Neural Network Musicvideo

Gepostet vor 1 Jahr, 6 Monaten in #Design #Misc #Tech #AI #Animation #Musicvideos

Share: Twitter Facebook Mail

Das erste „industrial scale neural-network based music video“ zu ’nem ätzenden EDM-Dreckstrack:

Von Samims Blog auf Medium: Industrial DeepDreaming: Music Video for Band “Years & Years”

yearsDuring the production process, numerous challenges had to be overcome. Applying deepdream to 2K footage, building custom hardware rigs, designing tools for rapid iteration (deepUI), exploring hyper-parameters and collaborating with directors & corporates— All under time pressure.

The final video is the worlds first industrial scale neural-network based music video. It gives us a glimpse of a future where humans and machines collaborate as equal creative partners. We call this new paradigm creativeAI.

[update] From Samim on the Tweeties: „Producing the video was fun, but done mainly with muted audio due to sanity reasons“. I can relate to that.

Musicvideos: Ghostpoet, T.Raumschmiere, Slowdive, Fleet Foxes, Mogwai, !!! (Chk Chk Chk), From Indian Lakes, Strand of Oaks, Sorority Noise

Musicvideos: Poppy, Body Count, Casisdead, The National, Integrity, Red Fang, Andy Shauff, Palehound, Men I Trust, Cigarettes after Sex

Smile-Filtering a Face until there is no Face left to smile-filter

Gene Kogan: „just in case you were wondering, this is what happens when you repeatedly run FaceApp’s smile filter until…

Musicvideos: Ho99o9, ADULT., Perfume Genius, We Are Not Brothers, Skating Polly, alt-J, Portugal. The Man, Com Truise, Japanese Breakfast

Neural Network dreams your Dreams

Wissenschaftler können bereits seit Jahren Bilder aus Gehirnscans extrahieren, also: Tatsächlich ein Abbild davon schaffen, was wir sehen. Die Resultate…

Musicless Take On Me

Mal wieder ein Musicless Musicvideo von Mario Wienerroither. Die Meme ist zwar schon lange durch und ich habe sie ja…

4 AI-Obamas learn Algo-Lipsynch from Audio

Seit ich über die neuen Möglichkeiten von Machine Learning bezüglich Computer Vision und der Generation von Bildern schreibe, vor allem…

Akira Animation-Cels

Der Macher des Tumblrs Subject 28 sammelt Akira-related Storyboard-Zeichnungen, Backgrounds und Animation-Cels, die er mit Detail-Shots abfotografiert (und dabei öfter…

Neural Networks for Character Control

Daniel Holden, Taku Komura und Jun Saito haben ein Neural Network auf Character-Animationen trainiert, mit dem Figuren in Games und…

Open Eye Signal (Jon Hopkins) on a Modular Synthesizer

Colin Benders: „This track has been haunting me for a while now so I decided to see if I could…

Tokyo GIFathon

James Curran: „I’m in Tokyo for all of April where I’ll be making a new animation every day for 30…