This commit is contained in:
NNNNAI
2021-07-02 20:37:26 +08:00
2 changed files with 17 additions and 0 deletions
+5
View File
@@ -13,8 +13,13 @@ Our paper can be downloaded from [[Arxiv]](https://arxiv.org/pdf/2106.06340v1.pd
<!-- [[Google Drive]](https://drive.google.com/file/d/1fcfWOGt1mkBo7F0gXVKitf8GJMAXQxZD/view?usp=sharing)
[[Baidu Drive ]](https://pan.baidu.com/s/1-TKFuycRNUKut8hn4IimvA) Password: ```ummt``` -->
## Attention
***This project is for technical and academic use only. Please do not apply it to illegal and unethical scenarios.***
## Top News <img width=8% src="./docs/img/new.gif"/>
**`2021-07-02`**: We have added a hyper parameter to allow users to choose whether to add the simswap logo as a watermark, please go to the section "About watermark of simswap logo" of [Inference for image or video face swapping](./docs/guidance/usage.md) for details.
**`2021-06-20`**: We release the scripts for arbitrary video and image processing, and a colab demo.
## Dependencies
+12
View File
@@ -40,6 +40,17 @@ python test_wholeimage_swapsingle.py --isTrain false --name people --Arc_path a
```
python test_wholeimage_swapmutil.py --isTrain false --name people --Arc_path arcface_model/arcface_checkpoint.tar --pic_a_path ./demo_file/Iron_man.jpg --pic_b_path ./demo_file/mutil_people.jpg --output_path ./output/
```
### About watermark of simswap logo
The above example command line is to add the simswap logo as the watermark by default. After our discussion, we have added a hyper parameter to control whether to remove watermark.
The usage of removing the watermark is to add an argument: "***--no_simswaplogo***" to the command line, take the command line of "Swap all faces within one image" as an example, the following command line can get the result without watermark:
```
python test_wholeimage_swapmutil.py --no_simswaplogo --isTrain false --name people --Arc_path arcface_model/arcface_checkpoint.tar --pic_a_path ./demo_file/Iron_man.jpg --pic_b_path ./demo_file/mutil_people.jpg --output_path ./output/
```
Difference between single face swapping and all face swapping are shown below.
<img src="../img/multi_face_comparison.png"/>
@@ -52,6 +63,7 @@ Difference between single face swapping and all face swapping are shown below.
| --video_path | Path of video with the source face to swap |
| --temp_path | Path to store intermediate files |
| --output_path | Path of directory to store the face swapping result |
| --no_simswaplogo |The hyper parameter to control whether to remove watermark |
### Note
We expect users to have GPU with at least 8G memory. For those who do not, we will provide Colab Notebook implementation in the future.