Nav Lotay

This one is WEEKS overdue! Pt.3 of The Bounty Saga. In this episode, we're introduced to HYPERMIND - the Astronaut character (and the name of my co). Bounty understands what his brother Grogan really wants him to get out of the asteroid mission he sent him on in Ep1, and Hypermind offers a helping hand. Production Notes: Made with @Higgsfield, @Freepik, @suno , @FlowbyGoogle , @Kling_ai & cut on @Adobe Copyright and IP belongs to me, @NavLotay

@zanehkoch @bryan_johnson worth looking into for ur research (if you see this)

for a while i've had a slight fear that the bluetooth from my airpods could be frying my brain this weekend i pulled the raw data from a $30m government study of 1,679 mice blasted with cell phone radiation and reanalyzed it what i found was...not what I expected? 🧵

Controversial take but I don’t think the current SotA is ready for features. For verticals and short form stuff like I’m doing with Bounty Saga and likes of @neuralviz is doing - 100% ready. But for features, anyone who’s worked on one can attest - there’s a shit load more than anyone thinks that goes into it, that you just don’t see until you work on one. You’ll need art directors and continuity supervisors helping with this which throws the budget up and up. Plus the credit burn as you rightly pointed out is insane. We’ll get there, maybe some more progress this year

Spent about $1000 in credits on Seedance 2.0 over the last few weeks,and here are a few thoughts: First, the main thing that strikes me using a state-of-the-art model from this new generation is how hard it still is to scale beyond short form. Getting great animation is fast. Getting multi-cut sequences that make sense is possible. Consistency with Omnireference is actually very good. But the moment you move into real narrative work, things change. Multi-character exchanges, long sequences, maintaining visual continuity across shots, keeping tone, pacing, and staging consistent… it’s not impossible, but it is still a lot of work. And with generation costing somewhere between $2 and $7 per ~15 seconds, it adds up very quickly. As models improve, producing good looking short content is becoming trivial. Building something that holds together as a story is still not. Continue Video in Seedance is clearly trying to address part of this, but in my case it has been broken for the last couple of weeks, so none of my longer attempts would go through. In theory, you could imagine a small team of 5–10 people generating all day from the same storyboard, using a shared visual reference as a single source of truth. That alone shows how close we are to something that starts looking like a real production pipeline. But we are not fully there yet. Right now it still feels like we can touch the future with the tip of our fingers, while at the same time struggling to precisely steer a model using mostly words, references, and iterations when the narrative becomes complex. Short clips are easy. Worldbuilding is not. And storytelling is still the hardest part.

@jasonzada This, was great

The Heist 3. Set in Miami's Little Havana in the 1980s, this epic adventure was fun to create, as was the soundtrack coming out soon. Looking back at the original The Heist film, which I did in December 2024 when Veo2 came out, the quality of The Heist 3 (one year and three months later) is mind-blowing. I hope you enjoy the next chapter of The Heist storyworld!

@thepatwalls @HubSpot Congratulations on the success. Been watching for a couple years and inspiring to see how far you’ve gone with it. Laser focus ftw

8 years ago, I started a side project inside of a tiny Starbucks. Today, Starter Story is being acquired by @HubSpot. Here’s how it happened.

Part 4 soon come. You can also watch on YouTube youtu.be/Gs-iRXFRO2Y

This one is WEEKS overdue! Pt.3 of The Bounty Saga. In this episode, we're introduced to HYPERMIND - the Astronaut character (and the name of my co). Bounty understands what his brother Grogan really wants him to get out of the asteroid mission he sent him on in Ep1, and Hypermind offers a helping hand. Production Notes: Made with @Higgsfield, @Freepik, @suno , @FlowbyGoogle , @Kling_ai & cut on @Adobe Copyright and IP belongs to me, @NavLotay

@Casey @samsheffer i don't know how you did it, i can't even get into a daily routine with ai films..

@samsheffer me too

miss the days when @Casey uploaded every day

@Diesol Yeah, plain and simple this. I know a few art directors now using it to build their vision to life their way & tell their own stories.

See. This is what people fail to understand. There are artists out there who have been working on craft and taste for decades and due to unforeseen circumstances had their projects fall apart. AI was never scary to me because I knew it could never be me. I saw it as a tool that could help me bring my ideas to life. And it is paying dividends.

This. All of this.

🤌

@Diesol Uhm, hello 👋- Bounty Saga as a spin off from Homeward... Same universe, characters... youtube.com/watch?v=nuisUE…

Gloves are off. A solo creator will create a franchise. Quote me

@koh_terai @ycombinator Hey Koh, I’ve submitted my details through the typeform. Be good to connect - take a look at my profile / credits & YT

Thank you @ycombinator 🙏 If you’re a filmmaker or studio taking AI video seriously, we’re onboarding now.

@anothercohen 🤣

So we added OpenClaw to the company Slack and it's going about as well as you'd expect

I feel Kling just has better adherence and output atm. The few times I’ve used 4.5 left me disappointed and just burning credits, but I’m sure with more testing I’ll figure out the write prompt to get what I want out of it. But for production and deadlines it’s not quite there yet imo. Particularly without audio, feel that’s a bare necessity now

I just put Kling 2.6 head-to-head with the newly released Runway Gen-4.5 (image to video) Kling 2.6 videos and images made with Nano Banana Pro inside @LeonardoAi I included 9 examples with full prompts 🧵👇 Which model surprised you the most? I’m reading the comments

@tomnestorcomic 🤣

Wow 8 inches of snow

@jforozcop @runwayml Looks good man, great job

“The Grizzlies” So excited to share my most recent short film, produced by @runwayml I put so much love into this! #thegrizzlies #generativefilmmaking #madewithrunway

@mattworkman Straight outta a fantasy adventure film!

OK 4K gen AI images go hard

@0xInk_ This is cool, I can imagine this cycle transforming into a quadpedle bot too

Adventure Time if Jake wasn’t a dog but a flying motorcycle spot the Salomon sneakers on Finn

@vardtaken @netflix Thx for the feedback! Yeh the opening continues from the end of Ep1 and it's just building up slowly, so it probs is jarring. Ep1- youtube.com/watch?v=km9eZX…

@NavLotay @netflix The 1:30 scene was great and made me want to watch it. I was almost skipping watching the clip during the first scene tbh. It didn't hook me but that scene did.

This 3 minute episode cost me $500 and 2 days to make cause I kept burning through credits and I bet you can't do it @netflix Right, thats the ragebait out the way - here's Ep2 of The Bounty Saga! I'm vibe-making this as and when I get downtime just for bants, which is to say I'm not adhering to a script here per se, just kind of seeing where the story goes and make it as fun as I can. It's also helping me put some ideas and lessons I'm learning into practical use. The focus on this episosde was more sound design. Let's see if you notice the difference! Hope you enjoy watching as much as I enjoyed making :) Credit to @higgsfield_ai @freepik @Kling_ai @FlowbyGoogle @suno @elevenlabs for the tools that can make this happen. Oh, and @Adobe !

We’re at @sundancefest previewing our new animated short, "Dear Upstairs Neighbors" 📽️ In creating this film, our @GoogleDeepMind team of Pixar alumni, an Academy Award winner, researchers, and engineers designed new AI capabilities specifically for filmmakers. These tools gave director Connie He a new level of artistic control, allowing her to tell a story she's always wanted to share.