MiniMax (official)

@MiniMax_AI

Code: @MiniMaxAgent MiniMax Design: @Hailuo_AI API: platform.minimax.io Token Plan: platform.minimax.io/subscribe/toke…

San Francisco

minimax.io

Replies Reposts Media Articles

Pinned
MiniMax (official)
@MiniMax_AI
Jul 31
MiniMax H3: Omni-Reference, Commercial-Grade Generation, Unbeatable Cost Efficiency, Open Weights Your creative destiny, on your terms. Now Live at HailuoAI.video & MiniMax API.
MiniMax (official)
@MiniMax_AI
Jul 30
It's coming. @Hailuo_AI #MiniMaxH3
00:00
53
MiniMax (official)
@MiniMax_AI
Aug 30
It takes great taste and judgment to see what’s possible, and strong conviction & execution to actually make it happen @fal 🤝 @MiniMax_AI
Leanna Ren
@RenLeanna
Aug 29
Last week, my friend @BernieSu (3x Emmy winner) invited me to his private screening, my first time experiencing immersive film. It’s an unprecedented format & the frontier of what’s possible when AI + creativity come together. I kept saying the commercial and creative space this
12
MiniMax (official)
@MiniMax_AI
Aug 29
Some milestones move a leaderboard. A rare few change how you see the future. MiniMax H3 Max did both. We released MiniMax H3 as an open-weight model with the hope that the community would adapt it, challenge it, and take it further than we could alone. @fal did exactly that.
88
MiniMax (official)
@MiniMax_AI
Aug 27
A great deep dive from the @fal team on how they built H3 Max, combining post-training with a co-designed inference stack to improve prompt adherence, visual quality, and speed. We're proud to see MiniMax H3 serve as the foundation for this work. Congratulations to the team, and
fal
@fal
Aug 27
Yesterday, we launched H3 Max. We post-trained MiniMax H3 for stronger prompt adherence and visual quality, while co-designing the inference stack alongside it. As we pushed speed, we continuously tested for quality, only keeping optimizations that preserved the gains from
18
MiniMax (official)
@MiniMax_AI
Aug 27
Congrats to the fal team on MinMax-H3 Max - fantastic work! fal optimized the model for stronger real-world performance while co-designing the inference system around it to make sure faster than real-time is still possible. This required two capabilities that rarely sit under the
fal
@fal
Aug 26
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
28