Tensor.Art
Create

缤纷

LORA
Original

Updated:

1.0

基于 80 张 AI 图片训练，用来生成 2D 和 2.5D 的大头、半身和大半身图片，产出缤纷的头饰和衣服，适配主流二次元和三次元大模型。

在 512*768 分辨率下不开启修脸出图效果也不错，如果稍微增加图片高度，比如 512*840，可以获得更完整的出图。

开启修脸如 AD 等插件得到更接近真人的效果。

测试条件如下：

Prompt:

delicate and beautiful, best quality, Masterpiece,

Hyper detailed, Intricate detail, Exquisite detail,

1girl, solo, looking at viewer, earrings, black hair, hair ornament, hair bun, double bun, makeup, red lips, chinese clothes, jewelry,

Negative prompt:

ng_deepnegative_v1_75t, bad-hands-5,

Steps: 20,

Sampler: DPM++ 2M SDE Karras,

CFG scale: 7,

Size: 512x768, 512x840

Model: moonmix_utopia30,

Clip skip: 2,

Version Detail

SD 1.5
10
20
产出 2D 和 2.5D 效果的缤纷头饰和服饰效果，从默认分辨率到开启高清及修脸都能获得高质量出图。示例图片参数（开启2 倍高清，前四张开启修脸插件 AD）： Prompt: delicate and beautiful, best quality, Masterpiece, Hyper detailed, Intricate detail, Exquisite detail, 1girl, solo, looking at viewer, earrings, black hair, hair ornament, hair bun, double bun, makeup, red lips, chinese clothes, jewelry, Negative prompt: ng_deepnegative_v1_75t, bad-hands-5, Steps: 20, Sampler: DPM++ 2M SDE Karras, CFG scale: 7, Size: 512x768, 512x840, Model: moonmix_utopia30, Clip skip: 2,

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

No posts yet
Describe the image you want to generate, then press Enter to send.