Black Forest Labs ยท Announced July 23, 2026

FLUX 3 Video AI Video Generator

Black Forest Labs' first video model generates footage with dialogue, sound effects and ambience in one pass. 5 to 20 second clips at 720p or 1080p, six aspect ratios, no watermark. Available from the Starter plan on Aura AI.

20s
Max Duration
1080p
Max Resolution
Audio
Dialogue + Lip-Sync
6
Aspect Ratios

FLUX 3 Video on Aura AI

MakerBlack Forest Labs
ModesText to video, image to video
Duration5 to 20 seconds
Resolution720p, 1080p
Aspect ratios21:9, 16:9, 4:3, 1:1, 3:4, 9:16
AudioNative, with lip-sync
CreditsFrom 5 per clip
PlanStarter, Pro, Premium

What is FLUX 3 Video?

FLUX 3 Video is the video side of FLUX 3, the model Black Forest Labs announced on July 23, 2026. Until now the Freiburg-based lab was known for image models, from the original FLUX.1 to FLUX.2. FLUX 3 changes the scope: a single set of weights trained jointly on images, video and audio, using a method BFL calls Self Flow, and extendable to predicting robot actions. Video opened first to early-access applicants and became generally available through the BFL API and selected partners on August 4, 2026.

Upstream, FLUX 3 Video generates clips up to 20 seconds at 720p or 1080p with native audio: dialogue, sound effects and ambient sound, in multiple languages, with lip-sync. It supports text-to-video and image-to-video, including keyframe specification and continuation of existing footage, and it can switch between scenes and camera angles inside a single generation. According to BFL's internal evaluation, human raters preferred FLUX 3 over existing models for text-to-video and it tied Seedance 2.0 on image-to-video. Those are vendor figures. An open-weight FLUX 3 Dev variant is on the roadmap without a fixed date.

On Aura AI, FLUX 3 Video runs in text-to-video and image-to-video mode with any duration from 5 to 20 seconds, at 720p or 1080p, in six aspect ratios from 21:9 to 9:16. Output is delivered without watermark and ready for commercial use. It sits next to Seedance 2.5, Veo 3.1 and Sora 2 Pro in the same studio, so you can compare takes from different models without switching tools.

FLUX 3 Video Capabilities

Six things Black Forest Labs' first video model does well

Dialogue, Effects and Ambience

Audio is part of the model, not a post-process. A prompt with a spoken line returns the voice lip-synced to the character, layered over sound effects and room tone, in the language you wrote it in.

Up to 20 Seconds in One Pass

FLUX 3 Video generates any length from 5 to 20 seconds on Aura AI, one second at a time. That covers a full Story, a product demo or a short scene without stitching clips together.

Scene and Camera Switches

The model can cut between scenes and camera angles within a single generation. Describe two or three shots in the prompt and it stages them in order with consistent characters and lighting.

Image to Video with Keyframes

Start from a still to lock the look of a product, a character or a location. Upstream, FLUX 3 supports keyframe specification and continuation of existing footage on top of standard image-to-video.

One Model for Image, Video and Audio

FLUX 3 is a single multimodal model rather than a separate video pipeline.

Six Aspect Ratios

21:9 ultrawide, 16:9, 4:3, 1:1, 3:4 and 9:16 vertical are all native on Aura AI, so the same prompt can be rendered for cinema, web, feed and Stories without cropping.

How to Use FLUX 3 Video on Aura AI

Four steps from prompt to a finished clip with sound

  1. Open the Text to Video tool, or Image to Video if you want to animate a still. Sign in with your Aura AI account.
  2. Pick FLUX 3 Video in the model selector. Choose a duration between 5 and 20 seconds, 720p or 1080p, and one of the six aspect ratios. The credit cost updates live as you change settings.
  3. Write the prompt. Describe the shots in order, the camera angles, any dialogue in quotes and the sound you expect to hear.
  4. Generate, preview and download the MP4 without watermark. For anything longer than 20 seconds, run a second generation from the last frame and join the clips in the AI video editor.

FLUX 3 Video Pricing in Credits

Cost = 6 credits base for 5 seconds, plus 0.5 credits per extra second, multiplied by the resolution factor

Duration 720p (x0.8) 1080p (x1)
5 seconds5 credits6 credits
8 seconds6 credits8 credits
10 seconds7 credits9 credits
15 seconds9 credits11 credits
20 seconds11 credits14 credits
FLUX 3 Video requires the Starter plan ($14/mo) or higher. Pro ($59/mo) and Premium ($99/mo) include larger monthly credit allowances. Fractions are rounded up to the next whole credit, and only successful generations are charged.

