OpenSourceJoker/LivePortrait
3
0
Fork 0
mirror of https://github.com/KwaiVGI/LivePortrait.git synced 2024-12-23 05:02:38 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
1a11b2ffe2
LivePortrait/assets/docs/changelog/2024-07-10.md
Jianzhu Guo 3c1a866b6b
feat: add several features (#89) 
* feat: support template making, audio, etc, WIP

* chore: remove video2template.py

* feat: WIP

* feat: support auto cropping, template making, audio

* feat: ready for pr

* chore: format code

* chore: upload pkl

* doc: update readme

* doc: update readme

* doc: update readme

* doc: update readme

* doc: update readme

---------

Co-authored-by: zzzweakman <1819489045@qq.com>
2024-07-10 23:39:49 +08:00

1.8 KiB
Raw Blame History

2024/07/10

First, thank you all for your attention, support, sharing, and contributions to LivePortrait! ❤️ The popularity of LivePortrait has exceeded our expectations. If you encounter any issues or other problems and we do not respond promptly, please accept our apologies. We are still actively updating and improving this repository.

Updates

  • Audio and video concatenating: If the driving video contains audio, it will automatically be included in the generated video. Additionally, the generated video will maintain the same FPS as the driving video. Make sure ffmpeg-python package is installed, which has been added into the requirements.txt.

  • Driving video auto-cropping: Implemented automatic cropping for driving videos by tracking facial landmarks and calculating a global cropping box with a 1:1 aspect ratio. Alternatively, you can crop using video editing software or other tools to achieve a 1:1 ratio. Auto-cropping is not enbaled by default, you can specify it by --flag_crop_driving_video.

  • Template making: Added the ability to create templates to protect privacy. The template is a .pkl file that only contains the motions of the driving video. Theoretically, it is impossible to reconstruct the original face from the template. These templates can be used to generate videos without needing the original driving video. By default, the template will be generated and saved as a .pkl file with the same name as the driving video. Once generated, you can specify it using the -d or --driving_info option.

Others

  • If you encounter a black box problem, disable half-precision inference by using --no_flag_use_half_precision, see #62.