Pinned Tweet
#1 in Speed, by an order of magnitude
#1 in Quality, by a significant margin
#1 in Cost, with more cost optimizations coming soon
#1 in Quality, by a significant margin
#1 in Cost, with more cost optimizations coming soon
MiniMax H3 Max by @fal takes the #1 spot on Video Editing by Design Arena with an Elo of 1373.
The model ranks ahead of MiniMax H3 by @minimax and @GoogleDeepMind's Gemini Omni Flash and Gemini Omni Flash 1.1. It's also in a league of its own on the Pareto frontier for Preference vs Price.
Congratulations to the @fal team on post-training an exceptional model.
14
4
111
12,215
If anyone really needs a few thousand Hoppers at these prices, I have a bunch of extra 😆😆😆😆
The entire term structure of @nvidia H100 GPU rental rates continues to rise.
2
4
25
2,409
batuhan the fal guy retweeted
Paging all infra engineers:
Our team @a16z is hosting a hangout tonight with our friends at @fal, @bfl_ai, @ElevenLabs, and @krea_ai.
Expect pizza, beer, and some awesome convos around how to build + scale AI systems.
luma.com/fal-6m0z
Our team @a16z is hosting a hangout tonight with our friends at @fal, @bfl_ai, @ElevenLabs, and @krea_ai.
Expect pizza, beer, and some awesome convos around how to build + scale AI systems.
luma.com/fal-6m0z
9
11
102
9,585
batuhan the fal guy retweeted
This new video model from @fal x @bfl_ai is remarkable.
All of these clips were text-to-video, generated in <10 seconds (22x faster than Seedance 2.5 🤯).
AI video no longer needs to be painfully slow and expensive. We're entering a new era!
All of these clips were text-to-video, generated in <10 seconds (22x faster than Seedance 2.5 🤯).
AI video no longer needs to be painfully slow and expensive. We're entering a new era!
Introducing FLUX 3 Max, the latest post-trained video model from fal Research in partnership with @bfl_ai.
FLUX 3 Max is tied for #1 in image-to-video quality on independent third-party benchmarks, generating a 10-second, 720/768p video in ~12 seconds.
For the next three weeks, making it the most affordable frontier video model at its quality level.
38
36
494
34,600
batuhan the fal guy retweeted
Can’t stop won’t stop. @fal’s post training team makes other models feel unusable. We’ll see more and more labs partner with fal to keep pace.
Media labs create a killer base model - fal takes care of the rest. Congrats @bfl_ai and @fal!
Media labs create a killer base model - fal takes care of the rest. Congrats @bfl_ai and @fal!
Introducing FLUX 3 Max, the latest post-trained video model from fal Research in partnership with @bfl_ai.
FLUX 3 Max is tied for #1 in image-to-video quality on independent third-party benchmarks, generating a 10-second, 720/768p video in ~12 seconds.
For the next three weeks, making it the most affordable frontier video model at its quality level.
2
1
21
822
batuhan the fal guy retweeted
Introducing FLUX 3 Max.
Fastest in the west. Fast enough to try anything. And everything.
Generate a 10-second video in 12 seconds.
Tied for #1 in image-to-video. 22× faster than Seedance 2.5 at the same quality.
FLUX 3 is a model designed for customization. @fal adapted and FLUX 3 Max.
Fastest in the west. Fast enough to try anything. And everything.
Generate a 10-second video in 12 seconds.
Tied for #1 in image-to-video. 22× faster than Seedance 2.5 at the same quality.
FLUX 3 is a model designed for customization. @fal adapted and FLUX 3 Max.
97
107
997
77,438
batuhan the fal guy retweeted
so fast 🔥
Introducing FLUX 3 Max, the latest post-trained video model from fal Research in partnership with @bfl_ai.
FLUX 3 Max is tied for #1 in image-to-video quality on independent third-party benchmarks, generating a 10-second, 720/768p video in ~12 seconds.
For the next three weeks, making it the most affordable frontier video model at its quality level.
4
9
93
4,139
This is the culmination of 2 weeks of sleepless nights from fal’s Research & Performance teams: taking an extremely powerful base model, improving its quality beyond the base itself, and increasing its speed by 10x (literally).
We present to you the fastest model in the west 🤠
We present to you the fastest model in the west 🤠
Introducing FLUX 3 Max, the latest post-trained video model from fal Research in partnership with @bfl_ai.
FLUX 3 Max is tied for #1 in image-to-video quality on independent third-party benchmarks, generating a 10-second, 720/768p video in ~12 seconds.
For the next three weeks, making it the most affordable frontier video model at its quality level.
22
17
155
9,566
batuhan the fal guy retweeted
New work: @fal Worlds visual brand identity and interaction design
Our foray into the realm of World models. Infinite possibilities.
We wanted to craft an identity around the different ways people interact with this technology, the personas they take on, and the many forms Are you a wanderer, a creator, an explorer, a dungeon master, a cinematographer?
Our foray into the realm of World models. Infinite possibilities.
We wanted to craft an identity around the different ways people interact with this technology, the personas they take on, and the many forms Are you a wanderer, a creator, an explorer, a dungeon master, a cinematographer?
34
10
318
14,751
batuhan the fal guy retweeted
Introducing fal Worlds.
A new way to create and interact with AI-generated worlds in real time.
Build characters, explore environments, direct scenes, and watch worlds respond to your actions as they unfold.
Get hands-on with the latest frontier world models, including LingBot and more.
A new way to create and interact with AI-generated worlds in real time.
Build characters, explore environments, direct scenes, and watch worlds respond to your actions as they unfold.
Get hands-on with the latest frontier world models, including LingBot and more.
13
68
496
39,348
Looking for colo space (and OK for subleasing etc) in Santa Clara / Bay Area. OK for anything above 250 kW.
12
3
54
6,248
