In week 1 of animating a 10-minute short in a month, We tackle 88 mocap shots—while life gets in the way.

We are making progress and also having to pivot on a dime. 

We've managed to get about 63 of our 88 mocaps captured. Now we have to figure out how to get our gloves fixed while we make progress on the scenes we do have.

This is happening! We're not stopping! This project will not break us! 

Subscribe to the youtube channel if you haven't already. We're aiming to make this production vlog thing a series. 

We're pivoting away from AI-Trailers and diving headfirst into something we've been wanting to do for a while. It's also something we've been terrified to do for a while. 

We're going to produce a proof-of-concept short film for our next project.

Monster Sponsor is the "code name" for this project so far. We'll come up with a better title for it later. We did a world-building pitch trailer a few months back, and it placed in the Top 25 in the Project Odyssey Competition. 

This project is going to dive deeper into the world, follow some interesting characters, and really put our workflows to the test.

Now that we've tackled the "Flicker Problem" we're going to start really putting our pipeline to a stress test. We know how to do a lot of the work in segments, but what does it really take to tackle a full scale 10 minute piece with multiple characters, actual dialogue scenes, and major locations? 

Come along for the ride and watch our Daily Void series. We'll be posting every week on our youtube channel updating how things are going, what we learned, and any tips and tricks we learned along the way. 

Alright, 

If you've been following our little journey here on the internet, you'd know that we've been tinkering with UE5 + AI workflows for the last few years. 

Why, you ask? 

Well, there's a particular game-engine stink that really messes with the exciting adventure of animating in UE5. We figured an AI "filter" pass would help with that. 

Problem? There's a very slight, but very obvious flicker to the frame. Or at least... there as been. 

Up until this week our workflow entailed exporting our UE5 animations as frames. We would then run those frames through a batched upscale of Stable Diffusion using the prompt, "Cinematic Film Still" with a denoise of 0.8. We would then layer that AI pass ontop of our UE5 frames and find a nice middle ground that didn't completely destroy our eyeballs. 

The problem, of course, was there was still that constant flicker.

While we grew to find it endearing for our various screen tests, we knew that this wasn't where we wanted to be when we started producing longer short films and webseries. 

Solution? 

Wait.... wait for the technology to catch up. 

And this week my friends...we think we figured out a solution. 

WAN2.1 + WanFUN + WanVACE..... 

We gave ourselves 3 days to sort out whether or not this was a viable approach to our frame 2 frame workflow and we are happy to report that YES.....yes it is. 

Special shout-out to GoshniiAI and MDMZ for their incredible tutorials that helped us get there. 

The secret ingredient we needed to add to really lock in the frame-to-frame aspect of our tests was to add a Pyracanny to the workflows. 

And BAM, we've got a fun adventure coming as we develop our first 10-minute short film. It's our Proof of Concept for the "Monster Sponsor" project we've been developing these last few months.

We are looking forward to implementing this technique in the coming week.

Stay tuned. 

PS: Been watching some of Matt Hallet Visual's work in the VACE space and his tips are also pretty helpful in understanding whats going on under the hood. 

We've been tinkering with some new poster ideas for Astral Annie, Monster Sponsor, and Kung-Fu Kittens. 

 I hadn't realized how far behind we fell on updating the early ones still running wild around here.

So... let's get on it, huh?

We used ChatGPT to help generate some of these newer versions. We uploaded the old posters and a few frames from the pitch videos we've been producing over the last four months.

A few decent variations popped out right away.  ChatGPT did a great first pass and we did some cleanup work in Photoshop to keep it on brand.

We're still figuring out the final "looks" for these projects, so these aren't exactly what the end products will be. But exercises like this are super useful for shaping the vibe and exploring early packaging ideas.

Since we’re kicking off the screenwriting phase for a few of these, hopefully, these rough drafts will inspire even cooler cover concepts down the road.

Using AI to previs these early drafts has definitely been a game changer and, honestly, kind of fun.

✨ Take a peek! Tell us:

• Are there any you're vibing with?

• Got any wild ideas we should try next?

• Should we add more werewolves? (Always more werewolves.)

Hey Voidsters,

We just released a brand new Survivors Don’t Die video, and we’d love for you to check it out!

In this short vlog-style film, Yuki stumbles across an old camera and takes you on a tour of the crew’s zombie survival bunker. But this isn’t just a story drop—it’s also an experiment in pushing Unreal Engine’s Metahumans to the next level.

We’ve been testing an AI overlay pass to make the Metahumans look more photo-realistic—especially in the eyes, skin, hair, and teeth. Instead of the usual video game texture, we’re aiming for something that blends seamlessly with live-action visuals.

We’d love to hear your thoughts! Does this technique make our characters feel more real? Let us know in the comments.

Stay tuned—more films are coming next week!

Thanks for being part of this journey!

