Skip to main content

Photo Colorizer API

spicyapi/photo-colorizer-v1/edit

Photo Colorizer turns one black-and-white or sepia photo into a color JPEG with natural skin, sky and clothing tones, returned larger than the input.

From $0.06/image

Workbench

Input

Image editing
1/1

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

  • 1
1 / 1 files
The black-and-white, sepia or faded photo to colorize: a JPEG, PNG or WebP upload, or a direct link. The result is a JPEG about two to three times larger. at least 1 characters
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?

PHOTO COLORIZER API

Black-and-white photos back in believable color, at a larger size.

Key numbers

Output size
2–3×
768×1152 came back at 1664×2496; 1024×576 at 2848×1600.
Test turnaround
~17 s
Typical time for one portrait in our tests.
Prompts needed
0
Send the photo; the colors are chosen for you.

Before you spend

All modes

Colorize photos you own or are allowed to use, and label colorized historical images as such when you publish them.

Image editing

One photo per request, returned as a JPEG at roughly two to three times the input dimensions. Colors are inferred, so hair, eyes, clothing and painted surfaces may differ from the real ones. It does not remove scratches or dust; restore damaged prints first.

What it does

Photo Colorizer before and after: a black-and-white portrait of a bearded man on a city rooftop, and the colorized version with an orange sunset sky.

Before and after

A gray rooftop portrait turned into a sunset scene

From a plain black-and-white photo, the tool painted warm skin, a brown jacket, a blue-to-orange sunset sky and lit windows across the city. None of those colors were in the file; they were inferred from shapes and tones.

Restore, then colorize

From a scratched sepia print to a clean color photo

Three versions of one portrait: a scratched sepia scan, the restored scan, and the restored scan after colorization.

Left: the damaged scan. Middle: the same scan after Old Photo Restorer. Right: the restored file after Photo Colorizer. Coloring the cleaned picture kept the skin even and the sky smooth.

A guess, not a record

Colors are inferred from the picture

A black-and-white photo carries no color information, so every hue is the model's best reading of the scene. Treat the result as a natural-looking interpretation and keep the original next to it.

Made with Photo Colorizer

  • Photo Colorizer before and after: a black-and-white portrait of a bearded man on a city rooftop, and the colorized version with an orange sunset sky.
  • Three versions of one portrait: a scratched sepia scan, the restored scan, and the restored scan after colorization.
  • Photo Colorizer before and after: a black-and-white photo of a man and a woman at a bar table with wine glasses, and the colorized version.
  • Photo Colorizer output: a bearded man in a brown jacket and white T-shirt on a rooftop, with an orange sunset over a blue city skyline.

Where it fits

  • Bringing family history to life

    Give relatives a color version of a parent's or grandparent's portrait to sit next to the original in an album or on a memorial page.

  • History and documentary content

    Colorize archive stills for a video essay, a museum caption or a social post, and keep the original alongside for comparison.

  • Restoration workflows

    Chain it after Old Photo Restorer: repair first, colorize second, then upscale if you need a print.

Model reference

Photo Colorizer API reference

Photo Colorizer API specifications

Endpoint
Image edit
Input
One black-and-white, sepia or faded photo
Output
JPEG, about 2–3× the input dimensions
Controls
None beyond the photo
Best with
Clean scans; restore damaged prints first

How to call the Photo Colorizer API

  1. Start from a clean scan

    Colorizing works best on a picture without scratches or dust. If the print is damaged, run Old Photo Restorer (/models/photo-restorer-v1) first and color its output.

  2. Send image_url

    Upload the black-and-white or sepia photo as JPEG, PNG or WebP, or link to the file directly.

  3. Review the colors that were guessed

    Hair, eye and clothing colors are inferred, not recovered. If you know the real ones, treat the result as a starting point for a manual touch-up.

Photo Colorizer API questions