How it works
Complete the job in three clear steps
- Choose a JPG, PNG, WebP, or BMP image from this device.
- Run the lightweight U2-Net foreground model locally in your browser.
- Review the edges and download the generated PNG.
Private on-device image AI
Image Foreground Mask Generator
Generate a grayscale U2-Net foreground mask for compositing, editing, and segmentation review.
Free to use Your image and generated result stay in this browser. Lucaden serves the reusable AI model, but never receives the selected image.
Loading tool workspace…
Important
Check the result before relying on it
Keep an untouched copy of important source files. Browser processing depends on available device memory, and you should inspect every downloaded result before deleting the original.
Practical details
What this Lucaden tool does
Generate a grayscale U2-Net foreground mask for compositing, editing, and segmentation review.
White represents predicted foreground and black represents background. Gray edge pixels are partial confidence, not a manually verified selection.
The lightweight general-object model is self-hosted and cached by the browser. Its first run downloads roughly 4.6 MB; later runs can reuse the local cache.
Included capabilities
- Grayscale alpha mask
- General-object segmentation
- Edge post-processing
- Full-resolution PNG output
Useful for
- Build layer masks
- Review segmentation edges
- Prepare image composites
- Create editing mattes
Questions
About this tool
Does Lucaden upload my image?
No. The browser downloads Lucaden's self-hosted U2-Net model, then runs inference against the image locally with ONNX Runtime Web.
What should I verify?
White represents predicted foreground and black represents background. Gray edge pixels are partial confidence, not a manually verified selection.
Open-source foundations
Built transparently
Lucaden documents its standards sources, architectural references, and permissive runtime dependencies while keeping this workspace consistent with the Lucaden interface.