匿名用户2024年07月31日
12阅读
开发技术Pytorch
所属分类ai、text-to-image、lora
开源地址https://modelscope.cn/models/sd_lora/G.E.M
授权协议Apache License 2.0

作品详情

It's confusing that after I set training images larger to 640704 and remained other settings like before, I thought I would get better results, but the outputs after hirex.fix(448640-->716*1024, denoising 0.45, latent) look not like her, sometimes on the contrary.

By the way, I happened to find that ESRGAN4x may works better than Latent or Latent (bicubic antialiased) while keeps the same high speed of these two? Could u share me with your hires.fix settings in comment? Thanks!

Weighted around 0.8 as ever.

~~

Be kind to these lovely.

Legal & Risk

It is prohibited to use this model for commercial purposes and any scenarios of illegal acts and purposes.

声明:本文仅代表作者观点,不代表本站立场。如果侵犯到您的合法权益,请联系我们删除侵权资源!如果遇到资源链接失效,请您通过评论或工单的方式通知管理员。未经允许,不得转载,本站所有资源文章禁止商业使用运营!
下载安装【程序员客栈】APP
实时对接需求、及时收发消息、丰富的开放项目需求、随时随地查看项目状态

评论