- 5 to 20 seconds
Clip length
- 720p or 1080p
Resolution
- 7 ratios, 21:9 to 9:16
Aspect ratios
- Text, start image, optional end frame
Inputs
- Native, on by default
Audio
About FLUX 3 Max
FLUX 3 Max is a post-trained variant of FLUX 3 Video from Black Forest Labs, tuned for stronger prompt adherence and better visual quality while optimized for lower latency. In Masonry it runs through two fal endpoints: text-to-video, which builds a clip from a written brief, and image-to-video, which starts from an image you supply and can land on an optional end frame. Either way you choose a whole-second duration from 5 to 20 seconds, 720p or 1080p output, and one of seven aspect ratios from 21:9 ultrawide to 9:16 vertical. Audio is generated with the picture by default, and you can switch it off for a silent clip.
For business teams, the image-to-video route is the practical change. A product shot, a key visual, or an approved campaign frame can become the first frame of the clip, so the video starts from something your brand already signed off on instead of a text description of it. Add an end frame and the model has two fixed points to move between, which suits reveals, before-and-after transitions, and packshot endings. Because sound arrives in the same generation, a draft is already closer to a sound-on social ad, launch teaser, or storyboard than a silent visual sketch would be.
Why teams choose FLUX 3 Max
Choose FLUX 3 Max when a clip has to start from an image you already have, or land on one, and you want sound in the same pass. The image-to-video route with an optional end frame is what separates it from the FLUX 3 text-to-video launch endpoint, and the 20-second ceiling gives more runway than many short-form video models. Kling and Seedance remain strong alternatives when you need their specific reference or motion workflows, and Veo is a good comparison when you want higher resolutions than 1080p. FLUX 3 Max's clearest fit in Masonry is sound-on business video at 720p or 1080p, from either a written brief or an approved frame.
What FLUX 3 Max can do
The capabilities that set FLUX 3 Max apart and earn its place in a brief
Start From Your Own Image
The image-to-video endpoint takes a PNG, JPEG, or WebP start image and animates from it, so a real product photo or approved key visual anchors the opening frame of the clip.
Optional End Frame
Supply a second image as the last frame and the model moves from the start image to the end image. Use it for reveals, transformations, and shots that must finish on a specific packshot. An end frame requires a start image.
Native Audio, On or Off
Audio is generated together with the frames and is on by default. Describe dialogue, effects, ambience, or music in the prompt, or switch audio off when the clip will be scored or voiced later.
Clips From 5 to 20 Seconds
Pick any whole-second duration from 5 to 20 seconds. That covers a quick social beat at the short end and a fuller product story at the long end, with cost estimated from the exact length before you generate.
720p or 1080p in Seven Ratios
Draft at 720p or render at 1080p, framed as 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, or 9:16. One model covers ultrawide hero banners, landscape video, square feed posts, and vertical Reels or Shorts.
Prompt Enhancement Control
Masonry's enhance prompt setting maps to the endpoint's reasoning level. On (the default) lets the model reason over and expand your brief before rendering, which is slower. Off renders closer to the prompt as written and generates faster.
Where teams reach for FLUX 3 Max
- Animating an approved product photo into a short sound-on product video
- Start-and-end-frame reveals that open on a scene and finish on a specific packshot
- Before-and-after transitions for home, beauty, fitness, and renovation brands
- Vertical 9:16 social ads for TikTok, Instagram Reels, and YouTube Shorts
- Launch teasers that need picture and an audio sting in the same generation
- Bringing a campaign key visual to life for paid social or a landing page hero
- Storyboards and concept films that need pacing and sound together
- Ultrawide 21:9 B-roll for websites, pitches, and presentation openers
Frequently asked questions
What teams need to know about creating with FLUX 3 Max in Masonry
What is FLUX 3 Max?
