# manuelruder/artistic-videos

Torch implementation for the paper "Artistic style transfer for videos"

Repository: https://github.com/manuelruder/artistic-videos
Canonical: https://ross.abutalabs.com/products/artistic-videos
Language: C++
License: NOASSERTION
License Family: other
Archived: true
Last push: 2018-02-14T22:10:55+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3784, "days_push": 3122, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1754, forks 251 (observed 2026-08-28T04:05:32.042646+00:00)

## What it is
A Torch (Lua) implementation of the paper 'Artistic style transfer for videos', which applies the style of a painting to an entire video while keeping frames temporally consistent using optical flow constraints. It builds on Justin Johnson's neural-style code and requires a CUDA GPU for practical runtimes.

## Use cases
- stylize a video in the style of a painting
- apply artistic style transfer to video frames with temporal consistency
- reproduce results from the 'Artistic style transfer for videos' paper
- convert a movie clip into a Van Gogh-style animation
- research video style transfer with optical flow

## When to choose
- you need arbitrary style images, not just precomputed style templates
- you want the original research-quality implementation with temporal consistency constraints
- you have a CUDA GPU and can tolerate minutes of processing per frame

## When to avoid
- you need fast, real-time stylization - use fast-artistic-videos instead
- you want a maintained, modern PyTorch or TensorFlow codebase - this uses legacy Torch7
- you only have a CPU or a small GPU
- you need a permissively licensed project - the license is non-standard

## Facets
- artifact type: application
- maturity: maintenance
- function: image-processing, video-processing, deep-learning
- domain: computer-vision, image-processing, deep-learning
- platform: cpp
- tags: style-transfer, neural-style, torch7, optical-flow, research-code, video, linux, gpu

## Member repositories
- manuelruder/artistic-videos (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:32.042646+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 2026-08-30T03:28:08.185069+00:00, confidence not recorded.
  - readme: https://github.com/manuelruder/artistic-videos (fetched 2026-08-28T04:05:32.042646+00:00, sha 8e1f87078c7e)
- Data as of 2026-08-30T08:39:29.467469+00:00.