manuelruder/artistic-videos

Health v2 · maintenance only

Flags: no_releases archived no_license

Adoption not part of the score

1754 stars · 251 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

application · maturity maintenance

image-processing video-processing deep-learning computer-vision image-processing deep-learning cpp style-transfer neural-style torch7 optical-flow research-code video linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="manuelruder/artistic-videos")