FLUX 3 Video vs Seedance 2.5 vs Veo 3.1 vs Sora 2 Pro

How BFL's first video model compares to the other flagship audio models on Aura AI

Feature FLUX 3 Video Seedance 2.5 Veo 3.1 Sora 2 Pro
Max resolution on Aura AI 1080p 1080p 4K 1080p
Duration 5 to 20 s 4 to 15 s 4, 6 or 8 s 4, 8, 12, 16 or 20 s
Native audio Dialogue, effects, lip-sync Single pass, 10+ languages Yes Yes
Scene switches in one clip Yes Multi-shot No No
Multimodal references upstream Image, keyframes, continuation Up to 50 Image + text Image + text
Aspect ratios 6 6 2 2
Credits, 8 s at 1080p 8 15 11 11
Plan Starter+ Starter+ Starter+ Starter+

What to Make with FLUX 3 Video

Where 20 second clips, dialogue and six ratios pay off

Product Demos with Voice-Over

A 15 to 20 second walkthrough of a product with a spoken script and matching sound effects. Start from a packshot in image-to-video to keep the exact design.

Example Prompt: "Stainless steel coffee grinder on a wooden counter, slow orbit, then close-up as beans pour in. Voice-over: 'Forty settings. One perfect cup.' Grinding sound, soft jazz, 16:9, 15 seconds"

Dialogue Scenes

Two characters, a written exchange, lip-synced in the language of your choice. FLUX 3 keeps faces and voices consistent across a scene switch, so a short exchange fits in one generation.

Example Prompt: "Rooftop at night, two friends at a railing. She: 'You really quit?' He, grinning: 'This morning.' City hum, distant siren, 21:9, 10 seconds"

Vertical Ads and Stories

Native 9:16 with the soundtrack already mixed. Use the full 20 seconds for a Story-length ad, or 5 to 8 seconds for a punchy feed clip.

Example Prompt: "Runner tying her shoes at dawn, cut to her sprinting along a beach, cut to a smile at the finish. Driving electronic beat, breathing, waves, 9:16, 12 seconds"

Multi-Angle Storyboards

Pre-visualize a scene as a wide shot, an insert and a reaction in one clip. FLUX 3 stages the switches itself, which saves generating and stitching three separate takes.

Example Prompt: "Wide: a lighthouse in a storm. Insert: the keeper's hand on the lamp switch. Reaction: he looks out at the waves. Thunder, rain on glass, 4:3, 20 seconds"

FLUX 3 Video FAQ

Common questions about FLUX 3 Video on Aura AI

What is FLUX 3 Video? +
FLUX 3 Video is the video generation capability of FLUX 3, the multimodal model Black Forest Labs announced on July 23, 2026 and made generally available for video on August 4, 2026. It is BFL's first video model, trained jointly on images, video and audio, and it generates footage with dialogue, sound effects and ambient sound in one pass. On Aura AI it runs in text-to-video and image-to-video mode with 5 to 20 second clips at 720p or 1080p in six aspect ratios.
How many credits does FLUX 3 Video cost on Aura AI? +
FLUX 3 Video starts at 6 credits for a 5 second clip at 1080p, plus 0.5 credits for every additional second. 720p costs 20 percent less. A 5 second 720p clip is 5 credits, an 8 second 720p clip is 6 credits, a 10 second 1080p clip is 9 credits and a 20 second 1080p clip is 14 credits.
Which plan do I need to use FLUX 3 Video? +
FLUX 3 Video is available on the Starter ($14/mo), Pro ($59/mo) and Premium ($99/mo) plans. Every plan includes a monthly credit allowance and works on web, iOS, Android and Windows. No BFL API key or approval is required.
How does FLUX 3 Video compare to Seedance 2.5 and Sora 2 Pro? +
All three generate native audio and top out at 1080p on Aura AI. FLUX 3 Video and Sora 2 Pro both reach 20 seconds, while Seedance 2.5 stops at 15. FLUX 3 Video offers six aspect ratios like Seedance 2.5, against two for Sora 2 Pro, and an 8 second 1080p clip costs 8 credits on FLUX 3 Video versus 15 on Seedance 2.5 and 11 on Sora 2 Pro. Seedance 2.5 remains the choice for heavy multimodal reference work.
Does FLUX 3 Video generate audio and lip-sync? +
Yes. Black Forest Labs trained FLUX 3 on audio alongside video, so a generation returns dialogue, sound effects and ambient sound together with the picture, with lip-sync and support for multiple languages. Write the spoken line in quotes and describe the ambience in your prompt and the soundtrack arrives already synchronized.

Generate FLUX 3 Videos Online

Black Forest Labs' first video model with native audio, up to 20 seconds at 1080p, no watermark. Available from the Starter plan, worldwide.