Skip to main content

srrt

Recolor a person toward a reference skin colour. You pass the colour, the photo, and a mask of the person. The result is a BGR image with that region moved toward the reference and a soft edge.

from srrt import transfer

result = transfer("#C68642", "person.jpg", "person_mask.png")

result is a uint8 BGR array, the same size as the photo.

Install

pip install srrt

Histogram-rotation mode (idt) needs SciPy:

pip install "srrt[idt]"

Inputs

Argument What it is
reference_color #RRGGBB, #RGB, "R,G,B", an RGB tuple, or a close-up skin photo (path or BGR array)
human_image Person photo (path or BGR array)
human_mask Mask of the same height and width. Non-zero pixels are recolored

Colours are RGB. Image arrays follow OpenCV and are BGR.

A binary mask is feathered over a few pixels. A soft mask (values other than only 0 and 255) is used as the blend itself. Bright, low-chroma pixels inside the mask, such as teeth and eye whites, stay on the original colour.

import cv2
from srrt import transfer

image = cv2.imread("person.jpg")
mask = cv2.imread("person_mask.png", cv2.IMREAD_GRAYSCALE)
result = transfer((198, 134, 66), image, mask, strength=0.8)
cv2.imwrite("out.jpg", result)

A reference photo is sampled the same way as a flat colour:

result = transfer("skin_reference.jpg", image, mask)

Options

Argument Default Meaning
strength 0.8 0 leaves the photo unchanged, 1 applies the full transfer
feather 3 Edge width in pixels for a binary mask
luma_shift 1.0 0 keeps original lightness, 1 matches the reference lightness
erode 4 Border pixels left out of the source colour estimate
protect_whites True Keep teeth and eye whites
seed 0 Sampler seed

Command line

srrt --reference "#C68642" --image person.jpg --mask person_mask.png --output out.jpg
srrt --reference skin_reference.jpg --image person.jpg --mask person_mask.png --output out.jpg --strength 1

Author

vijeshkpaei@gmail.com

Metadata

Release files for srrt 0.1.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for srrt 0.1.1
File Size Uploaded Provenance Actions
srrt-0.1.1.tar.gz 12.6 kB Without provenance Details for srrt-0.1.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for srrt 0.1.1
File Interpreter ABI Platform Actions
srrt-0.1.1-py3-none-any.whl Python 3 none any Details for srrt-0.1.1-py3-none-any.whl

Total release size: 24.7 kB

Release files / srrt-0.1.1.tar.gz

Download URL srrt-0.1.1.tar.gz
Size 12.6 kB
Tags Source
SHA-256 checksum
How to use checksums
85cf66178922c61bede01108541d45e2a88498060e2eab499efa47387fb65f24
BLAKE2b-256 checksum
How to use checksums
5174f45e97306a6fb2b610791c747e67e936fe67da9eb76e908b91beb54d9ead
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.7

Release files / srrt-0.1.1-py3-none-any.whl

Download URL srrt-0.1.1-py3-none-any.whl
Size 12.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
ccdc752a56a7d54625cc8b87cb5544ba50e0fba1d0af48934578fb93f2fef1fc
BLAKE2b-256 checksum
How to use checksums
50f3dc61f48b3824a758c9b47d54926a8104cd7a9a99c163e659ea21c910fb1d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.7

Security for srrt 0.1.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.1 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page