Export subject mask
Export a grayscale subject segmentation mask.
Export subject mask
Drop your files here
or choose files from your device
Jak używać Export subject mask
Export subject mask produces a grayscale segmentation mask for a photo: white where the subject is, black where the background is, and gray along soft or partial edges. It uses the BEN2 model in a browser worker after a one-time download. The mask is saved as an opaque PNG for use in other editing software.
- Choose a source file. If the tool accepts multiple files, arrange them in the order you want.
- Check the source format before running the operation.
- Run export subject mask, review the output, then use the available copy or download controls.
Funkcje narzędzia
Downloads a browser inference model on first run, then processes source locally in a cancellable Web Worker. Background removal uses BEN2; transcription uses Whisper tiny. Review recognition errors and image edges.
Limity i przetwarzanie
Image inputs: up to 32 megapixels, batches up to 10 images. Audio/video uploads: 50 MB; transcription: 120 seconds. Edited videos: 20 seconds, 4 fps and 640 pixels wide. Translation: English/Spanish, 30,000 characters; subtitles: 200 cues. Neural speech: 1,000 English characters. Model downloads and memory requirements vary by device.
Przykładowe dane
A useful tool makes everyday work easier. Review the results before sharing.
Często zadawane pytania
What is a subject mask used for?
A mask lets you apply the cutout in another program, for example as a layer mask in an image editor or a matte in compositing software, while the original photo stays untouched.
What do the gray areas in the mask mean?
Gray pixels come from partial transparency in the model's cutout. Lighter gray means more of that pixel belongs to the subject, which typically appears around hair, fur and blurred edges.
Can I export masks for several images at once?
This tool processes the first image you select. Run it once per photo, or use batch background removal if transparent cutouts of up to 10 images are enough for your workflow.
Where is my input processed?
Source files and text stay in this browser. The first run downloads public models from Hugging Face and local runtime assets from the site. Models may remain in the browser cache. No source upload to Vercel, Supabase or a conversion service is required.
What are the input limits?
Image inputs: up to 32 megapixels, batches up to 10 images. Audio/video uploads: 50 MB; transcription: 120 seconds. Edited videos: 20 seconds, 4 fps and 640 pixels wide. Translation: English/Spanish, 30,000 characters; subtitles: 200 cues. Neural speech: 1,000 English characters. Model downloads and memory requirements vary by device.