fal Releases FLUX 3 Max Video Model, Generating a 10-Second Video Takes 12.45 Seconds
fal, in partnership with bfl_ai, released the post-trained video model FLUX 3 Max, which takes 12.45 seconds to generate a 10-second video, compared with 277.8 seconds for Seedance 2.5; the two share an Elo score of 1,139 on third-party benchmark evaluations. The model is tied for first place in image-to-video quality on an independent third-party benchmark, and can generate 10-second, 720/768p videos in about 12 seconds. fal said FLUX 3 Max will be 75% off for the next three weeks.
Why read this
SelectedAI score 75
The original text provides comparison data on generation speed and third-party Elo, allowing readers to judge the trade-off between speed and quality for the video model.
Topics
View original postIntroducing 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, FLUX 3 Max is 75% off, making it the most affordable frontier video model at its quality level.
View original
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, FLUX 3 Max is 75% off, making it the most affordable frontier video model at its quality level.
Body
FLUX 3 Max, our latest post-trained model, generates a 10-second video in just 12.45 seconds, compared to 277.8 seconds for Seedance 2.5, while achieving the same Elo score of 1,139 on third-party benchmark evaluations.
Read how we pushed the frontier of speed and quality through post-training and inference optimization: https://t.co/JBoRMfIkeP