https://civitai.com/models/105182/arlecchino-or-genshin-impact-or-lora-or-pop-waifu-series
文件名arle.safetensors
<lora:arle:1>
1girl, solo, white hair, black hair, multicolored hair, black eyes, x-shaped pupils, <lora:arle:1> , white arle_suit , face focusedNegative prompt: (easynegative:1.2), (ng_deepnegative_v1_75t), (worst quality:2.0), (low quality:2.0), text, error, blurry, jpeg artifacts, normal quality, signature, low quality lowres, very ugly, fat, (weird fingers), inaccurat ...
这一课主要将安装扩展与插件安装视频：
https://www.bilibili.com/video/BV1hz4y1a76M/?spm_id_from=333.788&vd_source=7aa5bcb5a7c34becbf26b1d712279ba8这节主要是安装扩展和插件。
扩展文件夹保存在根目录下\extensions中
Concept_Scenery_scene_V4https://civitai.com/models/34132/conceptsceneryscenev4
文件名：sceneConcept_s_v2.safetensors
基本型号可以是 Counterfeit-V2.5 或其他相关样式型号
可与其他 LORA 结合使用
CoMix BGXL | Anime Scenery Pony Lorahttps://civitai.com/models/319451/comix-bgxl-or-anime-scenery-pony-lora
这些 lora 是在 CoMix Wave 电影、Your Name、Weathering With You 和 Suzume 的大约 160 张图像上训练的。我的目标是捕捉电影中的背景艺术风格。我没有在数据中包括电影中的任何角色（或任何人）。
文件名：MeMaXL_V3.safetensors
Prompt: score_9,score_8_up,score_7_up,score_6_up,source_anime,anime screencap,& ...
https://civitai.com/models/88001/miyazaki-hayao
文件名Miyazaki.safetensors
< lora: miyazaki: 0.8 ~ 0.9 >
masterpiece, best quality, 1girl, shirt, upper body , smile, street，<lora:Miyazaki:0.85>,miyazaki hayao ,
尝试只生成风景
宫崎骏漫画场景https://www.liblib.art/modelinfo/49183f3f53bb4443a9afd58e54fc3a8d
参数推荐：
底模建议：动漫ReVAnimated
采样方法：DPM++ 2M Karras
迭代步数：展示图用的是30（步数越高细节越多）
VAE：vae-ft-mse-840000-ema-pruned
权重：0.7-1之间表现都不错
画面尺寸：推荐512*768
（建议开分辨率修复，迭代步数30，放大算法：R-ESRGAN 4x+ Anime6B，重绘幅度0.2-0.3）
https://civitai.com/models/124806/sdxlstickers
在同一个画面生成多个相似形象。触发词prompt：（biaoqing,stickers,<lora:stickers_0.8+stickers2_0.8:0.8>
parameters stickers,biaoqing,stickers of 20yo girl,white background,simple background,emotional,illustration,best quality,highly detailed,masterpiece,an extremely delicate and beautiful,extremely detailed,8k wallpaper,Amazing,finely detail,official art,<lora:stickers_0.8+stickers2_0.8:0.8>,Negative prompt: lowres,bad anatomy,bad hands,text,error,missing fin ...
https://civitai.com/models/53295/march-7th-or-honkai-star-rail
文件名：March 7th.safetensors
使用0.6-0.8之间的LoRA权重
march 7th (honkai: star rail)
march 7th
触发词：girl, solo, pink hair, bangs, looking at viewer, smile, long sleeves, white shirt, open mouth, blue eyes, blue jacket, skirt, breasts
具体如何需要自己调试
例图参考
1girl holding a ((beer)), march 7th, short hair, multicolored eyes, pink hair, bangs, blue_eyes, long locks, ribbon errings, CG, software anime, slight smile <lora:March 7th:0.9>
https://civitai.com/models/64441/honkai-star-rail-kafka-lora
文件名HSR Kafka.safetensors
触发：<lora:Kafka 5-000009:0.7>,原装：stellaron hunters outfit星核猎手
hsr_kafka, Photorealistic, Realistic, 1girl, eyewear on head, standing, cafe, maid apron, maid, plate pressed to chest, large breasts <lora:Kafka 5-000009:0.7>Negative prompt: (worst quality, low quality:1.4), monochrome, zombie, (interlocked fingers), bad anatomySteps: 40, ENSD: 31337, Size: 512x512, Seed: 2982487574, Model: models_Meina ...
https://civitai.com/models/58390/detail-tweaker-lora-lora
Detail Tweaker LoRA文件名：add_detail.safetensors
这是一个用于增强/减少细节的 LoRA，同时保持整体风格/特征;
它适用于各种基本模型（包括动漫和逼真的模型）/风格 LoRA/角色 LoRA 等。
施加自己的重量;这个 LoRA 可用于任何重量上升/下降至 2/-2！
使用：<lora:add_detail:1>
注意：使用负权重来减少细节！
图例：
https://civitai.com/models/366138/aventurine-honkai-star-rail
文件名Avent-10.safetensors
触发词aventhsr
aventhsr, cd cover, blue shirt, long sleeves, white necktie, looking at viewer, city, tower, building, night, outdoors, blurry backgroundNegative prompt: (worst quality, low quality, large head, extra digits:1.4), EasyNegativeV2, ng_deepnegative_v1_75tSteps: 20, Seed: -1, Sampler: DPM++ 2M Karras, CFG scale: 6
