memegirl,  <lora:memgirl_v2:1>,
(8k), (best quality), (masterpiece:1.2), (realistic), (photorealistic:1.37), ultra-detailed, european girl, 1girl, cute, smile, closed mouth, beautiful detailed eyes, beautiful detailed nose, full body, realistic body, blonde hair,
memegirl,  <lora:memgirl_v2:1>,
masterpiece, best quality, (photorealistic:1.2), extremely_detailed_eyes_and_face, detailed face,  depth of field, detailed face, face focus, ,((ultra skin detail)):10 ,portrait,
[ blurry background],((8k, highest quality, masterpiece)), High detail RAW photo, (realistic, photo realism:1. 37), (highest quality), (best shadow), (best illustration), ultra high resolution, physics-based rendering, cinematic lighting,extremely_detailed_eyes_and_face,detailed face, shiny skin, smile, thick lips,  (portrait),  ultra-detailed, highres, 8k, (best quality), physically-based rendering, Realistic photography,
finely makeup, makeup, pink lipstick, pink eye shadow,
black skirt, college student, dark green hair, dark green blond hair, sunset:5, (blue|red|orange sky),(standing on beach):5,Bondi beach, sea, spindrift,
1girl, petite, (looking at viewer:1.5),[large breasts],
medium shot, standing,
(Draw only one person)
memegirl,  <lora:memgirl_v2:1>,
(8k), (best quality), (masterpiece:1.2), (realistic), (photorealistic:1.37), 
memegirl, blurry, depth_of_field, virtual_youtuber, photo_\(medium\), solo, pink_hairband, long_hair, blurry_background, open_mouth, realistic, 3d, hairband, bangs, looking_at_viewer, blurry_foreground
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

Cute, Easy to use!

可以使用这里免费出图:Lovable Chinese Girl | Meme | Lora - v1 | 吐司 Tusi.Art

Trained by ChilloutMix-Ni.

很容易生成比较可爱的圆脸,但是想要生成有特色的脸需要把权重调到0.8左右比较好。很容易搭配其他风格使用。

All training pictures are from the internet.

Do not use this model in commercials!

Version 2: 经过这段时间的实践,对于这个刚入门时候的Lora进行了翻新。大大缓解了过拟合的问题,此外表情更加丰富,更加符合我出这个Lora的目的,但是出想要的表情需要随机,以及尽可能详细的描述。更直接就使用ControlNet。

对于参数其实不太敏感,但是我喜欢最可爱的,推荐1。

以下展示新旧版本的区别,其实版本一的风格挺独特的,但是第二代效果更自然:

Version 2: After this period of practice, I retrain this Lora. The problem of over-fitting has been greatly alleviated. In addition, the expressions of this character are richer, which is more in line with my purpose of creating this Lora, but the desired expression needs described as much detail as possible. Using ControlNet can be more directly.

It is not very sensitive to the parameters, but I like the cutest, recommend 1.

The following shows the difference between the old and new versions. In fact, the style of version 1 is quite unique, but the effect of the second generation is more natural:

真的非常可爱de:

Do not use for NSFW.

I don't responsible for anything you generated with this 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.