Lightweight and efficient open-source AI ID photo generation and matting tool.
Generate standard ID and layout photos with local matting and face alignment.
HivisionIDPhotos is an open-source Python tool built for automated ID photo creation, matting, and sizing. It suits professional photographers and developers looking to integrate passport and ID generation workflows into local or web applications.
The software combines background matting models like MODNet, BiRefNet, and RMBG with face detection (MTCNN, RetinaFace, or Face++) to crop, resize, and alter ID photo backgrounds. It includes a Gradio interface supporting custom HEX background colors, beauty filters, print layouts, and 300DPI JPEG output.
It suits photographers and studios needing an automated pipeline for bulk ID photo processing or custom print layouts. It does not suit non-technical users who require a ready-to-use commercial desktop application without handling code, python environments, or Docker containers.
Supports multiple offline background removal models including MODNet and BiRefNet.
Generates 6-inch, 5-inch, A4, 3R, and 4R photo layout sheets with crop lines.
Deployable via FastAPI or Docker with options for beast mode memory caching.
Customise dimensions in millimeters and select background colors via CSV configs or HEX input.
Free under its open source license. The only cost is running it on your own hardware or server infrastructure.
876 open remote AI-training roles, updated November 15, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.
These reviewed AI tools do the same job instantly — from our scored directory.
Yes, default models like MTCNN and MODNet run completely offline on your CPU without internet access.
You can modify the size_list_CN.csv file located in the demo assets folder to add or alter dimensions.
Yes, the BiRefNet model supports NVIDIA GPU acceleration if you install the corresponding ONNX Runtime GPU and CUDA drivers.
See Zekai first in Google