Went to a Dallas Stars game tonight and got there pretty early. The team hadn’t even come out for warmups yet, so I figured, why not see if I could get Jess into a Stars game? Since I’ve already got her based in Dallas, it made sense. I took a quick picture from my seat down by the glass. There were a bunch of people standing around, so I figured I’d just replace one of them with Jess. I went online, found a picture of a girl wearing some Stars gear that looked like something Jess would actually wear, and used that to make a character sheet. Honestly, that was just easier than trying to mess around with the mannequin and build an outfit from scratch, especially since the Wi-Fi was pretty spotty. Then I gave it a really simple prompt. Basically, put Jess down by the glass posing for a picture. As I was thinking about it, I figured it’d be funny to have a hockey player skate by and smack the glass to scare the shit out of her. Ran a few versions and got some pretty different results. But the whole point was really just to see what it was like using ShortPulse on my phone while sitting at a hockey game. And it works! It’s actually pretty interesting what you can do with it. The interface takes a little getting used to, though. You can’t really see everything at once, so you’re scrolling around trying to get to your reference grid. Then, when you’re ready to prompt, you pretty much have to close everything down so you can actually see what you’re typing. And if you don’t tap the reference grid just right, it’ll kick you back to the home screen and you have to start over. That happened a few times. So there’s definitely some fumbling around involved, but I was just messing around anyway. I uploaded all the assets I used so you can see how I put it together. The video is a bit long but you can scroll through it to see how painful this is. I’m not completely sold on the videos themselves. I probably could’ve gotten better results with some more thoughtful prompting and using the chat to work through the shots. But that wasn’t really the point.

So I’m working my way back through the episodes and just got to Episode 10, where y’all are talking about what I was requesting. I think there was a little misunderstanding about what I was asking for. I don’t necessarily want a delay. I agree with Scotty, that sounds pretty awful. What I’m looking for is just some kind of visual feedback when I press a button. Something as simple as the button changing color or showing an active state so I know it registered my click. Kind of like haptic feedback on a phone, or even an audible click, although I know most websites don’t do that. Right now, you press the button and nothing appears to happen. Unless you happen to look over to the right and see things starting to work, you have no idea your click registered. So what ends up happening is I press the button two or three times when I only needed to press it once. That’s really all I’m asking for. Just some immediate feedback that says, “Yep, got it. I’m working on it.” Hopefully that clears things up a little bit.

So I might have gotten a little carried away with this one. 😂 I just finished a 12-and-a-half-minute YouTube video featuring AI robots, cinematic comedy scenes, recurring characters, and an AI sidekick named Tally who apparently exists just to insult me. And 100% of the AI-generated video footage was created using ShortPulse. No other AI video platforms. Just ShortPulse, ChatGPT, Final Cut Pro, and a ridiculous amount of back- and-forth. I wanted to share the process because I think there's a big difference between generating a cool AI clip and using AI video to tell an actual story. 👻 It started with a Ghostbusters joke. I was working on a project using ChatGPT and Claude together when I randomly thought: "Man... I'm crossing the streams." And then I started wondering why I thought of it that way. Why do we treat different AI tools like we have to choose one or the other? What happens when you combine their strengths with your own experience and creativity? That became the concept for the video. ChatGPT and Claude became two different robots. I became the idiot standing between them. And the whole thing turned into a ridiculous Ghostbusters-inspired production. 🎥 Step 1: Record the actual video first. I started by writing a tentative script and recording my talking-head footage. "Tentative" is doing some heavy lifting there because once the camera's rolling, I tend to go off-script. 😂 I brought everything into Final Cut Pro, trimmed the footage, and organized it into seven scenes. Each scene became its own little production. 🧠 Step 2: Use ChatGPT to plan the visual storytelling. This is probably the most useful trick I discovered. I'm using the regular $20/month ChatGPT plan. For each scene, I gave ChatGPT three things: - The rough-cut video. - Closed captions exported from Final Cut Pro, including timestamps. - My original tentative script. The script showed what I intended to say. The captions showed what I actually said and exactly when. And the video provided visual context.

As I was listening to the repeat of the latest call and y'all were discussing the 500 limit or whatever the limit is depending on your subscription was that it would be nice to at the top of just everything like the grid the you can just click on a button and say download all that would be my request even character sheets download my character sheet download whatever just have that availability so that if I just want a group of things altogether there it is

One thing I saw @Scotty Art do in one of his videos that saves me time is put my file name at the very beginning of my prompt. When I save, it uses the first part of my prompt. I don't know how many characters, but the first part of my prompt is my file name. I just delete everything after it. Now I have a nice, tidy file name. Easy breezy.