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.