Change Log

September 8, 2026 · View on GitHub

Release history for the InsightFace Python Library. See the package README for installation and quick starts.

[2.0] - 2026-09-10

Add opt-in RGB liveness through FaceAnalysis(addons=["liveness"]), with normal / observe modes and a configurable live-score threshold (default 0.8).
Return per-face scores and input-rejection guidance. Normal mode retains detections while skipping recognition for faces that do not pass.
Download and verify the separate addon model under <root>/addons/liveness.onnx. See usage and result fields.

Add local video face detection/tracking with Gaussian blur or mosaic through the Python API, insightface-privateframe CLI, and Evaluation Studio GUI.
Add all, blur_only, and exempt policies, with a folder of reference photos for selecting people.
Export editable analysis JSON and render it again without another inference pass; provide analyze, process, and render workflows.
Add configurable analysis sampling (Fast mode, target 15 FPS by default), interpolation between scans, encoding/audio controls, and structured CLI status and progress.
Add the PrivateFrame feature and usage guide.

Add manifest-backed raccoon_s / raccoon_l model packages and make raccoon_s the default for new GUI configurations.
Add automatic CoreML/CUDA/CPU provider selection and persistent CoreML compilation caches; use reusable fixed-shape SCRFD sessions per resolution.
Set ORT_DISABLE_TELEMETRY=1 before importing ONNX Runtime, where supported.
Add the privateframe installation extra and include it in the gui extra.

Install onnxruntime by default for CPU and supported macOS CoreML systems. NVIDIA CUDA users must replace it with onnxruntime-gpu after installing or upgrading InsightFace; the two runtime distributions must not coexist.
Remove the PyPI package metadata license classifier field while keeping the README license guidance.
Move direct Pillow and scikit-learn requirements to the GUI extra, and matplotlib to the optional face3d extra.
Remove unused base dependencies on easydict and prettytable.

Add InsightFace Evaluation Studio, a cross-platform PySide6 desktop GUI for local face recognition, album grouping, enterprise evaluation/report export, and face swap trials.
Add GUI launch commands: insightface-gui, insightface-eval-studio, insightface-desktop, and python -m insightface.gui.

FaceAnalysis.prepare() now defaults ctx_id to 0 and uses Auto detection size, running SCRFD at both 128x128 and 640x640 before unified NMS.
Route detection models loaded by model_zoo.get_model() through SCRFD by default.
The optional face3d Cython/C++ extension is no longer built by default; use --with-face3d or INSIGHTFACE_WITH_FACE3D=1 to opt in.