Batch background removal
Remove backgrounds from a batch and download a ZIP.
Batch background removal
Drop your files here
or choose files from your device
How to use Batch background removal
Batch background removal removes the background from up to 10 images in one run and downloads them as a ZIP of transparent PNG files. Each image is processed in turn by the BEN2 segmentation model, which downloads on first use and runs in a browser worker. Files are numbered by position, such as 1-background.png.
- 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 batch background removal, review the output, then use the available copy or download controls.
What this tool supports
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.
Limits and processing
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.
Example source
A useful tool makes everyday work easier. Review the results before sharing.
Frequently asked questions
How many images can I remove backgrounds from at once?
Up to 10 images per run. Each is segmented separately and the progress bar updates after every file. For a larger set of photos, split them into several batches.
What is inside the batch background ZIP?
The archive backgrounds.zip contains one PNG per input, named 1-background.png, 2-background.png and so on in the order you selected the files. Each PNG has a transparent background around the subject.
Does batch background removal keep the original file names?
No. Outputs are numbered by position rather than named after the source files, so keep your selection order in mind when matching results to the originals.
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.