# Replace image background

> Cut out a subject and place it on an uploaded background.

[Open tool](https://www.toolcabana.com/si/replace-background) · [රූප සහ නිර්මාණ](https://www.toolcabana.com/si/category/images-and-design)

Tool ID: replace-background. Requested language: si. Description language: en. Complete guide translation: no; untranslated sections use English.

## Supported tasks (en)

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.

## Steps (en)

1. Choose a source file. If the tool accepts multiple files, arrange them in the order you want.
2. Check the source format before running the operation.
3. Run replace image background, review the output, then use the available copy or download controls.

## Settings

No additional settings.

## Limitations (en)

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 input

```text
A useful tool makes everyday work easier. Review the results before sharing.
```

## Privacy and connections (en)

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.

## Questions (en)

### What does replace image background do?

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.

### 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.

## Related tools

- [Image watermark remover](https://www.toolcabana.com/si/remove-watermark)
- [Object eraser](https://www.toolcabana.com/si/remove-object)
- [Remove text from photo](https://www.toolcabana.com/si/remove-photo-text)
- [Remove photo date stamp](https://www.toolcabana.com/si/remove-date-stamp)