Fast Style Transfer
AI
neural style transfer
SHOW HN2016
184points
20comments
#155of 2,264 in 2016
Top 7%of 2016 by points
How HN took it
CuriousMostly questions and neutral comments
3 positive, 6 neutral or asking, 2 mixed, 1 critical, out of 12 comments about the project. Thread score +0.17.
Execution: 2 for, 0 againstIdea: 1 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Impressive results and fast stylization
From 3 comments
This is ridiculously cool.
rubyfan on HNResults look pretty nice. Congrats!
visarga on HNTerminology note: there is a difference between Style Transfer and Fast Style Transfer. Fast Style Transfer takes a very long time to train a style model (and the output models…
minimaxir on HN
Easier setup than Torch/Lua implementations
From 1 comment
Terminology note: there is a difference between Style Transfer and Fast Style Transfer. Fast Style Transfer takes a very long time to train a style model (and the output models…
minimaxir on HN
Objections
Checkerboard artifacts in output
From 1 comment
Nice work! Have you seen this - could help reduce some of those checkerboard artifacts http://distill.pub/2016/deconv-checkerboard/
dharma1 on HN
Larger images produce repeated patterns
From 1 comment
Playing around with the tool a bit, supersampling seems to work pretty well to avoid those artifacts. (Thanks to the speed of Fast Style Transfer, this is feasible.) EDIT:…
minimaxir on HN
Requests
Localised brush-based style application
From 1 comment
It would be nice if this algorithm could be created in a more localised form, so that you could take a photo and apply the effect with different intensities as if you were using…
lhnz on HN
Questions
Can style be amplified beyond the original?
From 1 comment
So you can transfer style from image A to image B. What I want to know is, can you use style transfer to "amplify" image A's style to, say, 500%?
pizza on HN
How does it compare with other fast style transfer methods?
From 1 comment
Nice work. I'd be curious how this technique compares with other fast style transfer methods, if any exist.
spacehacker on HN
Alternatives named
Neural Doodle
From 2 comments
It has been done with manual segmentation [1]. And the results are mind blowing. There also a lot of work done on segmentation with neural nets [2, 3], so I wouldn't be surprised…
ebalit on HNAs I mentioned in another thread, there is some work on this: https://github.com/alexjc/neural-doodle
ebalit on HN
Google TensorFlow style transfer implementation
From 2 comments
Relevant Tensorflow/Brain blog post: https://research.googleblog.com/2016/10/supercharging-style-transfer.html
eitally on HNTerminology note: there is a difference between Style Transfer and Fast Style Transfer. Fast Style Transfer takes a very long time to train a style model (and the output models…
minimaxir on HN