# anishathalye/neural-style

Neural style in TensorFlow! 🎨

Repository: https://github.com/anishathalye/neural-style
Canonical: https://ross.abutalabs.com/products/anishathalye-neural-style
Homepage: https://anishathalye.com/an-ai-that-can-mimic-any-artist/
Language: Python
License: GPL-3.0
License Family: copyleft
Last push: 2026-04-18T16:29:56+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 78, release rhythm 35, longevity 100
- inputs: {"age_days": 3938, "days_push": 137, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5541, forks 1487 (observed 2026-08-28T04:09:22.199153+00:00)

## What it is
A Python command-line tool implementing the neural style transfer algorithm (Gatys et al.) in TensorFlow, applying the style of one image to the content of another. It supports multiple style images with blending weights, checkpointing, and various hyperparameter tweaks.

## Use cases
- apply a painting's style to a photo
- turn my picture into a Starry Night style image
- blend two art styles onto an image
- run neural style transfer from the command line
- generate artistic images with a deep learning algorithm
- stylize photos like famous painters

## When to choose
- you want a simple, well-known implementation of Gatys-style neural style transfer
- you want CLI control over style weights, layer weights, and checkpoints
- you have a GPU or Apple Silicon and want reasonably fast optimization-based stylization

## When to avoid
- you need real-time or fast feed-forward style transfer
- you want a GUI or web interface
- you need modern generative models like diffusion-based stylization

## Facets
- artifact type: cli-tool
- maturity: maintenance
- function: machine-learning, image-processing, deep-learning
- domain: machine-learning, image-processing, computer-vision
- platform: python, cross-platform
- tags: neural-style-transfer, tensorflow, artistic-style, gatys, image-synthesis, gpu

## Member repositories
- anishathalye/neural-style (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:22.199153+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 2026-08-29T17:55:41.920687+00:00, confidence not recorded.
  - readme: https://github.com/anishathalye/neural-style (fetched 2026-08-28T04:09:22.199153+00:00, sha ee5b5f252494)
  - homepage: https://anishathalye.com/an-ai-that-can-mimic-any-artist/ (fetched 2026-08-29T08:51:00.712449+00:00, sha 1a6f68ba4ebb)
- Data as of 2026-08-30T08:39:29.467469+00:00.