How AI can remove background from a photo
The tool uses a model based on U2Net, a neural network trained to spot the main subject in a picture. It looks at every pixel and decides whether it belongs to the subject or to the scene behind it. The result is a mask with soft edges, which is then used to cut the subject out.
Some photos are easier than others. You get the cleanest cutout when:
- there is one clear subject that fills a good part of the frame
- the subject and the background have different colors
- the light is even and the subject is in focus
Fine flyaway hair, glass, smoke and see through fabric are hard for any automatic tool. If an edge looks rough, try a second photo with a plainer background. There is no manual brush for touch ups yet, so a good source photo makes the biggest difference.
Choose the right output
| Output | Best for |
|---|---|
| Transparent PNG | Designs, collages, stickers, slides and logos on colored pages |
| White background | Product listings, catalogs, resumes and team pages |
| Black or custom color | Social posts in brand colors, dramatic product shots |
| Blurred original | Profile pictures that still feel natural, portrait style photos |
A transparent PNG is the most flexible choice because you can place it on anything later. Keep in mind that JPG cannot store transparency, so if the cutout is converted to JPG, the empty area turns white.
For dedicated guides, see White Background and Blur Background. Cutout PNGs can be heavy, so run them through Compress PNG before you put them on a website.
Popular ways to use a cutout
- Online shops: place every product on the same clean background for a tidy catalog.
- Presentations: drop a cutout of a person or device onto a slide without an ugly box around it.
- Social posts and thumbnails: put yourself in front of bold colors or text.
- Cards and collages: combine pets, family members or objects from different photos into one picture.
