Neural Deep Learning

Please see this :
https://macdaddy.io/style/
they are trying to bring deep learning style paintings to desktop (like pikazo for iOs),

Adobe is trying too:
https://research.adobe.com/leveraging-deep-learning-to-fix-images/

Is it the time for SA that looks these and does some integrating too,
Or you think Deep Learning Is not good enough?

thank you

You need to be a member of Studio Artist to add comments!

Join Studio Artist

Email me when people reply –

Replies

  • Topaz Labs has a similar product: https://topazlabs.com/ai-remix/

  • I have looked at these software alternatives and am grateful for the information. They raise significant questions. Is one satisfied to travel the path of a copyist or venture into the realm of true creativity?

    I am constantly surprised and happy to uncover/discover the new, the realm of creativity as I experiment with the myriad of options and possibilities offered in Studio Artist. Why convert or use Studio Artist as a copy machine? I am constantly amazed by the results that come from experimentation in the digital playground offered in Studio Artist. Leave the domain of copy to these other softwares.

    Paul

  • Ok personal opinion time: Style and AI-REMIX programs use what's known as the fast neural style (feedforward network). The tendency for this algorithm is that it makes the style transfer very fast on large images, but it also makes quite a mushy, kinda hideous, but accurate-to-style look. The generated results often introduce a bunch of chatter and unnecessary noise which results in an overall dimension-less, gargled image.

    The code is pretty much free for you to run it yourself, there are already a gajillion programs that do the same.
    https://github.com/jcjohnson/fast-neural-style

    To be fair, the pace at which this sort of NN (neural network) is developing is incredible, we see improvements in just a few short years (even months at times). So it'd be probably unfair to say the same in a couple years time. Algorithms, methods, and ideas will definitely improve the overall image quality so I hope to see that.

    For higher quality results currently we have to resort back to the original context of this research. Originally this took a crap load of time to render and output, especially for larger images. But personally, this is far better than the current generation of feedforward network results.

    There are a couple websites that offer high resolution output, one in which is:
    https://art.app/

    The resulting output from art.app is not only impressive, it's far better than anything that the fast-neural style can produce as of today. The problem with the image generation is that it takes a huge amount of processing power to accomplish it. It takes some tremendous amount of GPU power to just get these fantastic results. I personally gravitate towards this however, artistically, quality-wise incredible. Below are some extreme test examples.

    2472689088?profile=RESIZE_1024x10242472689435?profile=RESIZE_1024x1024By the way, these are the same source image, just with different styles. One was processed far extreme than the other.

    This isn't to say that those fast-transfers are bad or anything. I'm just saying that the aesthetic output kinda feels at a loss somewhere. However, it will be fantastic to see something of this nature in StudioArtist!

  • I have tested many neural networks software, Pikazo, Art.app, Artisto, DeepArt Effects, Style, etc. The most interesting, with the best result is Pikazo. I played with it 2 years, and posted results, here and here (Pikazo, SA, Filter forge pictures).

    Yes, as Yuya wrote, (The generated results often introduce a bunch of chatter and unnecessary noise which results in an overall dimension-less, gargled image) it's a problem. But it you modify your source and style pictures, the results are better. Sometimes, I deleted black or whites regions, etc...Or just turn 90° my style..Some interesting results also when you revisit 2 artists, like Picasso with Kandinsky : 

    2472711810?profile=RESIZE_1024x1024

    or a lion head, "mixed" with a metal structure :

    2472711972?profile=RESIZE_1024x1024

    or something like this, with :

    2472712194?profile=RESIZE_1024x1024

    Art.app : the deep effect is more "regular"2472712420?profile=RESIZE_1024x1024

    I have my own methods to make large pictures.

    But there are no settings where you can modify some parameters.

    Yes, a "deep effect" tool in V6 would be great....

    • I think as a tool just like other tools of SA, Studio Artist is better think of Deep Learning as soon as possible, It must ride it and not stay under the wave. 

      Dear Bernard,
      you can see my works here:
      https://deepdreamgenerator.com/u/smmsamm

      but I like your pikazo result and tested Pikazo too, never could get Large and high quality from it,
      Please tell us how to enlarge with this quality?

      thank you

      • thanks, I found two website that can enhance and increase the resolution by Deep Learning algorithm:

        https://deep-image.teonite.com/
        But It shows me error "fetching filters failed" maybe in my country it is banned.

        and

        https://letsenhance.io/boost
        that I checked and liked it.

        I hope if you know better ways tell us here.

This reply was deleted.

Interdimensional Coincidence Control

Hi everyone, I am glad the site is still here! Here is a new short video I made. All made in Studio Artist, several separate videos with alpha channels, then combined in layers with the music in Blender. A lot of MSG running through brushes, with several of the brush Path Starts being controlled by the MSG Scan Generator in the Generator part of the Path Start in the Paint Synthesizer. Also some MSG running through a brush, then making a video of that with an alpha channel, then making that a…

Read more…
3 Replies · Reply by Thor Johnson Mar 22

Whats going on with this site?

Has anyone else gotten a warning about this site disappearing? An email form just popped up, asking me to contract the owner and leave a message to let them know that they may loose their "network"Did Synthetik forget to pay it's bills, or is something else going on?I think 8 months is more than enough vacation time. Is anyone at Synthetik doing any development work at all? 

Read more…
4 Replies · Reply by Emil G. on Saturday

Having difficulty exporting canvas as image

I'd like to export a canvas as a .tiff/.tif image file to a folder I made on my desktop.I select that from a dropdown menu, I can name the exported file, change the extension, etc, and I press save but nothing happens.It's always worked until now. It seems like a simple task. Any ideas?I'm on Mac OSX 12.6, if that matters, and my system hasn't changed since the last time I was able to export successfully.Thanks  

Read more…
2 Replies · Reply by Tony Bouttell Mar 5