Amber & J-Wall

We just made a wild new film about our cats… but in an alternate reality where they are Kung & Fu, two mischievous little warriors. 🐱⚔️

This is just an interview video—a way for us to get to know these characters while also figuring out how the hell to make animals talk using AI video tools. 🤯 Spoiler: It was chaotic, hilarious, and we learned a lot about working with AI animals.

🐾 No real animals were harmed in the making of this movie—just our patience. 😂

Check it out, let us know what you think, and tell us if you’d watch a full Kung & Fu adventure! 👀🔥

It's Friday, y'all! This means its time for another pitch from the Blitz!

This piece is a scene test for a project we're code-naming Astral Annie, about a girl who comes into her psychic abilities as she moves to a new town with her military family.

While the initial project will have Annie in the 14-15 age range, this was a backstory scene I wrote years ago when this project was a middle-grade book. It’s cute, and lighthearted, and introduces one of Annie's best friends—10-year-old Otis, a ghost she met when she was 5.

This pitch allowed us to test what it would take to pull off a single scene in a single location. And let me tell you, it was harder than it sounds.

Fighting the AI for consistency was a chore.

But here are a few tips we learned along the way:

1. Script with animatics - Use AI images with a scratch track of audio first. Read your screenplay aloud and make sure it hits all the right beats. Our initial script fell really short and didn't build up too much of anything. Like amateurs, we jumped ahead to running AI animations, hoping it would “fix” the bad writing. Spoiler alert—it didn’t. lol
   
   
2. Talking Heads Only Needs 2 Angles - We got a little too fancy with our camera angles early on, which created a lot of issues with AI. Keeping character consistency was tough when cutting back and forth. Even though we had character LoRAs for both kids, the starting image angle with Minimax really affected how they looked in the final product. What worked? Sticking to one angle for each kid and then running them through Minimax for different emotional movements.
   
   
3. Live Portrait has a "Retargeter" - Use it - When pulling Minimax movement clips into Live Portrait, always close their mouths with the retargeter. This makes the final lip-sync process look way better.
   
   
4. Driver Video Tips - Jayson discovered that using a slightly lower angle for your driver video captured mouth movement more accurately. We tested with the head mount, but it was too wiggly and messed up the AI performance. A small tripod and flat lighting worked best. Also, try not to move your head too much while capturing—it causes weird artifacts along the edges.

Surprisingly, last week’s trailer was way easier than this scene. Character consistency across different locations has more leeway than cutting back and forth in the same scene.

So... maybe trailers are actually easier with AI than full dialogue scenes right now? More tests will make that clear, I think.

The tools are definitely improving, so who knows where this tech/workflow will lead. We're just excited and grateful to explore even more of it in the future.

Created, Written, & Performed by; Amber & Jwall
Audio: Elevenlabs Voice2Voice & SoundFx | FreeSounds
Music: Adobe Stock
Images: Flux ComfyUI Studio
Ai Animation: Minimax Hailuo
Face: LivePortrait w/ Pinokio
Upscale: WinxvideoAI

Thanks for being part of our creative journey—your feedback and support mean the world! Let us know what you think, and drop any questions about the project below.

🚀 Stay tuned for more pitch vids next week!

🚀 The 2025 Pitch Blitz is Here! 🚀

2022 – We decided to publish screenplays as books. (Because Hollywood wasn’t calling, so we called ourselves.)

2023 – We dove headfirst into character design and AI. (Turns out, robots can be useful beyond world domination.)

2024 – We learned how to animate in Unreal Engine 5 with Survivors Don’t Die. (And yes, it was as complicated as it sounds.)

2025? – Oh, it’s gonna be wild. Introducing... The 2025 Pitch Blitz! 🎉

What the Heck is a Pitch Blitz?

Glad you asked. It's where we throw a brand-new idea at you every single week—through micro-content and mini projects—because why not?

These pitches will help us dive into new worlds, meet new characters, and experiment with storytelling styles.

We’ve been hoarding these ideas for years, and now that we've harnessed the skills necessary to get them out, we’re making them a reality.

No more "someday"—the time is now.

What’s in It for You?

In short—more content, more often.

You'll get a front-row seat to all our wild ideas and the chance to tell us what’s hot and what’s... not.

Our goal? To get each of these ideas into a Screenplay Book by year’s end—just like Survivors Don’t Die.

But here’s the deal: If a pitch doesn’t spark joy (or terror, or excitement—whatever floats your boat), we’ll try other ways to pitch it. But if those don't hit shelf them b**ches and move onto the next.  

No need to waste anyone’s time on something that doesn’t hit.

How Can You Help?

Easy—TALK TO US.

As we roll out new pitches, tell us what you loved, what made you cringe, and which ideas deserve to be fast-tracked.

Your feedback guides our creative chaos and helps us zero in on what really excites you.

More comments = better stories = a world where everyone wins.

So, buckle up, because 2025 is about to be non-stop storytelling madness.

Ready to help us make something epic?

Stay tuned!

Can't wait? Here's a sneak peek at whats to come!