Flux的人物高清Lora模型5200步，1024分辨率，权重0.8-1，建议euler+betaflux-fp8-jav-shanshou-v01.5.safetensors 620M此版本比V01版本，精度128的1.2G版本可控性略低，光影和还原度略低，有条件的请使用V01版本。支持我，将会有更多更好的Lora炼制出来，感谢！Support me, there will be more and better Lora refining, thank you!My Patreon Site<a target="_blank" rel="ugc" href="https://www.patreon.com/c/Fairytale2399">https://www.patreon.com/c/Fairytale2399</a>如需定制Lora，可在我的Pateon页面上留言。If you need to customize Lora, you can leave a message on my Pateon page.This version has slightly lower controllability, lighting, and restoration than the V01 version with an accuracy of 128 and a 1.2G version. If possible, please use the V01 version.Flux's high-definition Lora model of charactersThis Lora model has a size of 1.2G and no trigger words. It is recommended to have weights ranging from 0.8 to 1声明： 本模型内容仅为知识分享与学术交流目的，模型的使用均基于合法合规前提展开，禁止用于任何违反所在国家/地区法律法规的用途。Disclaimer: The content of this model is only for the purpose of knowledge sharing and academic exchange. The use of the model is based on legal and compliant premises, and is prohibited from any use that violates the laws and regulations of the country/region where it is located.

shanshou

Can be used without triggering words, it is recommended to add Asian faces for better controllability

Files with SHA256: afbb0ce8548143d45f7bfccae1819051a5f4546b9308cf91fec4af17dccf6d58