Skip to main content

Object Extractor API

spicyapi/object-extractor-v1/edit

Object Extractor cuts the object you describe out of one photo and returns it as a transparent PNG, at the full photo size or trimmed to the object.

From $0.024/image

Workbench

Input

Image editing
30/500
Required. A short description of the one object to keep, such as "the red car" or "the woman in the cream sweater". Add color, position or clothing to separate similar things. Does not change the price. at least 1 characters · at most 500 characters
1/1

Drop files or media links, paste, or browse · 1 file · Max 10 MB · JPG · PNG · WEBP

  • 1
1 / 1 files
The photo that contains the object: a JPEG, PNG or WebP upload or a direct link. Without autocrop the cutout keeps this photo's dimensions. at least 1 characters
Clean up the edges
Off by default. On runs an extra background-removal pass that cleans leftover background pixels and edge transparency, useful around hair and soft outlines. Does not change the price.
Crop to the object
Off by default, which returns the cutout at the full photo size. On trims the canvas tightly around the object. Does not change the price.
Safety checkerOff

SpicyAPI does not run a safety checker on this model. Your prompt and media go to the model as written, and the model itself decides what comes back.

Checking your account before enabling submission and pricing.

Output

Ready for a new run
Example result

Related models and next tasks

Missing the model you need?

OBJECT EXTRACTOR API

Name the thing you want, get it back on a transparent background.

Key numbers

Test turnaround
11–22 s
Range across our runs on 1024 to 1536 px photos.
Output
PNG
Transparent background, full size or trimmed to the object.
Extra switches
2
Trim to the object and an extra edge-cleanup pass, both off by default.

Before you spend

All modes

Use photos you own or are licensed to use; cutting an object out of an image does not change its rights.

Image editing

One object description per request and one PNG back. Objects that are partly hidden come back with the hidden parts missing, and items touching the subject, such as a held glass or a strip of table, may be included. See-through materials keep whatever was behind them in the photo. The description is required.

What it does

Object Extractor before and after: a man and a woman at a bar table, and the woman alone cut out on a transparent checkerboard background.

Pick a person

One of two people, chosen by description

We asked for "the woman in the cream sweater" in a two-person bar scene. She came back on a transparent canvas at the full 1536×864 size, hair and sweater edges intact, while the man and the bottle shelf were removed.

Pick an object

A single wine glass, trimmed tight

The bar scene next to a single wine glass cut out and trimmed tight on a transparent checkerboard background.

With autocrop on, "the wine glass in front of the man" came back as a 130×307 PNG of just the glass. The bar lights seen through the bowl stayed in the cutout, which is worth knowing before you place glassware on a new background.

Words, not clicks

No mask to draw

There is no brush or box to place. A short phrase with a color, a position or a piece of clothing is enough to tell two similar things apart.

Made with Object Extractor

  • Object Extractor before and after: a man and a woman at a bar table, and the woman alone cut out on a transparent checkerboard background.
  • The bar scene next to a single wine glass cut out and trimmed tight on a transparent checkerboard background.
  • Object Extractor output at full photo size: the woman in the cream sweater alone on a transparent background, the rest of the bar removed.
  • The red-haired woman in a cream sweater, holding a glass of red wine, cut out and trimmed tight with autocrop on a checkerboard background.

Where it fits

  • One product out of a busy shot

    Pull a single bottle, bag or shoe out of a lifestyle photo for a catalog tile, without retouching the rest of the scene by hand.

  • Choosing one person in a group photo

    A background remover keeps everyone in front; here you name the person to keep and the others are dropped with the background.

  • Assets for collages and thumbnails

    Trim the cutout to the object and drop it onto a new background, a video thumbnail or a slide.

Model reference

Object Extractor API reference

Object Extractor API specifications

Endpoint
Image edit
Input
One photo plus a text description of the object
Output
Transparent PNG
Canvas
Full photo size, or trimmed with autocrop
Edge cleanup
Optional extra pass (refine_edges)

How to call the Object Extractor API

  1. Describe one object

    Write a short noun phrase in prompt, such as "the red car" or "the woman on the right". Add a color, position or clothing detail when the photo has several similar things.

  2. Choose the canvas

    Leave autocrop off to get a cutout at the full photo size, ready to layer back in place. Turn it on to get a tight PNG around the object for a product card or a sticker.

  3. Clean the edges if needed

    Switch on refine_edges for an extra background-removal pass that tidies stray pixels and edge transparency, useful on hair and soft outlines.

Object Extractor API questions