HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
jcjohnson
fast-neural-style
Lua2016–2017
jcjohnson / fast-neural-style

fast-neural-style

Feedforward style transfer

4Distinct people
4Mentions
0Explicit recommenders
4.4KGitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

Feedforward style transfer

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by month4 dated mentions

Observed mentions: 2016-10-04 09:36:12 UTC to 2017-10-03 12:34:56 UTC.

0122016-10-01 00:00:00 UTC to 2016-11-01 00:00:00 UTC (exclusive): 2 mentions; 1 submissions, 1 commentsOct 20162016-11-01 00:00:00 UTC to 2016-12-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2016-12-01 00:00:00 UTC to 2017-01-01 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 comments2017-01-01 00:00:00 UTC to 2017-02-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-02-01 00:00:00 UTC to 2017-03-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-03-01 00:00:00 UTC to 2017-04-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-04-01 00:00:00 UTC to 2017-05-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsApr 20172017-05-01 00:00:00 UTC to 2017-06-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-06-01 00:00:00 UTC to 2017-07-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-07-01 00:00:00 UTC to 2017-08-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-08-01 00:00:00 UTC to 2017-09-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-09-01 00:00:00 UTC to 2017-10-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-10-01 00:00:00 UTC to 2017-11-01 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsOct 2017

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Oct 20162016-10-01 00:00:00 UTC2016-11-01 00:00:00 UTC211
Nov 20162016-11-01 00:00:00 UTC2016-12-01 00:00:00 UTC000
Dec 20162016-12-01 00:00:00 UTC2017-01-01 00:00:00 UTC110
Jan 20172017-01-01 00:00:00 UTC2017-02-01 00:00:00 UTC000
Feb 20172017-02-01 00:00:00 UTC2017-03-01 00:00:00 UTC000
Mar 20172017-03-01 00:00:00 UTC2017-04-01 00:00:00 UTC000
Apr 20172017-04-01 00:00:00 UTC2017-05-01 00:00:00 UTC000
May 20172017-05-01 00:00:00 UTC2017-06-01 00:00:00 UTC000
Jun 20172017-06-01 00:00:00 UTC2017-07-01 00:00:00 UTC000
Jul 20172017-07-01 00:00:00 UTC2017-08-01 00:00:00 UTC000
Aug 20172017-08-01 00:00:00 UTC2017-09-01 00:00:00 UTC000
Sep 20172017-09-01 00:00:00 UTC2017-10-01 00:00:00 UTC000
Oct 20172017-10-01 00:00:00 UTC2017-11-01 00:00:00 UTC101

What Hacker News says

4 sources
Real-time neural style transfer is not new; in the past year there have been several academic papers [1-4] on this topic and several open-source code releases: https://github.com/jcjohnson/fast-neural-style https://github.com/DmitryUlyanov/texture_nets https://github.com/chuanli11/MGANs Neural style blending is also not new; I did it more than a year ago using optimization-based method: https://github.com/jcjohnson/neural-style#multiple-style-ima... The novelty of this work is a clever way for training a single network that can apply many different styles; existing methods for real-time style transfer train separate networks per style. Their method also allows for real-time style blending, which is very cool and to my knowledge has not been done before. (Disclaimer: I'm the author of [2]) [1] Ulyanov et al, "Texture Networks: Feed-forward
Read the rest
Synthesis of Textures and Stylized Images", ICML 2016 [2] Johnson et al, "Perceptual Losses for Real-Time Style Transfer and Super-Resolution", ECCV 2016 [3] Li and Wand, "Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks", ECCV 2016 [4] Ulyanov et al, "Instance Normalization: The Missing Ingredient for Fast Stylization", arXiv 2016
In Supercharging Style Transfer

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.