Stable Diffusion - Style Editor 和 Easy Prompt Selector 提示词插件配置

欢迎关注我的CSDN:https://spike.blog.csdn.net/

本文地址:https://spike.blog.csdn.net/article/details/132122450

Style Editor 插件:

bash 复制代码
cd extensions
git clone https://ghproxy.com/https://github.com/chrisgoringe/Styles-Editor

报错:

bash 复制代码
  File "extensions/Styles-Editor/scripts/main.py", line 164
    match command:
          ^
SyntaxError: invalid syntax

原因是 match 是 Python3.9.1 支持,与当前的环境不符合,需要修改源码,即:

  • extensions/Styles-Editor/scripts/main.py
bash 复制代码
  @classmethod
  def handle_outstanding_api_calls(cls):
    with cls.api_lock:
      for command, value in cls.api_calls_outstanding:
        if command == "delete":
        # match command:
          # case "delete":
          FileManager.remove_style(maybe_prefixed_style=value)
        elif command == "move":
          # case "move":
          FileManager.move_to_additional(maybe_prefixed_style=value[0], new_prefix=value[1])
          # case "duplicate":
        elif command == "duplicate":
          FileManager.duplicate_style(maybe_prefixed_style=value)
      cls.api_calls_outstanding = []
    return FileManager.get_current_styles()

修复Bug,重启UI,即可显示:

删除空行,Command + 右键 选中整行,再按 Delete,即可删除空行。

Easy Prompt Selector 插件,同时,再进行汉化:

cd extensions
git clone https://ghproxy.com/https://github.com/blue-pen5805/sdweb-easy-prompt-selector

汉化参考:

bash 复制代码
1、老用户,先更新升级,再下载我的汉化包。
2、新用户,先安装,安装地址:https://github.com/blue-pen5805/sdweb-easy-prompt-selector
3、升级或者安装完毕后,解压缩汉化包,覆盖掉原文件即可,路径:extensions\sdweb-easy-prompt-selector
4、新增汉服触发词界面,需结合汉服唐风、宋风、明风三个lora使用,汉服lora总下载地址:https://civitai.com/models/15365?modelVersionId=54777
当前版本,原版本20230613,汉化时间20230617,原插件只有几十个提示词,我增加到3000+。
欢迎知乎关注"路过银河",每日更新模型评测、下载,当然不关注也没关系。

重启 WebUI,即可以使用插件。效果如下:

测试:

1girl,black footwear,black hair,boots,curtains,dress,floral print,full body,handbag,lips,long hair,long sleeves,looking at viewer,polka dot legwear,shoes,smile,solo,standing,tile floor,tile wall,

a woman standing in front of a building wearing a gray dress and purple socks and a gray jacket with polka dots,Ayami Kojima,long black hair,a hologram,private press,

best quality,masterpiece,ultra high res,(photorealistic:1.4),

Negative prompt: (ng_deepnegative_v1_75t,badhandv4,bad_prompt_version2-neg,EasyNegative:0.9),(worst quality, low quality:1.3),(depth of field, blurry:1.2),(greyscale, monochrome:1.1),croped,lowres,text,jpeg artifacts,(logo,signature,watermark,username,artist name,title:1.3),

Steps: 30, Sampler: DDIM, CFG scale: 7, Seed: 2800574805, Size: 512x768, Model hash: 4b5bc79af1, Model: 墨幽人造人_v1030, Denoising strength: 0.3, Clip skip: 2, ADetailer model: face_yolov8n.pt, ADetailer confidence: 0.3, ADetailer dilate/erode: 4, ADetailer mask blur: 4, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer version: 23.7.6, Hires upscale: 2, Hires steps: 10, Hires upscaler: 4x-UltraSharp, TI hashes: "ng_deepnegative_v1_75t: 54e7e4826d53, badhandv4: 5e40d722fc3d, bad_prompt_version2-neg: 6f35e7dd816a, EasyNegative: 66a7279a88dd", Version: v1.5.1

更新墨幽模型:

bash 复制代码
wget https://liblibai-online.liblibai.com/web/model/4b5bc79af15151d058d12d5e61c68ffc5b2b7f47dbdee4523b3c54a9bad1efda.safetensors?attname=%E5%A2%A8%E5%B9%BD%E4%BA%BA%E9%80%A0%E4%BA%BA_v1030.safetensors -O 墨幽人造人_v1030.safetensors

测试效果,墨幽1030、+CandyLand、+RealGirlFace,即:

Lora:

相关推荐
9命怪猫4 小时前
AI大模型-提示工程学习笔记13—自动提示工程师 (Automatic Prompt Engineer)
人工智能·ai·大模型·prompt
风雨中的小七16 小时前
解密prompt系列49. 回顾R1之前的思维链发展路线
prompt
农夫山泉2号1 天前
【个人开源】——从零开始在高通手机上部署sd(二)
stable diffusion·智能手机·sd·高通·qnn
后知后觉1 天前
windows 安装 stable diffusion
stable diffusion
农夫山泉2号2 天前
【个人开源】——从零开始在高通手机上部署sd(一)
stable diffusion·智能手机·sd·高通·qnn
workflower2 天前
Prompt Engineering的重要性
大数据·人工智能·设计模式·prompt·软件工程·需求分析·ai编程
forestsea2 天前
DeepSeek 提示词:定义、作用、分类与设计原则
人工智能·prompt·deepseek
AIGC安琪3 天前
【Stable Diffusion】SD迎来动画革命,AnimateDiff快速出图
人工智能·网络协议·tcp/ip·stable diffusion·aigc
小白顶呱呱4 天前
图解【提示工程 VS 微调 VS RAG、全量微调 VS LoRA微调、TopK VS TopP】截图笔记
笔记·大模型·prompt·rag·大模型微调
Allen-Steven5 天前
《Stable Diffusion绘画完全指南:从入门到精通的Prompt设计艺术》-配套代码示例
人工智能·pytorch·深度学习·stable diffusion·prompt·checkpoint