naoto0804/pytorch-AdaIN

Health v2 · maintenance only

Flags: archived

Adoption not part of the score

1181 stars · 215 forks observed · 2026-08-28

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

An unofficial PyTorch implementation of the AdaIN paper 'Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization' (Huang+, ICCV 2017). It provides scripts for applying arbitrary artistic styles to content images and for training the style transfer network.

Use cases

• apply an artistic style to a photo
• transfer painting style onto images in real time
• mix multiple styles with interpolation weights
• preserve content color while stylizing
• train a custom AdaIN style transfer model
• batch stylize a directory of images

When to choose

• you want fast arbitrary style transfer in PyTorch
• you need to reproduce or extend the AdaIN ICCV 2017 paper
• you want pretrained decoder and VGG weights ready to use
• you need multi-style mixing or color preservation options

When to avoid

• you need video style transfer
• you want a maintained GUI or web app rather than scripts
• you need official author-supported code
• you need style transfer on mobile or edge devices

Facets

library · maturity maintenance

image-processing machine-learning deep-learning image-processing deep-learning computer-vision python cross-platform style-transfer adain pytorch neural-style-transfer unofficial-implementation gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="naoto0804/pytorch-AdaIN")