SimSwap
SimSwap copied to clipboard
An arbitrary face-swapping framework on images and videos with one single trained model!
------------ Options ------------- Arc_path: models/BEST_checkpoint.tar aspect_ratio: 1.0 batchSize: 8 checkpoints_dir: ./checkpoints cluster_path: features_clustered_010.npy crop_size: 224 data_type: 32 dataroot: ./datasets/cityscapes/ display_winsize: 512 engine: None export_onnx: None f: /root/.local/share/jupyter/runtime/kernel-c658d45c-eca0-4802-ae1e-33ceab63846b.json feat_num: 3 fineSize:...
Hi, for 512 multispecific video the eyes and mouth won't move, unlike 224 multispecific video. In some cases, the 512 verion looks cock-eyed, while the 224 version doesn't. Can someone...
Traceback (most recent call last): File "test_video_swapmulti.py", line 65, in img_a_align_crop, _ = app.get(img_a_whole,crop_size) TypeError: 'NoneType' object is not iterable
Hello! There is no tutorial to install it on the pc? Sorry my english. I bought an nvidia and wanted to try. Thank you
Hello everyone, SimSwap in Google colab reaches this deadline in the last cell and stops in the attributes of the error writes AttributeError: 'SGD' object has no attribute 'defaults' What...
full message: RuntimeError: CUDA out of memory. Tried to allocate 2.00 GiB (GPU 0; 6.00 GiB total capacity; 3.25 GiB already allocated; 0 bytes free; 4.51 GiB reserved in total...
Thank you for your works. When I followed the guidence of the preparation and tried to install the insightface, I met some problems. It turned out that I can't install...
I want to swap the lip features at the same time as the face swap, is it possible?
I am training with a custom dataset and I would like to know two questions: 1. Why my output is different from the official output, the official output is preceded...