[LoRA] Cumbersome / 繁雑度 Concept (With dropout & noise version)

模型简介：
使用 dropout 和块权重训练的 LoRa 模型。
这是通过 NijiV5 生成的 60+ 张图片训练的 LoRa 模型，是噪声版本。
该模型可以添加带有宝石的背景和服装装饰，具有增强装饰细节和略微改变风格的效果。
建议将此模型与照明模型结合使用。
静物的风格可以根据描述进行一定程度的调整。

~~~~~~~~~~~~~~~~~~~~~~~o(*￣︶￣*)o~~~~~~~~~~~~~~~~~~~~~~~

主图提示词和参数：
Prompt: (((gold, silver, glimmer)), faerie), limited palette, contrast, phenomenal aesthetic, best quality, sumptuous artwork
<lora:cumbersome-block:1>

Negative prompt: (worst quality, low quality:1.4),(animal ears,cat ears,fox ears,ribbon:1.4),(long body:1.2), (realistic, lip, nose, tooth, rouge, lipstick, eyeshadow:1.0), (dusty sunbeams:1.0),(abs, muscular, rib:1.0), (bokeh, blurry:1.4),(motion lines, motion blur:1.4), (greyscale, monochrome:1.0), text, title, logo, signature

Steps: 25, Eta: 0.67, Size: 448x768, Seed: 948160271, Model: tbZmix_v10, Version: v1.4.0, Sampler: DPM++ 2M SDE Karras, CFG scale: 7, Clip skip: 2, Model hash: e5c453838a, Hires steps: 20, Hires upscale: 2, Hires upscaler: Latent (nearest-exact), "cumbersome-block: 4414162a31d7", Denoising strength: 0.6