AI Generated Videos, In Minutes! – Just A Free Thinker At Large

Years ago, when we bought our first Google Home unit (as soon as it was available), I described the technology as “magic”. I demonstrated it to my kids, pointing out the fact that you could ask the Assistant for the weather, or to explain something, or translate from one language to another. You could ask for any song to be played, or any movie to appear on the TV via Netflix. This disembodied voice would listen and then do your bidding. “Your with is my command!” Yeah, magic.

This was (and is) the kind of science-fiction universe I envisioned as a kid, a world where a supercomputer living in my house would listen in and chat with me, answering questions, playing music; you know, all that stuff it can do now. I also envisioned living in an orbital hotel, going to Mars for a holiday, or zipping through the sky in my flying car, but you know… baby steps.

But the magic has continue to come. Now, we’ve got generative AI, so the magic just keeps getting more magical with every passing day. Stable Diffusion, Dall-E, and Midjourney will create an image based on your written description. ChatGPT will write a poem for kids that explains nuclear fusion, and when it gives me 8 stanzas and I only wanted 3, it will turn around and give me that.

Magic!

Lately, things in the world of generative AI are getting downright scary. Whether you think it’s scary good, or scary bad, is something I leave up to you.

I was reading an

Augie editor window

Each scene in the video is shown on a timeline at the bottom of the screen. Over on the left, you can access their free stock photo library, upload your own content, generate an image with Stable Diffusion (I tried it for the second scene), add text to the video, add music, and so on. When you’re happy, click “Download” and voila! You’ve got a video.

Here’s what 5 minutes of ‘work’ got me. It’s a short video, so take a moment to watch it. And remember, AI wrote the script, spoke the words, created individual scenes, selected the images and video clips, with only slight modifications by me, mostly because I wanted to see how the tool worked.

Now, it’s not brilliant, but if I had spent more than 5 minutes, it might have actually been quite good.

As we look around, we find ourselves in the midst of an extraordinary technological revolution, one that brings with it a sense of awe and, yes, a flicker of trepidation. We stand on the precipice of a new era, where advancements in generative AI technology, like the astounding capabilities of Augie, Stable Diffusion, ChatGPT, etc, are transforming how we create and communicate.

Let’s take a moment to appreciate the magic (yes, I know I keep using that word) that unfolds when we invest a few minutes into crafting an idea or a story. The result is a visually stunning video that has the power to captivate viewers, engaging them in ways previously unimaginable. Well, okay, mine might not have been all that visually stunning, but it could be.

However, as we marvel at these wonders, I’d be remiss if I didn’t acknowledge the disruptive nature of such technological leaps. The power this technology holds can be both inspiring and daunting. There’s plenty of controversy to go around, not to mention questions of fair use, copyright, consent, and plenty of legal questions yet to be answered. As with any revolutionary tool, there are valid concerns that emerge alongside its potential. It’s a delicate balance to strike — harnessing the benefits while mitigating the risks.

In the meantime, however, there’s a lot of fun to be had, and some really cool things to play with and to explore. So, while I don’t want to ignore the concerns, I want to emphasize just how utterly ridiculously amazingly fantastically magical this time we’re living in truly is.

Expecto Videoum!

Until next time.. Don’t forget to subscribe, share with others, comment, and all that stuff!

Leave a Comment Cancel Reply