Ein von einer künstlichen Intelligenz erzeugtes Musikvideo
Mittwoch, 1.6.2022, 22:41 > daMaxWelcome to the future. Ich will das als Screensaver. Jetzt!
Die Beschreibung dazu liest sich so:
In this video, I utilized artificial intelligence to generate an animated music video for the song Canvas by Resonate. This tool allows anyone to generate beautiful images using only text as the input. My question was, what if I used song lyrics as input to the AI, can I make perfect music synchronized videos automatically with the push of a button? Let me know how you think the AI did in this visual interpretation of the song.
After getting caught up in the excitement around DALL·E2 (latest and greatest AI system, it's INSANE), I searched for any way I could use similar image generation for music synchronization. Since DALL·E2 is not available to the public yet, my search led me to VQGAN + CLIP (Vector Quantized Generative Adversarial Network and Contrastive Language–Image Pre-training), before settling more specifically on Disco Diffusion V5.2 Turbo. If you don't know what any of these words or acronyms mean, don't worry, I was just as confused when I first started learning about this technology. I believe we're reaching a turning point where entire industries are about to shift in reaction to this new process (which is essentially magic!).
Important note:
While this AI is impressive, it still required additional input beyond just the song lyrics to achieve the music video I was looking for. For example, I added keyframes for camera motion throughout the generated world. These keyframes were manually synchronized to the beat by me. I also specified changes to the art style at different moments of the song. Since many of the lyrics are quite non-specific, even a human illustrator would have a hard time making visual representations. To make the lyrics more digestible by the AI, I sometimes modified the phrase to be more coherent, such as specifying a setting or atmosphere.This was my first time working with DDV5, and I'm very happy with the results! There were many times where my jaw dropped upon seeing what the AI came up with. I haven't felt this sense of wonder from technology since I first experienced a HD videogame as a child.
If you would like to learn more about how this video was made, try this yourself, or ask me any questions, I'll post a more detailed explanation of how to get started on Patreon (link below). The post is free to the public, no need to pay. If you do want to support me and become a member that would be much appreciated, you'll also automatically be entered into the end screen minigames where you earn points on each video and move up the leaderboard!
(via kfmw)
ai | ki | artificial intelligence | deep dream | trip
Endlich wieder Screensaver die CPU & GPU zur Vollast treiben. <3
An meiner Uni hatte sich (vor langer Zeit) jemand die Mühe gemacht, sämtliche Screensaver die zu finden waren, auf den Pool-PCs zu installieren (Linux). Man musste schon viel Zeit dort verbringen, um jeden einmal gesehen zu haben.
Habe versucht einige davon zu finden... keine Chance. Vermisse jetz auch die alten Visualisierungen von Winamp, WMP, ...
Mir wird ganz komisch dabei. Kann das nicht länger anschauen. Mein Kopf mag es außerdem nicht, dass es die ganze Zeit virtuell nach oben geht. Komisches Zeug.
Doppelt Plus lol:
ohne deinen Kommentar gesehen zu haben, dachte ich an einen Screensaver. Wenn das die Zukunft der KI ist, bin ich beruhigt.
Es dürfte simpel sein, daraus einen Bildschirmschoner zu "generieren". Ich verwende yt-dlp (einen Fork von Youtube-dl) auf meinem Laptop. Der Fork ist auf Github auch für Windows erhältlich.
Mit ein bisschen Commandline-Kungfu habe ich mal geguckt, welche IDs beim Download für dich voraussichtlich relevant wären und dir mit einer senkrechten roten Linie markiert:
https://ibb.co/W3dRdB3
Du musst halt nur noch gucken, was deiner Bildschirmauflösung am nächsten kommt.