HiAPI
flux-3-max 图生视频详情页 Hero 图:右侧玻璃胶片带与光轨延展,左侧柔光留白,冷调粉蓝与暖金交织,名字以发光立体字蚀刻在胶片带上。

Black Forest Labs

FLUX 3 Max

flux-3-max/keyframes-to-video

A video generation model that supports text-to-video and image-to-video, focused on low-latency, fast turnaround; public benchmarks report roughly 11–12 seconds to generate a 10-second clip, making it well suited to creative iteration and short-video assets

Try flux-3-max/keyframes-to-video

Input

Keyframes

Output

video
Fill in the parameters and run — results show up here.

Pricing

flux-3-max/keyframes-to-video per second

Specifications Unit Price
720P $0.0608
1080P $0.1036

Positioning Overview

flux-3-max/keyframes-to-video is the keyframe-driven image-to-video line in the flux-3-max family: developers provide a prompt and up to 10 keyframe images, anchoring them at specified positions on a 24 fps timeline by frame index, and the model fills in the motion and transitions between keyframes, outputting a 5 to 20 second video at 720p or 1080p. It suits storyboard previsualization, advertising, and short film asset production teams that need precise control over pacing, and it is called through the unified HiAPI.ai API.

Key Highlights

  • Pinpoint keyframe control over pacing — up to 10 images are placed at any position on the timeline by frame index, with the intermediate process completed by the model rather than only a first frame being given.
  • Keyframes support synchronized audio — audio generation is enabled by default, outputting sound synchronized with the visuals to reduce post-production dubbing work.
  • Switchable reasoning intensity — reasoning_level offers low and high settings: use high intensity to improve interpretation quality for complex scenes, and lower it for simple scenes to reduce latency.

Capability Details

Keyframe timeline arrangement: with 24 fps as the time base, frame_index specifies where each keyframe appears; frame indices must be unique and must not exceed the duration multiplied by 24, enabling precise segment-by-segment visual storytelling.

5 to 20 second duration and dual resolution: duration covers 5 to 20 seconds, resolution can be 720p or 1080p, and billing is by output seconds, making it easy to control cost by clip length.

Eight aspect ratios and automatic following: aspect_ratio offers eight ratios including 21:9, 16:9, 1:1, and 9:16, while auto follows the input image ratio, so a single line covers landscape, portrait, and square delivery.

Prompt and reasoning intensity working together: prompt supports up to 6000 characters, and reasoning_level controls interpretation depth for complex scenes, trading off between image quality and response latency.

Use Cases

  • Storyboard artists and advertising teams: key visuals plus script — place finalized storyboard images as keyframes on the timeline to produce a motion storyboard previsualization with controllable pacing for client pitches and pre-shoot reviews.
  • Brand short film production: product images and voiceover copy — use product stills as keyframes and prompts to describe camera movement and mood, generating short assets with synchronized audio for direct use in social media campaigns and website showcases.
  • Creative teams: comparing multiple keyframe options — batch-generate videos with the same prompt while swapping keyframe combinations and aspect ratios, producing multiple candidate videos for rapid iterative selection.
  • Vertical content creators: 9:16 keyframe sequences — use the portrait aspect ratio with 5 to 10 second short durations to produce short video clips as publishing assets or intermediate assets for secondary editing.

Limitations and Selection Advice

This line accepts only image-to-video input and requires at least one keyframe image; for pure text-to-video, choose the text-to-video line in the same family. Output resolution is limited to 720p and 1080p, and duration is capped at 20 seconds; longer or higher-spec final videos need to be generated in segments and then stitched together. High reasoning intensity brings higher latency, so simple-paced assets can use low instead. Keyframe images must be public HTTPS URLs, and incorrect frame index planning will cause the arrangement to differ from expectations, so verify the timeline before submitting.

  • New model flux-3-max/text-to-video video generation model now available
  • Price update flux-3-max/text-to-video Pricing Adjustment
  • Price update flux-3-max/image-to-video price update: new pricing at $0.0608

Frequently asked questions

View all FAQs →
  • What inputs does FLUX 3 Max Image to Video need?

    prompt and image_url (the first frame, PNG/JPEG/WebP) are required. Optional: end_image_url as the last frame, plus duration, resolution, aspect_ratio, generate_audio and reasoning_level.

  • Can I set the video length?

    Yes. duration accepts whole seconds from 5 to 20, 5 by default. Image to video shares the same per-second pricing as text to video, and a 5-second check shows whether the source stays stable.

  • What decides the aspect ratio?

    aspect_ratio defaults to auto, which follows the first frame's ratio. You can also set 21:9, 2:1, 16:9, 4:3, 1:1, 3:4 or 9:16. If a manual ratio differs from the image, the frame may be cropped.

  • How do first and last frames work?

    Pass the first frame in image_url and the last in end_image_url; the video moves from one to the other. The prompt only needs to describe the change in between, and the closer the two frames match in framing and light, the smoother the transition.

Related Models

View all models →

Same Type