March 3, 2026
By: Stephen Toback
We've had conversations for sometime to see if we should have a "Duke voice" to use for official voice over production using tools like Elevenlabs. There are still many discussions to have if this is in fact something we should...
Read the full post »
February 27, 2026
By: Stephen Toback
In academic video production, my primary tool has always been creating video—2D and linear. However, my ongoing testing with organic chemistry visualizations pushed me to try a different approach. After receiving some excellent feedback, I tried SVG (and ultimately WebGL)...
Read the full post »
February 23, 2026
By: Stephen Toback
What began as a simple experiment turned into a full benchmarking session. I found a sepia tone photograph of my father-in-law from the 1950s. I wanted to see what it might look like in color, so I started uploading it...
Read the full post »
By: Stephen Toback
The transition from Gemini 3.0 to Gemini 3.1 Pro isn't just a incremental update; for those of us involved in media technology and digital storytelling, it represents a fundamental shift in how AI perceives and constructs visual logic. We are...
Read the full post »
February 17, 2026
By: Stephen Toback
As many of you know, I’ve been deep in the trenches of testing AI video creation for academic projects at Duke University. My "litmus test" has always been trying to accurately animate molecular bonding—a project that dates back to the...
Read the full post »
February 10, 2026
By: Stephen Toback
On of my colleagues reached out to me today looking to create some animation for their training decks. I'm thinking about some ideas to add animation so I did a quick test for Google Veo 3 in Google Flow. I...
Read the full post »
By: Stephen Toback
We’ve all seen it: you ask an AI to generate a scientific diagram, and there, buried in the pixels, is a faint, ghostly watermark. Usually, we assume the AI is just mimicking "professional" vibes. But a recent experiment reveals something...
Read the full post »
February 5, 2026
By: Stephen Toback
I tested using a video of myself typing on the keyboard to map those movements to a video. What's crazy and cool but still random, is that it left my classical guitar in the frame. I think the "emotion" mapped...
Read the full post »
January 26, 2026
By: Stephen Toback
Luma Labs demonstrates how short video clips can be transformed into detailed, navigable 3D scenes using AI-driven capture techniques. Instead of traditional modeling or depth sensors, the process relies on standard video, then reconstructs geometry, lighting, and perspective into a...
Read the full post »
November 26, 2025
By: Stephen Toback
What started as a test prompt from Nick Janes to help doing some Nano Banana Pro 3 testing, ended up with an interesting video. You can read more information about how I used reference videos to create a series of...
Read the full post »
