Flux 3 is the next multimodal model associated with Black Forest Labs. Community coverage describes it as an omni model for image, video, audio, and action — aiming for stronger control, realism, and world understanding in one system.

Is generation free on this site?

New accounts get 1 free 720p video (120 credits). After that, generation uses credits: 120 for 720p/1080p and 180 for 4K. Yearly plans give the best value, then monthly, then one-time packs. Failed jobs are refunded.

Can outputs be used commercially?

Commercial rights depend on the official Flux 3 release terms and the channel you eventually use for production. Review Black Forest Labs licensing when weights or APIs ship.

Is this the official Black Forest Labs site?

No. This is an independent preview site about Flux 3. We are not Black Forest Labs and are not endorsed by them.

What happens to my prompts?

In demo mode, prompts stay in your browser session for the playground UI. See our Privacy Policy for how we handle data once live services launch.

Flux 3 — AI Video Generator with Native Audio

Flux 3 is the next-generation multimodal model from Black Forest Labs — a breakthrough in control, realism, and world understanding. Generate and steer media from a single creative prompt.

Try Flux 3 AI Model Now

Describe the scene you want. Choose aspect ratio, duration, and resolution, then hit Generate.

Prompt

324 / 7,000

Aspect

Duration

4s

4s15s

Quality

Reference images (0/9)

Up to 9 images. Refer to them as Image 1, Image 2… in the prompt.

Reference videos (0/3)

Up to 3 clips (MP4/MOV, ≤50MB, 2–15s each).

Reference audio (0/3)

Up to 3 clips (MP3/WAV, ≤15MB). Can be used alone.

This generation uses 10 credits

Preview

Demo

Example output for the prefilled text-to-video prompt. Generate your own to replace it. (1/3)

Demo uses a sample clip so you can see the workflow before generating.

Image generationVideo + native audioAction / world controlMultimodal inputsScene continuityCreator-first workflow

Try the playground

Omni modalities

One model trained jointly across image, video, audio, and action — not four disconnected tools bolted together.

Native audio video

Sound is generated with the picture: dialogue, ambience, SFX, and music in a single pass instead of post-layered stubs.

World understanding

Stronger control and realism for scenes that move, talk, and stay consistent as you refine the prompt.

Reference & continue

Start from text, image, or existing footage — reference, transform, or continue what you already have.

Workflow

From prompt to multimodal output

A simple three-step flow — describe the world, choose how you want it rendered, then generate.

01

Describe the scene

Write a rich prompt covering look, motion, sound, and mood — Flux 3 thrives on concrete scene direction.

02

Pick frame & quality

Choose aspect ratio, duration, and resolution that match the deliverable you need.

03

Generate & iterate

Hit Generate, refine the brief, and keep exploring until the scene matches your vision.

Product realism

Hardware hero with material fidelity and cinematic light — built for brand stills and launch assets.

World atmosphere

Environments that feel lived-in — travel mood boards, game concept art, and location scouting plates.

Character storytelling

Editorial portraits with narrative context — campaign covers and character bible frames.

Interface concepts

UI and product-screen compositions for demos, pitch decks, and design exploration.

Showcase images are original assets for this site. They illustrate creative directions, not official Flux 3 model outputs.

Showcase

Flux 3 AI Image Gallery

Illustrative stills for product, environment, portrait, and interface storytelling — remix them with omni-style prompts.

Capabilities

What Flux 3 can do

Flux 3 is positioned as more than another image model — a multimodal system for worlds that look, move, sound, and respond.

01

Image generation

High-fidelity stills with the control and realism the Flux line is known for — now inside a broader omni stack.

02

Video generation

Text-to-video and reference-to-video workflows for short clips with stronger scene continuity.

03

Native audio

Dialogue, sound effects, ambience, and music generated together with the visuals — not bolted on later.

04

Action & control

Prompt-steered motion and world interaction so scenes can be directed, continued, and remixed.

05

Multimodal inputs

Combine text with images or existing footage to guide reference, transformation, or continuation.

06

Creator pipeline

Compress ideation, visuals, sound design, and iteration into one prompt-first playground.

Use cases

Is Flux 3 right for you?

When your job needs more than a pretty still — motion, sound, and steerable worlds — the omni model is the point.

Studios & filmmakers

Previz, storyboards, short clips with native audio, and rapid visual R&D before full production.

Product & marketing teams

Hero stills, launch videos, UI mock concepts, and campaign systems from one creative stack.

Game & interactive teams

Concept art, environment plates, action-driven sequences, and audio-aware scene sketches.

4.5K

token-scale prompt budget (model class)

12

languages for native on-image text

10px

target small-text readability in demos

Flux 3 Video Pricing

Upgrade to unlock every feature and get more credits. Yearly billing saves the most.

Pro

Best value — more credits each year.

Save $36

$17$20/mo

Max 15s video generation

1,700 credits
Max 15s video generation
Private video
Unlimited downloads · Email support
Text, image & reference-to-video

Max

Maximum yearly volume with commercial rights.

Save $204

$83$100/mo