Deni.AI Labs100% in-browser · no uploads
LIVEBackground Remover · ~26 MB Image to Text (OCR) · ~10 MB Speech to Text · ~40 MB Object Detector · ~170 MB AI Image Describer · ~250 MB Text Summarizer · ~300 MB Sentiment Analyzer · ~70 MB Text to Speech · 0 MB
AI Labs › AI Tools › Background Remover

Background Remover

Cut the subject out of a photo and save it as a transparent PNG, processed entirely on your own device.

VisionModel MODNetDownload ~26 MBSpeed 1–5 sPrivacy stays on your device
Drop, paste or click to choose an image
Ready. The model downloads the first time you run it (~26 MB).

Removing a background by hand with selection tools can take a long time, especially around hair or soft edges. This tool does it automatically: choose a photo, and a segmentation model separates the main subject from everything behind it, leaving you with a PNG file whose background is transparent.

Your photo is handled inside the browser and never uploaded. That matters for portraits, family pictures and unreleased product shots. The model behind it is released under the permissive Apache 2.0 license.

How to use it

  1. Select or drag in a photo with a clear main subject, such as a person, pet or product.
  2. On first use, the model downloads, about 26 MB, and is then cached by your browser.
  3. Click remove background and compare the original with the cut-out preview.
  4. Download the result as a transparent PNG and place it on any new background in your editor.

How it works

The tool runs MODNet (Xenova/modnet) through Transformers.js. MODNet is a matting network originally designed for portraits: for every pixel in a resized copy of your image it estimates how much that pixel belongs to the foreground, from fully opaque to fully transparent. That estimate, called an alpha matte, is scaled back to the original size and applied as the transparency channel of the output image. Because the matte has soft values rather than a hard cut, edges such as hair fade out more naturally than a simple outline would. MODNet is published under the Apache 2.0 license.

Good for

Limitations

FAQ

Can I use the cut-outs commercially?

MODNet is released under the Apache 2.0 license, which allows commercial use. You are still responsible for having the rights to the photo itself, especially pictures of other people.

Why is my download a PNG?

PNG supports transparency. JPEG does not, so a JPEG would fill the removed area with a solid colour.

Is the photo uploaded?

No. The image and the mask are processed and combined locally in your browser.

More tools

1

Image to Text (OCR)

Turn screenshots, scanned pages and photos of printed text into editable text without sending the image anywhere.

VisionModel Tesseract (English and more)Download ~10 MBIn Screenshot, scan, photoOut Plain textSpeed 2–10 s
2

Object Detector

Find common objects in a photo and draw labeled boxes around them, using a detection model that runs locally.

VisionModel DETR ResNet-50Download ~170 MBIn JPG / PNG / WebPOut Labeled boxes, countsSpeed 3–10 s
3

AI Image Describer

Get a short, plain-English sentence describing what appears in a photo, generated entirely on your own device.

VisionModel ViT-GPT2 captioningDownload ~250 MBIn JPG / PNG / WebPOut One-sentence captionSpeed 2–6 s
4

Speech to Text

Transcribe English speech from an audio file or your microphone using a Whisper model that runs on your own device.

AudioModel Whisper tiny.enDownload ~40 MBIn MP3 / WAV / M4A / micOut Transcript, timestampsSpeed ~1× realtime
5

Text Summarizer

Condense a long English article or report into a few sentences, generated by a model that runs on your device.

TextModel DistilBART CNN 6-6Download ~300 MBIn English text, 60+ wordsOut Short summarySpeed 10–60 s
6

Sentiment Analyzer

Paste English text and see whether each line reads as positive or negative, with a confidence score for each.

TextModel DistilBERT SST-2Download ~70 MBIn Text, one item per lineOut Positive / negative + scoreSpeed <1 s per line