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
效果不错,就是太慢了,非常慢 #60
Comments
If you don't think AniPortrait is good, you build it; |
@dyingChinese Classic quotes, if they're not good enough, go ahead and optimize them |
给你几个优化方向:1)Unet的训练方式告诉你了,你可以考虑训练一个LCM-LoRA,25步降噪到4~6步降噪可以优化70%以上的时间 2)参考目前蒸馏的方法,大概能减少30%的时间 3)考虑对模型进行量化处理,可以优化30%~40%的时间。 |
很抱歉,这是一个初步开源的方案,我们会根据社区的建议逐步优化,感谢关注! |
期待作者优化
The text was updated successfully, but these errors were encountered: