TAG:souryuu_asuka_langley, bodysuit, red_bodysuit, neon_genesis_evangelion, medium_breasts, plugsuit

2.0 Version Update

1. Trained with 2000 images for better generalization.

2. Improved outfit restoration for more accurate results.

3. Enhanced image quality and expression for better visual representation.

2.0版本更新

1.使用2000张图片训练，更好的泛化

2.更好的换装还原

3.更好的画质和表现力

尽管wildcard/character.txt · Linaqruf/animagine-xl at main (huggingface.co)

中包含了souryuu_asuka_langley 明日香的标签，但是他的角色还原度并没有达到我的预期（相当来说，不是很像），于是，我还是训练了这个lora。

TAG: orange_hair, blue_eyes, plugsuit, breasts, long_hair, red_bodysuit, interface_headset

Based on https://civitai.com/models/260267/animagine-xl-v3 training

Training model: Animagine XL V3

Inference model: Animagine XL V3

Training resolution: 1024*1024

Recommended output resolution: 1024*1280

Recommended model weight: 0.8~1

基于https://civitai.com/models/260267/animagine-xl-v3 训练

训练模型：Animagine XL V3

跑图模型：Animagine XL V3

训练分辨率：1024*1024

建议出图分辨率：1024*1280

建议模型权重：0.8~1