A year ago, LLMs could barely make a 3D sword.
Now you can make that game you’ve had in your head with GPT-6-Astra and fal.
I made this game in a very short time. If you want to play it or fork it and build on it:
Play:
Code:
Show more
Who in generative media (image/video/audio/3D/robotics) fields needs a shit ton of hoppers right now?
not in a few months/weeks etc. literally now. Hit me up in DMs.
another one
LOOK AT THIS CONSISTENCY!
I think H3 MAX can absolutely work as a rendering engine with the right prompting. I’ll share a post today showing how.
I might’ve found a way to make yesterday’s Blender to Real video ~5,000x faster (and better imo) lol.
I put the scene together with GPT-6 Astra and PATINA in about 30 minutes. But it had around 7 million polygons, so rendering took a while.
I split it into chunks across 8 GPUs and rendered it in about 30min. My estimate for an M4 Pro was around 40 hours. Obviously, I could’ve optimized the settings, but that’s for the version I posted yesterday.
Since then, I’ve been trying different prompts to get H3 Max to follow the Blender animation while making the buildings and materials actually look real. I think I finally got it.
The 30s video took about 30s to generate with H3 Max. Compared to that estimated 41h render, that’s roughly 5000x faster :)
The part I’m most excited about is how much control this gives me. GPT-6 Astra can build a detailed 3D prototype in minutes, and I can use Blender to set up the camera and movement however I want, then have H3 Max follow it.
Show more
Who misses driving a taxi in San Francisco?
I made this with GPT-6 Astra and @fal PATINA
GPT-6 Astra might be the best model I've seen for 3D intelligence and it becomes much more powerful with fal PATINA.
Your heart takes ~0.8s to beat once, and H3 Max Turbo can make a 5s video faster than that. 🫣🫣
Announcing H3 Max Turbo (preview)
H3 Max Turbo is a faster, more cost-efficient version of H3 Max.
It runs at 2x the speed at half the cost, while targeting the 97th percentile of the original H3 Max's quality on our evals (and still performing better than H3 and any other video model). At our promotional price, 768p video runs at $0.01 per second of output.
H3 Max Turbo keeps the prompt understanding, aesthetics, and overall quality of H3 Max while cutting generation time in half.
It’s available to try at a promotional price for the next two weeks. See what happens when video generation gets an order of magnitude faster and cheaper.
Show more
vh5tape - a worn-VHS look for MiniMax H3
I'm releasing my first MiniMax H3 Lora. This works great on standard MiniMax H3 and MiniMax H3 Max.
The model that created its own launch video. Love that.
Reference-to-Video is now live for MiniMax H3 Max on fal!
This is an early preview that can achieve up to RTF=1 (and with references around RTF=1.5) on 768p, and we aim to improve the speed by 2x while slashing costs during this week. Quality wise it delivers the same performance you come to expect from H3 Max.
Show more
That's exactly what I call
GENERATIVE MEDIA
Introducing H3 Max Live
Video generation is now faster than real time
An infinite broadcast where every frame is generated on the fly and every scene is directed by chat
Type !prompt and it's on screen in seconds
Show more
million-dollar idea: whoever makes the highest bid within 15 seconds gets their prompt played in the next scene.
Okay I built it!
🍰 Infinite Slop
An infinite and interactive AI generated live stream of slop that goes on forever and ever
Anything that you write in the chat is generated next and AI will try to connect it to the previous video so there's an actual sequence and story line
Idea by @marcantoinefon and @rehan_shei's original stream so I made it
It'd be very expensive to run this so @fal very generously sponsors this
They also fine-tuned the model that makes this possible for the first time, making Minimax H3 50x faster and as "Max" and it can now generate videos faster than you can watch them, very cool!
Let me know what you think!!!! 😊
Show more
Motion Prompt guide for @fal MiniMax H3 MAX is live! I added a bunch of examples too, so you can just copy the prompts and tweak them however you want.
More prompting guides for this model are coming soon.
Show more
Here it is! An incredibly fast model that’s unrivaled, especially when it comes to motion graphics.
AND YES!
This video was also made using this model!
I’ll be posting a @fal guide very soon to help you create the best videos with this model.
Show more
Introducing H3 Max, new post-trained video model by fal Research.
H3 Max ranks #1# for overall quality, prompt understanding, and aesthetics against leading video models, on both first-party and third-party independent evaluations while generating a 5-second 720p video under 3 seconds.
H3 Max is 50% off for the next week, making it the highest quality, fastest and cheapest model for overall video generation tasks.
Show more
Maybe it’s because I used to work as a motion designer way back, but I’m having way too much fun with this model.
and yes, I didn't make a single edit to this.
Guess I can just tweet like this now.
this might be a bit of a bold take, but I generated a bunch of videos with both Seedance 2.5 and FLUX.3, and aside from RAW video quality, FLUX.3 feels way smarter and just better overall.
I think it’s time for agents to start making art too. wdyt?
the open-source era is coming back. be ready
