FaceFusion 3.6 Ships AI Age Transformation and Sharper Background Removal
FaceFusion ships versions 3.6.0 and 3.6.1, adding new age-modification and background-removal models with a patch for antivirus certificate conflicts
PRO- 3.6.0 released: FaceFusion ships the
franage-modifier model and two new high-res background remover models (corridor_key_1024,corridor_key_2048). - 3.6.1 patch: Fixes SSL certificate failures caused by Norton and Avast antivirus on Windows.
- New CLI arg:
--background-remover-despill-colorcontrols color bleeding at background edges, fixing a common artifact. - Conda revamp: Environment now auto-configures
PATHandLD_LIBRARY_PATHon startup, reducing GPU setup friction. - Free and local: Runs entirely on your hardware with no data upload; open-source on GitHub with 29k stars.
- One-click installers available for Windows and macOS via facefusion.io for users who want to skip the terminal setup.
FaceFusion, the open-source face manipulation platform with nearly 29k GitHub stars, has shipped two back-to-back releases: 3.6.0, which adds new AI models for age modification and background removal, and a quick-follow 3.6.1 patch that fixes a certificate issue caused by popular antivirus software.
The project has been on a steady release cadence, and the 3.6.x series continues that pattern: targeted model additions, environment improvements, and a handful of quality-of-life fixes. Nothing here rewrites the architecture (that happened in 3.0 and 3.5), but the new models are practically useful and worth knowing about.
What landed in 3.6.0
The release adds the fran model to the age modifier, and introduces corridor_key_1024 and corridor_key_2048 models to the background remover.
There is also a conda environment revamp and a new CLI argument for background edge control.
Breaking that down by processor:
- Age modifier ,
franmodel: Thefranmodel provides more natural-looking age transformation than earlier options. It can be used to apply aging or de-aging effects on top of a face swap, or as a standalone processor on any target footage. It is particularly effective at preserving facial identity through the age transformation, which earlier models struggled with. - Background remover ,
This story is for Pro members
You've reached the end of the free preview. Upgrade to AlphaSignal Pro to read the full article - and everything else behind the paywall.
Comments
