lengstrom/fast-style-transfer

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

10962 stars · 2546 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A TensorFlow implementation of fast neural style transfer that applies the style of famous paintings to photos and videos in real time. It is based on Johnson's perceptual losses and Ulyanov's instance normalization, and can stylize images in roughly 100ms on a Titan X GPU.

Use cases

• apply painting styles to photos with a neural network
• stylize videos frame by frame
• run fast artistic style transfer on images
• train a custom style transfer model
• learn how perceptual loss style transfer works

When to choose

• you want real-time or near-real-time style transfer rather than slow iterative optimization
• you need to stylize video, not just single images
• you want to train a network for a new painting style
• you are doing academic research on neural style transfer

When to avoid

• you need a permissively licensed library for commercial use - the license restricts non-research use
• you want a maintained project on modern TensorFlow or PyTorch versions
• you need general image editing rather than artistic style transfer

Facets

library · maturity maintenance

image-processing deep-learning machine-learning deep-learning computer-vision image-processing python style-transfer tensorflow neural-style cnn video-stylization artistic-filters gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="lengstrom/fast-style-transfer")