pyfeat-generator 0.1.1

Conditional facial-expression editing & face resynthesis runtime (FaceEditor) on top of py-feat 2.0

pyfeat-generator

Runtime for conditional facial-expression editing and face resynthesis — the FaceEditor / LiveEditSession API used by pyfeat-live, built on py-feat 2.0. Model weights are fetched from the py-feat HuggingFace org (py-feat/pyfeat-generator*).

MIT licensed.

Install

pip install pyfeat-generator

Pulls py-feat >= 2.0.3 and torch >= 2.12. Model weights download from the public py-feat HuggingFace org on first use (cached thereafter).

Device support

FaceEditor / LiveEditSession run on NVIDIA CUDA, Apple Silicon (MPS), and CPU. The rasterizer auto-selects a backend for the device; all three are parity-gated to byte-identical output, so results never depend on the machine.

Device	Backend	Notes
NVIDIA CUDA	nvdiffrast	Fastest. Optional — pip install nvdiffrast separately (needs the CUDA toolkit). Falls back to torch if absent.
Apple Silicon (MPS)	metal	Fused torch.mps.compile_shader kernel. Requires torch ≥ 2.12 (this package's floor); older torch falls back to torch.
CPU / other	torch	Pure-PyTorch, device-agnostic. Always works; slowest.

nvdiffrast is never imported off CUDA (the auto-selector guards it behind torch.cuda.is_available()), so it is not a dependency and is not needed on a Mac. Force a backend with the env var AU_RASTER_BACKEND=nvdiffrast|metal|torch.