Why choose it
- Text and single-image generation
- Optional native audio
- Up to 20 seconds at 1080p
Original model creator
Black Forest Labs
FLUX 3
Black Forest Labs’ frontier video model for text or single-image motion, optional native audio, and clips up to 20 seconds.
Official sampleSourced output
Official sample · Results vary by prompt and settings
Inspect the sample frame.
Direct answer
When should you use FLUX 3?
FLUX 3 is the catalog choice when you want Black Forest Labs motion from a prompt or a still. Generate 5–20 seconds at 720p or 1080p with optional native audio. It does not offer first/last frames or multi-image references, so keep the brief to one shot and one starting image.
Best for
Natural motion from text or a product still, especially when optional audio and 20-second runtime matter.
Technical readout
The supported shot envelope.
- Duration
- 5–20 seconds
- Resolution
- 720p or 1080p
- Aspect ratio
- Ultrawide, landscape, portrait, and square formats including 2:1
- Audio
- Optional generated audio
What to consider
- First/last frames and reference packs are not available
- 1080p costs more per second than 720p
Prompt direction
How to prompt FLUX 3
Describe one continuous unbroken action, the camera’s relationship to the subject, and the sound that should travel with the shot.
Start a FLUX 3 promptQuestions, answered
FLUX 3 FAQ
What is FLUX 3 best for?
FLUX 3 is best for natural motion from a text prompt or a single still, especially when you want optional audio and a clip longer than 15 seconds.
Can FLUX 3 animate images?
Yes. Video Lab supports a starting image. First-to-last-frame direction and multi-image references are not available.
How long can FLUX 3 videos be?
The supported duration range is 5 to 20 seconds at 720p or 1080p.
Change the lens
Compare FLUX 3 with another model.
Official sample
GoogleOriginal model creatorVeo 3.1
A premium text-and-image video model for cinematic shots, guided frames, references, optional audio, and up to 4K output.See model
Official sample
ByteDanceOriginal model creatorSeedance 2.5
A next-generation text-and-image video model with native audio, 30-second shots, first/last frames, and deep reference control.See model
Independent testByteDanceOriginal model creatorSeedance 2.0
A flexible text-and-image model with first/last-frame direction, up to nine references, broad formats, and optional audio.See modelBlack Forest Labs lens selected
Direct your first FLUX 3 shot.
Write the prompt, choose supported controls, and see the exact credit quote before you generate.
Open FLUX 3 in Video Lab