Black Forest Labs · video

FLUX 3 Max Video

FLUX 3 Max: reasoning before rendering for complex scenes, up to 20 seconds at 1080p.

Text to videoImage to videoStart and end frameNative audio
Length
5 to 20 s
Resolution
720p, 1080p
Aspect ratio
16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 2:1
References
Up to 2 image files

Opens the Studio with FLUX 3 Max Video and your prompt. You see the price before anything runs.

About FLUX 3 Max Video

FLUX 3 Max Video is the Max variant of the FLUX 3 video model from Black Forest Labs, priced at $0.43 per second. It runs as text to video, image to video and start and end frame, with audio, from 5 seconds to 20 seconds, at 720p and 1080p.

The difference is in how it works rather than in the controls: it spends effort reasoning about the prompt before it renders. A typical generation takes about 4 min, against about 3 min for FLUX 3 Video.

Good for

  • Complex scenes where the prompt has many parts, since the model reasons about the prompt before rendering

Getting good results

  1. With the shape on automatic, text prompts come out landscape and image prompts follow the first image, according to the provider.
  2. Allow more time than FLUX 3 Video, since reasoning comes first; the provider notes that more reasoning means slower generation.

FLUX 3 Max Video questions

How does it compare with FLUX 3 Video?

It is a post-trained FLUX 3 variant the provider tuned for prompt adherence and visual quality. It stops at 1080p, where FLUX 3 Video goes to 4K; at the resolutions they share, the price is the same: $3.63 for a default clip at 1080p.

Other video models

AI video generator