Just select a video, tap the pencil (edit) icon, and choose Stabilize. These videos (which you can play in sync here) demonstrate before & after results:
More examples can be found in this album.
(aka, Hieronymus Bosch, PBS Edition)
Felt like you’re having a stroke yet today? No? I can fix that. Here:
areben.com This artwork represents what it would be like for an AI to watch Bob Ross on LSD (once someone invents digital drugs). It shows some of the unreasonable effectiveness and strange inner workings of deep learning systems. The unique characteristics of the human voice are learned and generated as well as hallucinations of a system trying to find images which are not there.
Ever since the late 90’s, when I was a designer browbeating Adobe for a good collaboration system, I’ve been intrigued by efforts to help teams work better together. Frame.io has just rolled out v2 of its video-centric team platform:
Elsewhere, FiftyThree (makers of the much-loved Paper sketching/notes app) have introduced the Slack-savvy Paste tool:
- Arrange your flow and add text to craft the story you want to tell
- Fullscreen walkthroughs and fast feedback from your team that syncs with Slack.
Knowing their history, I’m expecting a lot of delightful attention to detail.
I’m intrigued by—but don’t quite know what to make of—Logojoy, a hosted app that promises, “Using artificial intelligence and advanced learning algorithms, our logo maker is able to produce designs just like a designer would.”
It seems that almost no one in the general public can define just what the hell “AI” means, and I’m not sure that this offers anything more than a nicely packaged wizard/template system. Still, some of the results I got weren’t half bad, and creative disruption will only continue: The world at large will get greater & greater access fairly competent aesthetics (think Target & design for all), while creative people will have to hustle more & more to remain relevant.
If you take it for a spin, let me know what you think.
Around 2am in a long-past life, I terrified some young kids fishing for sharks off the end of their pier in Puget Sound. I was wearing night vision goggles in a RIB alongside a bunch of M16-toting Navy guys, and we’d been quietly paddling around the boys’ pier as we hid from our own ships while we stalked Rangers. But that’s a whole other story.
The X27 seems amazing & makes the goggles I wore look like Frogger by comparison:
The camera was developed for military use, has an effective ISO rating of 5,000,000, and has a comically long name: “X27 Reconnaissance Day/Night high Fidelity true real time low light/low lux color night vision Imaging Security / Multi Purpose camera system”. Pricing information is not available, but I bet you’re paying for every single one of those words.
This blows. 🙂
Holland is one of the greatest countries to live in, but the biggest downside is that it rains 145 days a year. That’s why the Google Cloud Platform team in the Netherlands is launching Google Wind this Spring.
Because LOL nothing matters.
It’s a bit OT for this blog, maybe, but I’m excited to check out the marvelously named Song Exploder:
Song Exploder is a podcast where musicians take apart their songs, and piece by piece, tell the story of how they were made… Using the isolated, individual tracks from a recording, Hrishikesh asks artists to delve into the specific decisions that went into creating their work. Hrishikesh edits the interviews, removing his side of the conversation and condensing the story to be tightly focused on how the artists brought their songs to life.
The Weezer episode in particular sounds really interesting. In it Rivers Cuomo talks about how he constructs guitar solos by singing them, then using software to modify his recorded voice to match the desired tones.