# NVIDIA/FastPhotoStyle

Style transfer, deep learning, feature transform

Repository: https://github.com/NVIDIA/FastPhotoStyle
Canonical: https://ross.abutalabs.com/products/fastphotostyle
Language: Python
License: NOASSERTION
License Family: other
Last push: 2023-06-07T07:40:31+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3122, "days_push": 1183, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 11177, forks 1192 (observed 2026-08-28T04:10:46.312926+00:00)

## What it is
FastPhotoStyle is NVIDIA's official PyTorch implementation of the ECCV 2018 paper 'A Closed-form Solution to Photorealistic Image Stylization'. Given a content photo and a style photo, it transfers the style photo's appearance onto the content photo while keeping results photorealistic.

## Use cases
- transfer the style of one photo onto another photo
- apply a reference photo's color and texture to my image
- photorealistic image stylization research
- reproduce ECCV 2018 photo style transfer results
- make my vacation photo look like a painting but still photorealistic
- experiment with deep learning style transfer in PyTorch

## When to choose
- you need photorealistic (not artistic) style transfer between two photos
- you want the reference implementation of the WCT2 algorithm for research
- you are comfortable running PyTorch models on a GPU

## When to avoid
- you need a maintained production library - the repo has not been actively updated since 2018
- you want real-time or mobile style transfer
- your use case is commercial - the code is licensed CC BY-NC-SA 4.0 (non-commercial)
- you need artistic/stylized (non-photorealistic) transfer like AdaIN or Gatys-style methods

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, deep-learning, machine-learning
- domain: image-processing, computer-vision, deep-learning
- platform: python
- tags: style-transfer, photorealistic-stylization, pytorch, computer-vision, research-code, linux, gpu

## Member repositories
- NVIDIA/FastPhotoStyle (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:46.312926+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:16:43.369687+00:00, confidence not recorded.
  - readme: https://github.com/NVIDIA/FastPhotoStyle (fetched 2026-08-28T04:10:46.312926+00:00, sha 11fba3cddf57)
- Data as of 2026-08-30T08:39:29.467469+00:00.