FLUX 3 Max is a post-trained variant of Black Forest Labs' FLUX 3 Video model, tuned for stronger prompt adherence and better visual quality while optimized for lower latency. In Masonry it generates video from a text prompt or from a start image, with native audio and an optional end frame.
How is FLUX 3 Max different from FLUX 3?
fal describes FLUX 3 Max as a post-trained version of FLUX 3 Video with stronger prompt adherence, better visual quality, and lower latency. In Masonry the practical difference is inputs. The earlier FLUX 3 integration was text-to-video only, while FLUX 3 Max adds image-to-video with an optional end frame. FLUX 3 Max is now the FLUX video model in Masonry, and the old FLUX 3 page redirects here.
Can FLUX 3 Max animate an existing image?
Yes. Its image-to-video endpoint takes a start image in PNG, JPEG, or WebP format and generates the clip from that frame. Describe how the scene should unfold rather than re-describing what the image already shows.
Does FLUX 3 Max support an end frame?
Yes. You can add an optional end image that the video finishes on, so the model moves from your start frame to your end frame. An end frame needs a start image, so it is available on image-to-video only.
Does FLUX 3 Max generate audio?
Yes. It generates native audio with the video, and audio is on by default. Describe the dialogue, sound effects, ambience, or music you want in the prompt, or turn audio off when you plan to add a voiceover or score afterwards.
How long can a FLUX 3 Max video be?
Any whole-second duration from 5 to 20 seconds. The default is 5 seconds. Choosing an exact length keeps both the creative timing and the pre-generation cost estimate predictable.
What resolutions does FLUX 3 Max support?
FLUX 3 Max outputs 720p or 1080p, with 720p as the default. Use 720p to explore ideas quickly and at lower cost, then render the final version at 1080p.
Which aspect ratios can FLUX 3 Max generate?
Seven ratios are supported, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, and 9:16. That covers ultrawide banners, landscape video, square feed posts, portrait placements, and vertical Reels, TikTok, and Shorts.
What does the enhance prompt setting do for FLUX 3 Max?
In Masonry, enhance prompt maps to the endpoint's reasoning level. It is on by default, which lets the model put more effort into interpreting and expanding your brief and makes generation slower. Turn it off for faster renders that follow the prompt more literally.
How much does FLUX 3 Max cost?
In Masonry, FLUX 3 Max is billed in credits by resolution and exact clip length, the same for text-to-video and image-to-video, so a 1080p or longer clip costs more than a short 720p draft. The editor shows the exact credit cost before you generate. Draft at 720p and short durations, then render the final at 1080p.
Can FLUX 3 Max output be used commercially?
fal marks both FLUX 3 Max endpoints 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 Max?
For text-to-video, describe the result as a short shooting script covering subject, setting, action, camera movement, visual style, and the sounds you want. For image-to-video, focus on motion, camera, and audio, since the image already sets the look. Keep each beat concrete and place audio cues next to the moment they should accompany.
How does my team use FLUX 3 Max in Masonry?
Open a Masonry canvas, pick FLUX 3 Max 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 Max with other models in one workspace.
Is FLUX 3 Max free to try?
New Masonry accounts get 50 free credits to try GPT Image 2.5 Flare. FLUX 3 Max is included in every paid plan, and the editor shows the exact credit cost before you generate.
How do I write good prompts for FLUX 3 Max?
For text-to-video, write the prompt like a compact shooting script. Name the subject, action, camera movement, visual style, and the exact dialogue or sounds you want, and put each audio cue beside the action that causes it. For image-to-video, don't re-describe what is already in the image. Describe how the scene should unfold from it, what moves, how the camera travels, and what should be heard. When you add an end frame, describe the motion that connects the two images.
Who makes FLUX 3 Max?
FLUX 3 Max 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 Max
Generate, edit, and compare across 50+ models in one workspace.
Guides for FLUX 3 Max
Prompt walkthroughs and examples from the Masonry blog
Explore more AI models
Compare FLUX 3 Max with other models teams run in Masonry