SDXL:Improved semantic understanding, able to generate more interesting content, everyone can try more.Resolution sampling, etc. is recommended to be used according to the check XL usedSometimes if the content is not ideal, besides changing the prompt words, It's best to try different check modelsI often use Dreamshaper XL/Jumpernaut XL/LEOSA and M HelloWorld XL for large models.I haven't tested any other check, everyone can try moreLora weight recommendation 0.5-0.7However, there is no need to give up on 1.5. Currently, 1.5 has more ecology, and some images still require 1.5.1.5 model:Direct input Simple prompts for store categories can generate street shop facades, such as: coffee shop, flower shop, bookstore, etcIf not generated, you can add words like storefront, sign, entrance, etc., or increase LORA weightFor example: coffee shop entrance, coffee shop sign, coffee shop front. If it appears indoors and you want to be outdoors, you can add a hint word like "street" to control itThe weight is recommended 0.6-0.9, the higher the weight, the more obvious the store, the lower the weight, the better the generalization of the prompt wordcheckpoint recommends the realistic classCan have interesting effects with many architectural LORAsRecommended size: 768×512, because I trained set uniform this size can also try others

storefront

SDXL:The usage method is similar to before, improving semantic understanding and generating more interesting content. Everyone can try it more.Sometimes if the content is not ideal, besides changing the prompt words, it's better to try a larger model directly.I often use Dreamshaper XL/Juggernaut XL/LEOSA and M HelloWorld XL for checkYou can also try other check

Files with SHA256: bb5de39cf6f8ff423fea461e60ba5dbf4a339e0a436d119d54101f0226ab842c