AI Art Assistant

|

I am curently looking for collaborators for my new project. Would you like to join me? Continue reading below!


Hello future collaborator,

I am a software artist and developer looking for potential collaborators who would be interested in testing and/or using a software art tool I am designing. I am applying for grants with the Canada Council, Ontario Arts Council, and Toronto Arts Council which have deadlines at the beginning of October to receive funding to develop the software. The software would be open source and free to use by anyone, but I’m hoping to have some written support by local artists and arts groups to support my grant applications.

There is no financial requirement or even strict obligation to use this tool. Instead, I would simply require a statement of interest from potential collaborators: a brief description of their practice or previous work and why they are interested in using the software. Collaborators would also be welcome to be further involved in the design or testing of the tool. If you wish to commit to helping develop the tool or creating with it please contact me asap, as you may be able to be included as a paid artist in the grant.

Timeline for the project would likely be February 2020 - August 2020 for the software development. Thus testing would be in late summer and use of the tool any time after that.

I’m happy to answer any questions you have or meet in person.

AI Art Assistant Software:

This project will develop an open source, freely available software art tool that allows experts and non-experts to craft visuals to accompany their other content. Artificial intelligence will help quickly construct an initial concept which is then available for further detailed refinements. The goal is to lower the barriers for the creation of visual media to allow for diverse storytelling by people of all skill levels. Potential use cases include:

  • Photo slideshows with background music
  • Poetry with integrated visuals and other talks and presentations
  • Music videos, video essays and video installations
  • Live interactive VJing
  • Visual novels and storytelling games

There are some existing for-profit businesses using some basic AI for presentations and video essays but they are strongly biased towards business and monetization on social media platforms. They provide an example of some of the basic features and user experience however:

These services can be co-opted by artists, but are closed-source and financially prohibitive. Their design is based around profit seeking through “slick” presentation with minimal effort and skill. They demonstrate the feasibility and utility of the AI assisted user interface but free alternatives designed for artistic expression need to be created.

Example content:

For an example of the content the software will help create here is a previous project of mine, done with traditional video editing tools, that took many hours to do:

To test the existing AI-assistant presentation services, I remade the start of the poem. I allowed myself only a few minutes on each site and tried to let their automation do as much of the work as possible. The results are sometimes hilarious but even so it felt magical to have the AI suggest or create some of the content:

Further examples of AI generated visuals that this software could produce can be see in the work I did for the Coding Chaos concert.

Example features for the first version the AI art assistant:

  • AI assisted image search:
    • Search multiple copyright-friendly (creative commons, etc) image databases at once
      • Assisted rights and credits, i.e. automatic credits generation.
    • Image content interpreted by image recognition AI for further tagging and categorization
  • AI assisted sound and music search:
    • Search multiple copyright-friendly sound and music databases at once
  • AI assisted synchronizing of lyrics/text to image or video
    • Match textual lyrics to lyric audio in song, and see text displayed visually along side music
    • Beat finding and content tagging with text matching (i.e. image of a dog appears when the word “dog” is said in the lyrics of the song)
  • AI assisted slide deck:
    • Given a library of images and videos, place them in an initial sequential order to match music or text
    • Advance to next slide based on speech input
    • Layout assistance: choose from various professional layout based on the images and text supplied
      • Smart images: find important elements in images and align them

Longterm planned features: