FLUX 3 Max Is Now Live on VIDEO AI ME: What You Get

FLUX 3 Max is now live on VIDEO AI ME. Open the editor, pick FLUX 3 Max in the video model picker, and generate a 5 to 20 second clip at 720p or 1080p with sound made in the same pass, from a prompt or from one reference image. The standard rate is 17 credits per second at 720p.

If you run paid social, the clip you need most often is 10 to 20 seconds long, vertical or widescreen, and it has to have sound. FLUX 3 Max covers that brief in a single generation, at up to 1080p, with no separate audio pass and no stitching. Below: what the model is, what the editor exposes, what a clip costs, and where to start.

What is FLUX 3 Max?

FLUX 3 Max is a video model from Black Forest Labs, the team behind the FLUX image models. It is a post-trained variant of Black Forest Labs' FLUX 3 Video, which its developers describe as tuned for stronger prompt adherence and better visual quality, and optimized for lower latency. Those are the developers' claims, so check them against your own brief.

Prompt adherence is the claim that matters most for ad work. If it holds for your briefs, the product, the action and the line you wrote are more likely to be what comes back, which means fewer generations thrown away per usable asset.

One more behaviour is worth knowing before you write anything. FLUX 3 Max reasons about your prompt and expands it before rendering, so a short prompt still produces a full shot. That cuts both ways. The expansion fills in whatever you leave open, so if the product colour, the spoken line or the framing matters, write it down. Specific prompts still win.

For the longer explanation of where the model comes from and how it differs from the rest of the catalogue, read what FLUX 3 Max is and what it does.

What can you make with it on VIDEO AI ME?

There are two ways to create, and the mode is chosen by what you attach:

Text to video is for when you have a concept and no footage. You describe the shot and the sound, and the model builds both.

Image to video is for when you already have the look: a product photo, a lifestyle still, a frame from a previous campaign. Your image becomes the opening frame, so the prompt should describe motion and sound rather than appearance.

FLUX 3 Max takes one reference image, used as the start frame. It is not a multi-reference model on VIDEO AI ME. If your brief needs several reference images to hold a character or a product consistent, Seedance 2.5 and MiniMax H3 Max take several. If you want visuals built around your own voice-over, Boreal takes an uploaded audio track. All three sit in the same picker.

What are the FLUX 3 Max specs in the editor?

Duration. Every length up to 20 seconds is one generation. There is no stitching of shorter segments behind the scenes. If your concept needs three scenes, make three clips and join them in the editor.

Aspect ratio. auto renders 16:9 for text to video and follows your image for image to video. Picking a named ratio overrides that. The 21:9 option is there for cinematic placements and brand films, and 9:16 is the shape for most short-form feeds.

Audio. Every clip comes back with sound generated in the same pass: ambience, effects, music, and any spoken lines you write into the prompt. Audio is always generated. If you want a different track, replace it with your own audio after the clip lands.

How much does FLUX 3 Max cost?

Every model on VIDEO AI ME bills in credits per second of finished video, and 1 credit is 1 cent of generation cost. FLUX 3 Max costs 17 credits per second at 720p and 29 credits per second at 1080p. Text to video and image to video cost the same.

Launch rate: through November 6, 2026, FLUX 3 Max is billed at 5 credits per second at 720p and 8 at 1080p, so a 10 second clip is 50 credits at 720p or 80 at 1080p. The app switches to the standard rate above automatically on November 7, 2026.

Here is what a month of credits buys at the standard rate, counting 10 second clips:

Plan details are on the pricing page. For every duration, every plan and the cost per usable clip once you account for rejected drafts, see the FLUX 3 Max pricing breakdown.

How does it compare with the other models in the picker?

FLUX 3 Max sits alongside Seedance 2.5, Kling, Seedance 2.0, Happy Horse, Grok Imagine 1.5, Gemini Omni Flash, MiniMax H3 Max and Boreal. On price, it sits between the budget models and the premium tier:

The line worth reading twice: FLUX 3 Max at 1080p, at 29 credits per second, costs less per second than Seedance 2.5 at 720p, at 48. A 20 second clip is 580 credits at 1080p on FLUX 3 Max and 960 credits at 720p on Seedance 2.5.

