有模型和绘画皆免费提供,如果觉得还不错的话,欢迎在Patreon爱发电上支持我,非常感谢

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.