线稿手绘风格转换器LoRA

使用介绍

模型介绍：可以将人物照片/建筑。风景照等转换为线稿手绘风格。

建议底模：anything4.5,SD1.5,或者final-prune等2.5D或者二次元动漫模型，出建筑等可以搭配realisticvisonV20等真实模型。

生成建议：人物的预处理器可选择softedge,或者linerart，试具体情况而定，提示词引导系数不需要太高3~6左右即可，采样器可自行尝试，controlnet模式为均衡时更贴近原图，controlnet优先则效果相对较好，但是会和原来的人物有区别，clip层为2,模型权重可看情况加大至1.5也可以。可搭配animeoutline线稿系列，具体各个权重可自行尝试

建议提示词:manga,monochrome,sketch,line,greyscale,simple background,

触发词：	monochrome greyscale

封面提示

masterpiece, best quality,.line,monochrome,greyscale,simple background, 1girl,long hair,traditional media,lineart,trees,grass,.a woman sitting on a chair with her legs crossed and smiling at the camera, with a white background，.1girl, solo, high_heels, realistic, dress, v_arms, standing, white_dress,.<lora:Lineart-v2.0:1>.
Negative prompt: lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, easynegative, negative_hand-neg, ng_deepnegative_v1_75t,photograph,shoot,Real photography,real world location,.
Steps: 30, Seed: 1430946586, Sampler: DPM++ 2S a Karras, CFG scale: 4