That is a price comparison, not a quality verdict. Each model fits a different job:

MiniMax H3 Max is left out of the price table on purpose. It makes 5 to 15 second clips at 480p or 768p and takes up to 9 reference images or 3 reference videos; its current rate is on the pricing page.

How do you write your first FLUX 3 Max prompt?

FLUX 3 Max reads plain natural language. Write one paragraph per shot, in this order: subject and action, then camera, then light and look, then sound. For sound, put spoken lines in double quotes with who says them, then ambience and effects, then music or "no music".

A text to video example for a 9:16, 10 second clip:

A woman in her thirties holds a glass bottle of cold brew up to the camera in
a sunlit kitchen, then takes a sip and smiles. Handheld, eye level, slight
push-in. Warm morning light from a window on the left, soft natural grade.
She says, "This is the only coffee I make at home now." Quiet kitchen
ambience, the clink of the bottle on the counter, no music.

Three habits save most first attempts:

• Budget the dialogue. Roughly two to three spoken words per second of clip, so a 10 second clip holds about 20 to 25 words. Write fewer than you think.
• One scene, one idea. Twenty seconds is room for one beat done well, not a montage.
• Keep on-screen text out of the prompt. Add captions in the editor, where they stay sharp and editable, and any other text after export.

The full walkthrough, from opening the editor to exporting, is in how to use FLUX 3 Max.

What should you check before a clip goes live?

The honest limits, stated plainly:

Platform rules still apply once the clip leaves VIDEO AI ME. Check the placement specs for where you buy media, for example TikTok's video ad specifications and Meta's video ads guide, before you pick a ratio and a length.

Where should you start with FLUX 3 Max?

Start with the job you already pay for, not a demo prompt.

If you run UGC-style ads, write one script, generate it at 720p in 9:16, and judge whether the delivery and the product handling clear your bar. The FLUX 3 Max UGC ads guide covers scripting and structure.

If you sell physical products, start from a product photo you already have. Attach it, describe the motion and the sound, and you have a product clip without a shoot.

If you make brand films, try 21:9 at 1080p for one hero beat, once the prompt is settled at 720p.

Whichever you pick, test at 720p and deliver at 1080p. Agents and the API reach the model too, through the make_video skill on the VIDEO AI ME MCP server and through /api/v1, so the same prompt can move into an automated pipeline once it works.

Frequently Asked Questions

What is FLUX 3 Max?

FLUX 3 Max is a video model from Black Forest Labs, the team behind the FLUX image models. It is a post-trained variant of Black Forest Labs' FLUX 3 Video, which its developers describe as tuned for stronger prompt adherence and better visual quality, and optimized for lower latency. On VIDEO AI ME it generates 5 to 20 second clips with sound at 720p or 1080p.

What clip lengths can you pick for FLUX 3 Max?

Up to 20 seconds in one generation. The editor offers 5, 8, 10, 12, 15 and 20 seconds, and every length is a single generation with no stitching. For a longer concept, generate each beat as its own clip and join them in the editor.

Do FLUX 3 Max clips come with sound?

Yes. Every FLUX 3 Max clip comes back with sound generated in the same pass: ambience, effects, music and any spoken lines you write into the prompt. Audio is always generated on VIDEO AI ME, so if you want a different track, replace it with your own audio afterwards.

How much does FLUX 3 Max cost on VIDEO AI ME?

The standard rate is 17 credits per second at 720p and 29 credits per second at 1080p, where 1 credit is 1 cent of generation cost. A 10 second clip is 170 credits at 720p or 290 credits at 1080p. Text to video and image to video cost the same.

Can FLUX 3 Max turn an image into a video?

Yes. Attach one reference image and FLUX 3 Max uses it as the first frame, while your prompt drives the motion and the sound. It takes one image only. For briefs that need several reference images, Seedance 2.5 and MiniMax H3 Max in the same picker take several.

What resolution does FLUX 3 Max support?

On VIDEO AI ME, FLUX 3 Max renders at 720p or 1080p, in auto, 9:16, 16:9, 1:1, 4:3, 3:4 or 21:9. A practical habit is to test prompts at 720p, where a 10 second clip costs 170 credits, and deliver the winner at 1080p.