- 5–20 seconds
Clip length
- 720p or 1080p
Resolution
- Speech, effects, ambience
Native audio
- Text prompt
Masonry input
About FLUX 3
FLUX 3 brings Black Forest Labs' generative foundation model into video. It generates the picture and soundtrack together, so dialogue, environmental sound, and effects can arrive synchronized with the action instead of being assembled afterward. In Masonry, the initial FLUX 3 integration is text-to-video: describe the subject, action, camera, shot sequence, and sound, then choose a 5–20 second duration, 720p or 1080p output, and an aspect ratio from 21:9 ultrawide to 9:16 vertical.
The model is especially useful when a brief needs more than a silent visual sketch. FLUX 3 can follow multi-shot direction within one prompt, work across photoreal, cinematic, animated, and graphic styles, and generate speech, effects, and ambience with the frames. That makes it a practical fit for sound-on social ads, launch teasers, short narrative scenes, and fast storyboards. Black Forest Labs' wider FLUX 3 model family can also work from images and keyframes, but Masonry's launch integration currently uses the dedicated fal text-to-video endpoint.
Why teams choose FLUX 3
Choose FLUX 3 when you want a sound-on clip, a longer single generation, and room to direct more than one shot from text. Its 20-second ceiling gives it more runway than many short-form video models, while native audio keeps dialogue, effects, and ambience in the same creative pass as the image. Seedance and Kling remain useful alternatives when you need their specific motion or reference-image workflows, and Veo is a strong comparison for cinematic generation. FLUX 3's clearest fit in Masonry today is text-first ideation that needs flexible style, 720p or 1080p delivery, and a finished soundtrack from the start.
What FLUX 3 can do
The capabilities that set FLUX 3 apart and earn its place in a brief
Native Synchronized Audio
Generate speech, sound effects, and environmental ambience together with the frames, with audio enabled by default and an option to create a silent clip.
Clips Up to 20 Seconds
Choose any whole-second duration from 5 to 20 seconds, leaving enough room for a complete social beat, product story, or short multi-shot sequence in one generation.
720p or 1080p Output
Draft at 720p or generate at 1080p for higher-fidelity delivery, with cost estimated from both the selected resolution and exact clip length before generation.
Multi-Shot Prompt Direction
Describe a sequence of shots and cuts in a single prompt, such as an establishing view followed by a close-up, to create a more complete scene instead of one continuous camera take.
Flexible Framing
Compose for cinematic ultrawide, standard landscape, square, portrait, or vertical placements with seven explicit aspect ratios plus an automatic option in the API.
Broad Visual Range
Move between cinematic realism, animation, graphic design, surreal imagery, and stylized commercial looks while keeping motion, camera intent, and sound in the same brief.
Where teams reach for FLUX 3
- Sound-on product launch teasers with a reveal, close-up, and audio sting in one generation
- Vertical 9:16 social ads for TikTok, Instagram Reels, and YouTube Shorts
- Multi-shot brand stories that move from an establishing shot to product detail
- Short dialogue scenes with generated speech and synchronized character motion
- Storyboards and concept films that need picture, pacing, and sound together
- Music, performance, and atmosphere-led clips where audio is part of the idea
- Cinematic B-roll and world-building shots for pitches, treatments, and previsualization
- Graphic and animated motion concepts that go beyond photoreal footage
Frequently asked questions
What teams need to know about creating with FLUX 3 in Masonry
What is FLUX 3?
FLUX 3 is Black Forest Labs' multimodal generative model for images, video, and audio. Masonry's launch integration uses the dedicated FLUX 3 text-to-video endpoint on fal, turning a written brief into video with optional synchronized audio.
Does FLUX 3 generate audio?
Yes. FLUX 3 can generate speech, sound effects, and environmental ambience with the video. Audio is enabled by default in Masonry, and you can switch it off when you need a silent clip.
How long can a FLUX 3 video be?
Masonry exposes fixed durations from 5 to 20 seconds, in one-second increments. Choosing an exact duration keeps the creative timing and the pre-generation cost estimate predictable.
What resolutions and aspect ratios are supported?
FLUX 3 supports 720p and 1080p output. The fal endpoint accepts automatic framing plus 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, and 9:16, covering ultrawide, landscape, square, portrait, and vertical placements.
Can FLUX 3 animate an existing image in Masonry?
Not through this launch integration. The wider FLUX 3 model family supports image and keyframe inputs, but Masonry currently connects to fal's dedicated text-to-video endpoint. Use another image-to-video model in Masonry when a source image must anchor the result.
Can FLUX 3 create multiple shots in one video?
Yes. Black Forest Labs describes multi-shot generation as a core FLUX 3 capability. Write the desired sequence directly into the prompt, naming each shot, camera angle, action, and transition in order.
Can FLUX 3 generate dialogue and lip-synced speech?
FLUX 3 is designed for synchronized audio-visual generation, including multilingual speech and lip synchronization. Put the exact spoken line in quotation marks, identify the speaker, and describe the surrounding sound so the model can stage picture and audio together.
How much does FLUX 3 cost?
At launch, fal lists FLUX 3 text-to-video at $0.17 per generated second for 720p and $0.29 per second for 1080p. A 10-second clip is therefore $1.70 at 720p or $2.90 at 1080p before Masonry workspace metering. Provider prices can change, so the current estimate shown before generation is the figure to rely on.
Can FLUX 3 output be used commercially?
fal marks the FLUX 3 endpoint for commercial use. Review the current fal and Black Forest Labs terms for your project, particularly when content includes trademarks, regulated subjects, or a real person's likeness.
What is the best way to prompt FLUX 3?
Describe the result as a short shooting script. Include subject and setting, action, camera movement, shot order, visual style, dialogue, sound effects, ambience, and music. Keep each beat concrete and place audio cues next to the moment they should accompany.
How does my team use FLUX 3 in Masonry?
Open a Masonry canvas, pick FLUX 3 from the model selector, and describe the video you need: a product shot, an ad creative, a social post. Masonry generates it, then you refine, edit, and combine FLUX 3 with other models in one workspace.
Is FLUX 3 free to try?
Yes, you can start generating videos with FLUX 3 on Masonry's free tier, then scale up with higher limits and priority processing as your team grows.
How do I write good prompts for FLUX 3?
Write the prompt like a compact shooting script. Name the subject, action, camera movement, sequence of shots, visual style, and the exact dialogue or sounds you want. Put important audio cues beside the action that causes them.
Who makes FLUX 3?
FLUX 3 is built by Black Forest Labs. Inside Masonry it runs alongside 50+ image and video models, so your team can pick the right one for each brief without switching tools.
Start creating with FLUX 3
Generate, edit, and compare across 50+ models in one workspace.
Guides for FLUX 3
Prompt walkthroughs and examples from the Masonry blog
Explore more AI models
Compare FLUX 3 with other models teams run in Masonry