太懒了不想写介绍,所以是复制粘贴
“这个可能大概也许是木头人”
由多张木头人图片包括概念图广告等训练。强烈风格震撼。请注意,本lora可能与一些纯2d模型相性较差。
【请注意,本lora有严重的背景虚化】
起因是我的铜人lora下网友的建议,真的是很有创意,所以木头人lora诞生了
这次加关键词statue,我的例图使用的模型是:abyssorangemix3AOM3_aom3a3,lora权重是:0.55,仅供参考。
ღ( ´・ᴗ・` )比心
(statue:1.2),solo,masterpiece,best quality,1girl,<lora:木头人:0.55>
Negative prompt: (nsfw:1.2),(bad and mutated hands:1.3), (worst quality:2.0), (low quality:2.0), (blurry:2.0),
Steps: 10, Sampler: DPM++ 2S a Karras, CFG scale: 7, Size: 512x640,Denoising strength: 0.5, Clip skip: 2,
Hires upscale: 2, Hires steps: 10, Hires upscaler: R-ESRGAN 4x+
以下机翻
【【Please note that Ben lora has severe background blurring】】
Too lazy to write an introduction, so copy and paste
"This could be, maybe it could be a wooden person."
Trained by multiple images of wooden people, including concept images, advertisements, etc. Strong style shock. Note that this lora may be poorly compatible with some pure 2d models.
It started with my bronze lora's online friend's suggestion, which was really creative, so wooden lora was born
need to add keywords :statue, My example diagram uses the model: abyssorangemix3AOM3_aom3a3, and the weight of lora is 0.55, just for reference.
(statue:1.2),solo,masterpiece,best quality,1girl,<lora:木头人:0.55>
Negative prompt: (nsfw:1.2),(bad and mutated hands:1.3), (worst quality:2.0), (low quality:2.0), (blurry:2.0),
Steps: 10, Sampler: DPM++ 2S a Karras, CFG scale: 7, Size: 512x640,Denoising strength: 0.5, Clip skip: 2,
Hires upscale: 2, Hires steps: 10, Hires upscaler: R-ESRGAN 4x+