产品设计01-LORA

LORA

转载

田心雨

设计

运行3.5K

一个基本的Lora，并用多种检查点对其进行了测试，结果是不同类型的“极简主义；用了100 张具有“简约”风格的图像训练了这个模型（可能我会训练更多样式）。75%是产品，22%是运输，其中大部分是扬声器，智能机器人，水瓶等。我将通过添加100 多个具有各种形状和不同类型的图像来增强模型。我意识到这些模型在车辆-汽车形状中工作得很好，即使训练数据集中没有那么多车辆。

触发词：emauromin style,

TAG示例：

Positive prompt: emauromin style, futuristic armchair, finely detailed, purism, ue 5, a computer rendering, minimalism, octane render, 4k <lora:eddiemauroLora2:0.8>

Negative prompt: EasyNegative, (worst quality:2), (low quality:2), (normal quality:2), lowres, ((monochrome)), ((grayscale)), cropped, text, jpeg artifacts, signature, watermark, username, sketch, cartoon, drawing, anime, duplicate, blurry, semi-realistic, out of frame, ugly, deformed

Steps, from 20-40 (For EulerA is enough 20, and you can use also DPM++SDE Karras, but EulerA is better mostly)

CFG scale: 7-8.

版本详情

基底模型

SD 1.5

迭代步数

1000

训练总轮数

触发词

描述

Example Prompt: Positive prompt: emauromin style, futuristic armchair, finely detailed, purism, ue 5, a computer rendering, minimalism, octane render, 4k <lora:eddiemauroLora2:0.8> Negative prompt: EasyNegative, (worst quality:2), (low quality:2), (normal quality:2), lowres, ((monochrome)), ((grayscale)), cropped, text, jpeg artifacts, signature, watermark, username, sketch, cartoon, drawing, anime, duplicate, blurry, semi-realistic, out of frame, ugly, deformed Steps, from 20-40 (For EulerA is enough 20, and you can use also DPM++SDE Karras, but EulerA is better mostly) CFG scale: 7-8.