FLUX 3 Max
FLUX 3 Max is a video model post-trained by fal Research in collaboration with Black Forest Labs. It starts from FLUX 3 and is served by fal. Its release supports text, image and keyframe inputs.
Model details
The release combines further model training with inference optimization. It is a distinct served model rather than an alternative name for BFL's original flux-3-video endpoint. The checked page lists a public playground and API model routes.FLUX 3 Max official documentation
Practical use
Practical guidance. Treat Max as a separate provider integration even though it shares FLUX ancestry. Compare outputs using the same brief and input frames. Measure end-to-end delivery time in your application; vendor generation benchmarks do not include every network or queue condition.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API, Provider product |
| Model identifiers | FLUX 3 Max by fal Research |
| Access terms | Proprietary hosted service; no public weights verified.FLUX 3 Max official documentation |
| Service operator | falFLUX 3 Max official documentation |
| Current advertised output | Up to 15 seconds at 720p with sound.FLUX 3 Max official documentation |
Related models
- FLUX 3 Video
Black Forest Labs · FLUX 3
Video generation model with synchronized audio, timed image keyframes and existing-video input.
Launch date not confirmedPreviewAPI · Provider product