2.5.0
版本发布时间: 2024-04-10 16:47:42
facefusion/facefusion最新发布版本:2.6.1(2024-06-17 02:59:39)
- Introduce the frame colorizer using the
ddcoloranddeoldifymodel - Extract voice from the audio to enhance the lip-syncer quality
- Experimental 5 to 68 face landmark estimation
- Add the face enhancer
gpen_bfr_1024andgpen_bfr_2048model - Add the frame enhancer
real_esrgan_x2andreal_hatgan_x4model - Introduce
--force-downloadto download every model at once - Migrate the documentation and installer from venv to conda
- Full compatibility with CUDA 12 due
inswapper_128_fp16model fix - Fix fps boosting and lowering during video merging
- Fix crashes when using
--skip-downloadwhen models are absent - Fix
h264_nvencandhevc_nvencpresets mapping