Black Forest Labs / Video model

FLUX 3 Max

FLUX 3 post-trained for closer prompt adherence and better visual quality, with native audio and clips of up to 20 seconds.

Meet FLUX 3 Max

FLUX 3 Max is a post-trained version of Black Forest Labs' FLUX 3 video model. It sticks closer to what the prompt asks for and renders cleaner frames, and it runs with lower latency. It works from a prompt alone or from a start frame, with an optional end frame, over 5 to 20 seconds at 720p or 1080p.

It costs the same per second as FLUX 3 Standard. FLUX 3's cheaper Draft tier is still the place to test prompts before you commit.

Available in Advibly

Settings and estimated costs from Advibly's live model configuration.

Inputs
Text, Start frame, End frame
Durations
5s to 20s
Aspect ratios
9:16, 16:9, 4:3, 3:4, 1:1, 21:9, 2:1
Output options
720p, 1080p
Audio
Generated with the video, can be switched off
Estimated cost
$0.26 to $0.44 / secondOne credit costs $1. The range spans the cheapest and the most expensive settings this model offers; the composer shows the exact amount before you generate.0.26 to 0.44 credits / second

When to use it

Use Max when the clip has to match a written brief: specific actions, camera moves, and sound.

  • Final renders of a prompt you have already tested
  • Animating a designed opening frame toward a set ending
  • Cinematic clips with dialogue, ambience and sound effects

Things to keep in mind

No reference images. Use a start frame to fix the look of the subject.

1080p costs more than 720p, especially on longer clips.

Get more from your prompt

  1. 1.Write the action in order, with the camera's behaviour alongside it.
  2. 2.Short prompts get expanded by the model. Long, detailed prompts are kept close to how you wrote them.
  3. 3.Put spoken lines in quotes and name the ambient sound when audio is on.
  4. 4.Find the shot on FLUX 3 Draft, then render it here.

Common questions

What is FLUX 3 Max best used for?

FLUX 3 Max is particularly useful for final renders of a prompt you have already tested, animating a designed opening frame toward a set ending, cinematic clips with dialogue, ambience and sound effects. The right choice still depends on your input assets, delivery format, turnaround and credit budget.

What inputs does FLUX 3 Max support in Advibly?

FLUX 3 Max works from text, start frame and end frame. Advibly only shows the controls a model actually supports once it is selected, so you are never offered a combination it cannot render.

How many credits does FLUX 3 Max use?

The current estimate is 0.26 to 0.44 credits / second ($0.26 to $0.44 / second, at $1 per credit). The exact amount follows the options you pick, and Advibly shows it on the generate button before anything is charged.

Reviewed September 29, 2026 against Advibly's model configuration and Black Forest Labs's published material.

Developer source

Create with FLUX 3 Max

Open a new video workspace with this model selected.

Create with FLUX 3 Max
Back to video models