# alexjc/neural-doodle

Turn your two-bit doodles into fine artworks with deep neural networks, generate seamless textures from photos, transfer style from one image to another, perform example-based upscaling, but wait... there's more! (An implementation of Semantic Style Transfer.)

Repository: https://github.com/alexjc/neural-doodle
Canonical: https://ross.abutalabs.com/products/neural-doodle
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: image-processing, image-manipulation, image-generation, deep-learning, deep-neural-networks
Archived: true
Last push: 2020-10-01T16:54:52+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3833, "days_push": 2162, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9852, forks 891 (observed 2026-08-28T04:10:37.493794+00:00)

## What it is
A Python implementation of Semantic Style Transfer (Champandard, 2016) based on the Neural Patches algorithm. It turns rough doodles into refined artworks, generates seamless textures from photos, transfers style between images, and performs example-based upscaling using deep neural networks.

## Use cases
- turn my doodle sketch into a painting with a neural network
- transfer the style of one image onto another photo
- generate seamless textures from a sample photo
- upscale a low-resolution image using an example high-res image
- create image analogies from a style image and its annotation
- render artwork in the style of a specific painter from a rough sketch

## When to choose
- you want semantic, annotation-guided style transfer rather than simple style transfer
- you need to generate seamless textures or image analogies from annotated examples
- you have a CUDA-capable NVIDIA GPU and want research-style neural image synthesis
- you want a scriptable Python tool for patch-based neural image generation

## When to avoid
- you need a fast, production-ready image generation pipeline with modern models
- you only have a CPU and cannot tolerate multi-hour render times
- you want an actively developed tool with recent updates and community support
- you need a GUI or one-click workflow rather than a command-line script with manual parameter tuning

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, deep-learning, machine-learning
- domain: image-processing, deep-learning, artificial-intelligence, graphics
- platform: python, windows
- tags: style-transfer, semantic-style-transfer, neural-doodle, image-synthesis, texture-generation, image-analogy, upscaling, linux, macos, gpu

## Member repositories
- alexjc/neural-doodle (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:37.493794+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 2026-08-29T17:20:53.910467+00:00, confidence not recorded.
  - readme: https://github.com/alexjc/neural-doodle (fetched 2026-08-28T04:10:37.493794+00:00, sha b91a83eadac1)
- Data as of 2026-08-30T08:39:29.467469+00:00.