SimSwap
SimSwap copied to clipboard
neuralchen
problem in simswap inference
@neuralchen @R3PO97 @luoxyhappy @bfirsh yes the above .zip file works , thanks alot, but when i run this code as per steps mention in colab file, then the resulting generated video has blurr faces like an image below i have attached ??? why??? https://colab.research.google.com/github/neuralchen/SimSwap/blob/main/SimSwap%20colab.ipynb#scrollTo=wwJOwR9LNKRz
when i run: !python test_one_image.py --name people --Arc_path arcface_model/arcface_checkpoint.tar --pic_a_path crop_224/6.jpg --pic_b_path crop_224/ds.jpg --output_path output/
it generates warnings also: -------------- End ----------------
/content/SimSwap/models/base_model.py:70: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. pretrained_dict = torch.load(save_path) Pretrained network G has fewer layers; The following are not initialized: ['down0', 'first_layer', 'last_layer', 'up0']
and wrong image
you need to set crop_size to 224, run: !python test_one_image.py --name people --Arc_path arcface_model/arcface_checkpoint.tar --pic_a_path crop_224/6.jpg --pic_b_path crop_224/ds.jpg --output_path output/ --crop_size 224
you need to set crop_size to 224, run: !python test_one_image.py --name people --Arc_path arcface_model/arcface_checkpoint.tar --pic_a_path crop_224/6.jpg --pic_b_path crop_224/ds.jpg --output_path output/ --crop_size 224你需要将 crop_size 设置为 224，运行： ！python test_one_image.py --name people --Arc_path arcface_model/arcface_checkpoint.tar --pic_a_path crop_224/6.jpg --pic_b_path crop_224/ds.jpg --output_path output/ --crop_size 224
Thank you!
still getting blurred faces. I am wondering do we need to align the face as in FFHQ before seeding our own images to the inference script
