# DmitryUlyanov/texture_nets

Code for "Texture Networks: Feed-forward Synthesis of Textures and Stylized Images" paper.

Repository: https://github.com/DmitryUlyanov/texture_nets
Canonical: https://ross.abutalabs.com/products/texture_nets
Language: Lua
License: Apache-2.0
License Family: permissive
Topics: texture-networks, torch, neural-style, style-transfer
Last push: 2018-01-07T06:56:34+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3831, "days_push": 3160, "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 1225, forks 215 (observed 2026-08-28T04:04:03.058660+00:00)

## What it is
Research code implementing the 'Texture Networks' paper for fast feed-forward texture synthesis and neural style transfer using Torch7. Once trained, the generator network can instantly produce textures or stylized images of any size.

## Use cases
- stylize images with neural style transfer
- generate textures from a sample image
- train a feed-forward style transfer network
- apply artistic filters to photos in real time
- reproduce texture networks paper results
- experiment with instance normalization for stylization

## When to choose
- you need to reproduce or extend the Texture Networks or Johnson perceptual losses papers
- you want fast feed-forward stylization instead of slow per-image optimization
- you are researching generator architectures and instance normalization

## When to avoid
- you want a maintained tool with modern PyTorch or TensorFlow support
- you cannot install the deprecated Torch7 framework and loadcaffe
- you need production-ready image stylization with GPU support guarantees

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, image-processing, llm-training
- domain: deep-learning, image-processing, computer-vision, graphics
- platform: python
- tags: style-transfer, texture-synthesis, neural-style, torch7, instance-normalization, generative-models, research-code, gpu, linux, macos

## Member repositories
- DmitryUlyanov/texture_nets (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:03.058660+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 2026-08-30T06:15:21.953814+00:00, confidence not recorded.
  - readme: https://github.com/DmitryUlyanov/texture_nets (fetched 2026-08-28T04:04:03.058660+00:00, sha 118868cf81e0)
- Data as of 2026-08-30T08:39:29.467469+00:00.