Motion study with audio
“A ceramicist shapes a spinning bowl on a pottery wheel in a sunlit studio, wet clay glistening, the camera slowly circling as the wheel hums and tools clink.”
video model
Generate AI video with audio using FLUX 3
FLUX 3 is Black Forest Labs’ first video model, generating 5 to 20 second clips with natively synchronized audio from a text prompt or a start image, in seven aspect ratios up to 2:1.
$0.17 / second at provider cost for members — see the full price breakdown
What you need to start
Describe the shot, the motion, and the sound — or add a start image to animate.
Loading...
Original results
FLUX 3 examples made in Made
These examples use media produced for Made. Prompts are included when the production record allows them.
Image-to-video
“Bring the studio to life: dust drifts through the window light, the camera pushes in slowly, quiet room tone with the wheel starting to spin.”
Creative scene
“Rain begins over a neon-lit night market, umbrellas opening one by one, sizzling food carts and distant chatter, a slow dolly forward through the crowd.”
Start-frame control
“Use this image as the opening composition.”
Scene brief
“Set the scene as a still before describing its motion and sound.”
Composition brief
“Plan the shot as a still, then hand the motion to the model.”
Where FLUX 3 fits best
Best uses
- Clips up to 20 seconds with synchronized sound design
- Cinematic camera language from the maker of the FLUX image models
- Animating a still image with matching ambient audio
- Wide formats like 21:9 and 2:1 for filmic frames
Limits to know
- Made pins output to 720p, the tier it bills at provider cost; 1080p masters need the provider’s higher tier or an upscale pass.
- Duration must be set explicitly — the provider’s “auto” length is not exposed, so Made can quote the exact cost before generation.
Specifications in Made
These are the controls exposed by Made, which may be narrower than a provider’s full API.
- Aspect ratios
- 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16
- Resolution
- 720p (Made pins the billed tier)
- Duration
- 5–20 seconds
- Output formats
- MP4 with audio
- Reference images
- 1
- Processing
- Scales with duration; progress appears in the generation view.
How to use FLUX 3 in Made
- 1
Write the shot and its sound
Describe the subject, motion, camera path, and the audio the clip should carry — sound is generated natively.
- 2
Add a start image if needed
Upload a still to animate; FLUX 3 keeps its composition and adds matching motion and audio.
- 3
Choose format and length
Pick one of seven aspect ratios and any duration from 5 to 20 seconds.
- 4
Review and refine
Check motion, audio sync, and continuity, then adjust one instruction at a time.
Compare relevant models
video
Happy Horse 1.1
Happy Horse 1.1 is Alibaba’s flagship video model — a long-running #1 on the Artificial Analysis Video Arena — generating 3 to 15 second clips at 1080p with native audio and multilingual lip-sync.
Explore model →video
Kling 3 Pro
Kling 3 Pro is the benchmark tier of Kling AI’s third-generation video model, generating 3 to 15 second clips with audio on by default and the cinematic motion the Kling line is known for.
Explore model →video
Seedance 2.5
Seedance 2.5 is ByteDance’s newest video model in Made, generating clips up to 30 seconds in a single pass with native audio at 480p to 1080p — the longest single-shot ceiling in the Made library.
Explore model →Continue with a related tool
AI Video Generator
Turn any image into a captivating video. Upload a photo, describe the motion you want, and watch AI bring it to life with realistic movement, cinematic camera work, and professional quality.
Open tool →AI Image Generator
Create scroll-stopping product photos and marketing visuals in seconds. Describe your shot, pick your style, and get professional images ready for your store, social feed, or ad campaign.
Open tool →It is Black Forest Labs’ first video model, launched in July 2026, generating clips up to 20 seconds with natively synchronized audio from text or a start image.