hififace
hififace copied to clipboard
maum-ai
Unofficial PyTorch Implementation for HifiFace (https://arxiv.org/abs/2106.09965)
Instruction very confusing with this text which is not a cmd text and not a valid dockerfile. Code itself broken and contain lot of errors. "attempted relative import beyond top-level...
will it train a 512 model? 256 is very bad .
First, thanks for taking the time to implement this faceswapping model - seems like it has a lot of potential! That said, I noticed a few issues while setting it...
Thank you for your efforts, but can you improve the model to produce better results?
Dear sir, I got errors when building the docker with command `docker build -t hififace:latent .`: **Sending build context to Docker daemon 122.9MB Step 1/16 : ARG BASE_IMAGE=pytorch/pytorch:1.7.1-cuda11.0-cudnn8-devel Step 2/16...
Hi, thank you for sharing the code, and I have a question about your implementation. I found that the both of the [m_r](https://github.com/mindslab-ai/hififace/blob/c92db89c7bd0e4d1518f872827fdb69a98f16060/model/hififace.py#L154) and [m_low](https://github.com/mindslab-ai/hififace/blob/c92db89c7bd0e4d1518f872827fdb69a98f16060/model/hififace.py#L169) are generated by tanh function...
would be awesome to test it out on Google Colab
Thanks for you great work to reimplement hififace! I find that you use the Deep3dFaceRecon model straightly in size (256, 256). But the offical code of Deep3dFaceRecon is (224, 224)....
Hi, thx for sharing your codes, great works! I have serval questions about the implementatation. 1. according to the issue from the official hififace github repo, both masks are activated...
Meeting problem: RuntimeError: [enforce fail at inline_container.cc:145] . PytorchStreamReader failed reading zip archive: failed finding central directory I just started using torch version 1.10, ms1mv3_arcface_r100_fp16_backbone has this problem, and then...
