Quick Generate
Select a style, write what you want to see and click Generate
masterpiece,realistic,1girl is holding a magic shield, <lora:magic_v3beta:0.55>,
masterpiece,realistic,1girl is building a magic circle, <lora:magic_v3beta:0.55>,
What you want in the image.
Clear
Random

Model Description by Creator

本lora包含三个魔法概念:magic shield, magic portal, magic circle,使用方法见示例,我第一个概念型lora,有优化方案可以和我讲,另外这里问一下如何减少训练集内出场人物对训练结果的影响,知道并且愿意分享的可以在下面评论。

v1: dim 512,细节理论上更多,试验也更稳定

v2: dim 128, 魔法的发散性更强,稍微不稳定

v3beta: dim256,去除了一点模糊的感觉,高清修复能完美去除,但是这个版本的魔法没有发散性。增强了训练集的画质和提高了亮度和对比度,训练方式也有不同, 是一个全新的版本,令我不满意的是魔法阵太圆了!!

例图都能直出

另外如果使用本来就有以上三个魔法概念的大模型出图,把权重调低一点可以改变原来魔法概念的颜色。就比如使用majic大模型出图的时候本来就有magic circle概念的,原来的魔法阵是画在桌子上的,合并的出图效果就是桌子上的魔法阵变成了金色。

Images Generated With This Model

masterpiece,realistic, 1girl building  a magic circle,  <lora:magic_v1:0.7>,
N/A
Hidden For Public Users
masterpiece,realistic, 1girl building a magic circle, <lora:magic_v1:0.7>,
masterpiece,realistic, 1girl in a magic portal,  <lora:magic_v1:0.6>,
N/A
Hidden For Public Users
masterpiece,realistic, 1girl in a magic portal, <lora:magic_v1:0.6>,
masterpiece,realistic,1girl building a magic circle,  <lora:magic_v1:0.6>
N/A
Hidden For Public Users
masterpiece,realistic,1girl building a magic circle, <lora:magic_v1:0.6>
masterpiece,realistic, 1girl holding a magic shield,  <lora:magic_v1:0.7>,
N/A
Hidden For Public Users
masterpiece,realistic, 1girl holding a magic shield, <lora:magic_v1:0.7>,
masterpiece,realistic, 1girl holding a magic shield,  <lora:magic_v1:0.7>,
N/A
Hidden For Public Users
masterpiece,realistic, 1girl holding a magic shield, <lora:magic_v1:0.7>,
masterpiece,realistic, 1girl in a magic portal,  <lora:magic_v1:0.7>,
N/A
Hidden For Public Users
masterpiece,realistic, 1girl in a magic portal, <lora:magic_v1:0.7>,
masterpiece,realistic,1girl building a magic circle,  <lora:magic_v1:0.7>
N/A
Hidden For Public Users
masterpiece,realistic,1girl building a magic circle, <lora:magic_v1:0.7>
masterpiece,realistic, a magic circle,  <lora:magic_v1:0.7>,no humans,
N/A
Hidden For Public Users
masterpiece,realistic, a magic circle, <lora:magic_v1:0.7>,no humans,
masterpiece,realistic,1girl building a magic circle,  <lora:magic_v1:0.7>
N/A
Hidden For Public Users
masterpiece,realistic,1girl building a magic circle, <lora:magic_v1:0.7>
masterpiece,realistic,1girl building a magic circle,  <lora:magic_v1:0.7>
N/A
Hidden For Public Users
masterpiece,realistic,1girl building a magic circle, <lora:magic_v1:0.7>
masterpiece,realistic, 1girl in a magic portal,<lora:magic_v2:0.85>,
N/A
Hidden For Public Users
masterpiece,realistic, 1girl in a magic portal,<lora:magic_v2:0.85>,
masterpiece,realistic, 1girl holding a magic shield,<lora:magic_v2:0.6>,
N/A
Hidden For Public Users
masterpiece,realistic, 1girl holding a magic shield,<lora:magic_v2:0.6>,

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.