SimSwapHD
SimSwapHD copied to clipboard
Reimplement of SimSwap training code
The "Weak Feature Matching Loss" is different (both here and in the original repo), from the one mentioned in the paper (the features **from all the layers** are used, instead...
20211130 后来我们团队有换脸相关需求了,做了很多改进与优化,不过应该没法分享出来; 没有代码没关系,能就说说做了哪些改进和优化吗?谢谢。

Hello,if using fp16(apex/torch.cuda.amp),loss=Nan after several iters,any solutions?
I'm a beginner who's dissatisfied with the official SimSwap_512 beta model and trying to finetune the official people model for better performance at `-image_size 512 --display_winsize 512`. When I'm starting...
now ,i dont still start run , so someone can give me some test images, i can see the results of this train code
Hello, could you please provide a Colab notebook for the training? Or if anyone has done it could you please share it? Very much thanks.
What would we need to change to train the nFM model in the paper?
Hello im very intrested in training for simswap, any chance theres a video on this or a better walkthru on how to get the environment set up and useage of...