/sber-swap

Primary LanguagePython

[Хабр] [Colab]

SberSwap

Results

Video Swap

Installation

  1. Clone this repository
git clone https://github.com/sberbank-ai/sber-swap.git
cd sber-swap
git submodule init
git submodule update
  1. Install dependent packages
pip install -r requirements.txt

If it is not possible to install onnxruntime-gpu, try onnxruntime instead

  1. Download weights
sh download_models.sh

Usage

  1. Colab Demo google colab logo or you can use jupyter notebook SberSwapInference.ipynb locally
  2. Face Swap On Video

Swap to one specific person in the video. You must set face from the target video (for example, crop from any frame).

python inference.py --source_paths {PATH_TO_IMAGE} --target_faces_paths {PATH_TO_IMAGE} --target_video {PATH_TO_VIDEO}

Swap to many person in the video. You must set multiple faces for source and the corresponding multiple faces from the target video.

python inference.py --source_paths {PATH_TO_IMAGE PATH_TO_IMAGE ...} --target_faces_paths {PATH_TO_IMAGE PATH_TO_IMAGE ...} --target_video {PATH_TO_VIDEO}
  1. Face Swap On Image

You may set the target face, and then source will be swapped on this person, or you may skip this parameter, and then source will be swapped on any person in the image.

python inference.py --target_path {PATH_TO_IMAGE} --image_to_image True

Training

We also provide the training code for face swap model as follows:

  1. Download VGGFace2 Dataset.
  2. Crop and align faces with out detection model.
python preprocess_vgg.py --path_to_dataset {PATH_TO_DATASET} --save_path {SAVE_PATH}
  1. Start training.
python train.py --run_name {YOUR_RUN_NAME}

We provide a lot of different options for the training. More info about each option you can find in train.py file. If you would like to use wandb logging of the experiments, you should login to wandb first --wandb login.

Tips:

  1. For first epochs we suggest not to use eye detection loss and scheduler if you train from scratch.
  2. In case of finetuning model you can variate losses coefficients to make result look more like source identity, or vice versa, save features and attributes of target face.
  3. You can change backbone for attribute encoder and num_blocks of AAD ResBlk using parameters --backbone and --num_blocks.
  4. For finetuning model you can use our pretrain weights for generator and discriminator that are in folder weights. We provide weights for models with unet backbone and 1-3 blocks in AAD ResBlk. The main model is model with 2 blocks in AAD ResBlk.