jiupinjia/stylized-neural-painting

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1600 stars · 261 forks observed · 2026-08-28

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

Official PyTorch implementation of the CVPR 2021 paper 'Stylized Neural Painting', which translates photos into vectorized painting artworks by predicting physically meaningful stroke parameters rendered via a learned neural renderer. It includes the full training and inference pipeline, Colab demos, and joint optimization with neural style transfer.

Use cases

• convert a photo into an oil or watercolor painting
• generate stroke-by-stroke painting animations from images
• reproduce results from the Stylized Neural Painting paper
• apply artistic style transfer to images with controllable painting styles
• train a neural renderer that imitates a vector graphics renderer
• run image-to-painting translation on CPU without a GPU

When to choose

• you need research-grade image-to-painting translation with vectorized stroke output
• you want to experiment with differentiable neural rendering or stroke parameter optimization
• you want a runnable PyTorch pipeline with pretrained demos and Colab notebooks

When to avoid

• you need a production-ready, actively maintained style transfer service
• you require commercial usage - the code is under a CC BY-NC-SA non-commercial license
• you need fast real-time image stylization rather than slow optimization-based rendering

Facets

library · maturity maintenance

machine-learning image-processing deep-learning computer-vision image-processing artificial-intelligence graphics python cross-platform style-transfer neural-rendering image-to-painting stroke-parameters pytorch cvpr-2021 research-code gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="jiupinjia/stylized-neural-painting")