Fal.ai Releases FLUX 3 Max Video Model

Oct 19, 2026
FLUX 3 Max generates videos lasting 10 seconds in 10.95 seconds, according to Fal.ai's benchmarks. The model is available through the company's API.

In a press release, Fal.ai introduced FLUX 3 Max, an image to video generation model developed with Black Forest Labs. Fal.ai used post training, reinforcement learning and inference optimization to adapt the FLUX 3 foundation model.

FLUX 3 Max received an Elo rating of 1,139 across 4,868 votes in preliminary human preference evaluations on the Artificial Analysis Video Arena. In Fal.ai's benchmarks, it generated a video lasting 10 seconds in 10.95 seconds, compared with 277.80 seconds for Seedance 2.5 at the same reported Elo rating.

Compared with the original FLUX 3, the model increased its image to video Elo rating from 1,089 to 1,139 and reduced generation time from 126.44 seconds to 10.95 seconds. FLUX 3 Max is available through Fal.ai's API for text to video, image to video and keyframes to video generation, with a 75 percent discount for the first three weeks.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.