欢迎大家使用本模型。如果你喜欢我的工作，欢迎在ko-fi上为我[** 买杯咖啡](https://ko- fi.com/mugglewizard) ☕**
** Everyone is welcome to use th models! If you like my work, feel free to buy me a coffee on ko-fi ☕.**
如您有模型定制或其他合作、咨询需求，请联系Wechat: pomelonioi。请简单注明来意，时间宝贵不闲聊哈，谢谢理解！
If you have any model customization or other collaboration and consultation needs, please contact Wechat: pomelonioi . Kindly provide a brief description of your inquiry, as there's limited time and no time for casual chats. Thank you!
为了更好地让新司机上路，作为老司机的Muggle在鹅群（891417811）放了自制抽卡机（wildcards），包含日常穿搭、职业制服、搞怪戏服、节日礼服等数百套风格；
此外，如果你会Openpose，我还准备了300个用于控制人物姿势的Controlnet骨架图（站姿、坐姿、躺姿）方便又实用；主流插件也都整理好了，等你来取。
NSFW请加TG群https://t.me/+bm9GZdmvf3dmMWM9
NSFW please add TG group https://t.me/+bm9GZdmvf3dmMWM9
使用小贴士：
（1）Lora触发词为fittingroom，建议权重0.8，权重过低会像普通房间而非试衣间
（2）如果叠加面部lora发现效果不好，请使用adetailer插件进行面部修复：勾选enable，模型选择face，Adetailer
prompt中
（3）如果手指和手机控制不稳定，可以把喜欢的例图放入controlnet插件中，预处理器选择openpose- full，模型选择openpose【Q群里为大家准备了多种openpose例图，可以来领取】
Usage Tips:
(1) The trigger word for Lora is "fittingroom." It is recommended to set the weight to 0.8; if the weight is too low, it may resemble a regular room rather than a fitting room.
(2) If facial synthesis with Lora is unsatisfactory, you can use the adetailer plugin for facial touch-ups: enable it and select the "face" model. In the Adetailer prompt, use the format <lora:character:weight > with a suggested weight of 0.75 or higher. If the likeness is still insufficient, increase the weight of the inpaint redrawing factor (default is 0.4). If facial features are good but the colors are too intense, reduce the inpaint redrawing factor.
(3) If fingers and phone controls are unstable, you can use the controlnet plugin and input your preferred reference images. Choose the "openpose-full" preprocessor and the "openpose" model. Various openpose reference images are available in the Q group for you to collect.
评论