Earlier quoted context omitted.
If a computer generates 100000000 unfunny jokes and one that seems funny, does that count?
It's not very different from how I learned to tell jokes. My brothers heard a lot of terrible jokes before I figured out timing and other aspects of humour. If it makes you laugh, it's a good joke. What does the origin matter?
Pikazo
81–90 of 99 posts
Re: Pikazo
#82Earlier quoted context omitted.
And now at http://deepart.io/ we have hi-resolution and the authors of the algorithm on-board. Thanks for mentioning us :)
Would you mind going into detail on how higher res is achieved? Splitting the original image into smaller regions, and rendering each separately?
Re: Pikazo
#83Earlier quoted context omitted.
And now at http://deepart.io/ we have hi-resolution and the authors of the algorithm on-board. Thanks for mentioning us :)
Just some UI/UX observations: The "Use style" wording didn't immediately register for me that the images were clickable. I wondered why the gallery images all had the same description when they were clearly different styles! Perhaps "Use this style" would be more expressive? When you do click through, it shows the same image (with face) to be used as the style image, leaving me wondering if a user provided style imag…
Re: Pikazo
#84Earlier quoted context omitted.
And now at http://deepart.io/ we have hi-resolution and the authors of the algorithm on-board. Thanks for mentioning us :)
There is 30 characters limit for the mail field :(.
Re: Pikazo
#85Is this done with the deep learning research that was published here a couple of months ago?
I was just thinking that. Seems it might be based on the description. Kinda interested how they'd do it in a speedy way on mobile devices. Hope they didn't just knock-off the open-source code though.
https://www.washingtonpost.com/news/innovations/wp/2015/09/1...
Re: Pikazo
#86Earlier quoted context omitted.
> No, it wouldn't count. Because then we would have some thousands of bohemian rhapsodies. The computer broke after completing the work: now does it count? I don't understand your idea of art, isn't there beauty in the result? You give different value if the same result has been reached by a computer, chaos or a human? Do you have to know how the piece has been produced to decide if it's art or not?
Yes. A rock that's been pleasingly shaped by desert winds is not considered art. But if we'd later find out that it was actually a man-made artifact, it would become a candidate for this label.
Re: Pikazo
#87Re: Pikazo
#88Is it using this algorithm? https://github.com/jcjohnson/neural-style
https://www.youtube.com/watch?v=pRL9J6DoCgs&feature=youtu.be
https://itunes.apple.com/us/app/joy-of-programming-painter/i...
Re: Pikazo
#89Earlier quoted context omitted.
I was just thinking that. Seems it might be based on the description. Kinda interested how they'd do it in a speedy way on mobile devices. Hope they didn't just knock-off the open-source code though.
"Stiefvater [...] described it to me as 'black magic,' and doesn’t even fully understand how it works. He downloaded it from Github, where a computer programmer he’s never met posted it." https://www.washingtonpost.com/news/innovations/wp/2015/09/1...
Let's refrain from making nasty implications about each other, shall we? Thank you.
Re: Pikazo
#90Earlier quoted context omitted.
Just some UI/UX observations: The "Use style" wording didn't immediately register for me that the images were clickable. I wondered why the gallery images all had the same description when they were clearly different styles! Perhaps "Use this style" would be more expressive? When you do click through, it shows the same image (with face) to be used as the style image, leaving me wondering if a user provided style imag…
Thank you very much! As these are recent changes which we haven't tested live, your comments are very useful and we are actually implementing them now.