-
Notifications
You must be signed in to change notification settings - Fork 864
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
FACT版本疑似内存泄露 #589
Comments
似乎FACT版本并不比原版降低配置需求,甚至还更高了。 |
内存泄漏源于diffusers中pipeline在CPU和GPU切换时的内存碎片,FACT版本由于包含inpainting和text-to-image的多个pipeline,为节省显存故而使用上述切换,该问题须使用jemalloc解决。 |
想问一下,Windows下要怎么安装jemalloc? |
即使是用APC inject注入jemalloc.dll也节省不了内存。 |
翻了一下源码,启动时没必要把两个sdxl模型都加载上吧。 |
感谢您的建议。针对加载多个sd模型的问题,该设计可以避免后续用户切换模型时重新加载的时间,但的确导致内存和初始启动时间的增加,如有需要,可以添加用户手动切换并加载模型的版本。针对sd webui预加载模型复用的问题,当前版本的facechain由于涉及到对sd模型inference流程的修改,故无法直接支持sd webui模型的复用,须重构webui中推理步骤的底层代码,如有兴趣,可以考虑加入facechain开发群,召集开发者合作开发该功能。 |
搭配sd webui运行,仅使用sd1.5 fp16模型,占用内存高达50.5GB,远高于说明文档上的30G->20GB和同类产品Easyphoto 28GB
而且Windows下要怎么用jemalloc?
The text was updated successfully, but these errors were encountered: