MiniMax

Hailuo Video

Hailuo 02 and Hailuo 2.3 support text-to-video and image-to-video workflows, while 2.3 Fast is intended for faster image-driven iteration. The models accept prompts for action and camera direction; Hailuo's API also supports bracketed camera commands for compatible image-to-video variants.

How to use this model

  1. 1

    Choose Hailuo 2.3 for text or image generation, 2.3 Fast for rapid image-to-video iteration, or Hailuo 02 when its first/last-frame workflow is needed.

  2. 2

    Describe the subject's action, expression, environment, shot size, and camera movement in temporal order.

  3. 3

    For image-to-video, upload a clean first frame; add a final frame only to a version that exposes that input.

  4. 4

    Select duration and resolution together because the available combinations vary by model version.

  5. 5

    Preview the result for body motion, facial consistency, and the transition away from the supplied frame.

02Available

Hailuo 02

Hailuo 02 is the family variant to use when an explicit end frame is part of the shot design. It also supports ordinary text-to-video and first-frame image-to-video with duration and resolution controls.

Try now

Properties

  • Supports text-to-video, first-frame image-to-video, and first/last-frame generation.
  • Available duration and resolution combinations are selected together.

How to use this model

  1. 1

    Choose text, first-frame, or first-and-last-frame generation.

  2. 2

    Describe the action and camera path connecting the supplied states.

  3. 3

    Select a supported duration and resolution combination.

  4. 4

    Review the opening and ending transitions for visual continuity.

Examples

Character motion generated with Hailuo 02.

Parameters

Prompt

prompt
Required

Text prompt for generation

duration

duration
Required

Duration of the video in seconds. 10 seconds is only available for 768p resolution.

  • 6

  • 10

resolution

resolution
Required

Pick between standard 512p, 768p, or pro 1080p resolution. The pro model is not just high resolution, it is also higher quality.

  • 768p

  • 1080p

First Frame Image

first_frame_image
Optional

First frame image for video generation. The output video will have the same aspect ratio as this image.

Last Frame Image

last_frame_image
Optional

Last frame image for video generation. The final frame of the output video will match this image.

Prompt Optimizer

prompt_optimizer
Optional

Use prompt optimizer

Default: true
2.3Available

Hailuo 2.3

Use Hailuo 2.3 for either a fully prompted shot or an image-led animation. The prompt should describe action and camera development in order; in image-to-video, the uploaded frame supplies the initial appearance and composition.

Try now

Properties

  • Supports text-to-video and first-frame image-to-video workflows.
  • Camera commands are available for compatible image-to-video prompting.

How to use this model

  1. 1

    Choose text-to-video or upload one first-frame image.

  2. 2

    Describe subject action, expression, framing, and camera movement in temporal order.

  3. 3

    Select a supported duration and resolution combination.

  4. 4

    Review body motion, facial stability, and the transition from the source frame.

Examples

A reviewed video output created with Hailuo 2.3 in Omnipix.

Parameters

Prompt

prompt
Required

Text prompt for generation

duration

duration
Required

Duration of the video in seconds. 10 seconds is only available for 768p resolution.

  • 6

  • 10

resolution

resolution
Required

Pick between 768p or 1080p resolution. 1080p supports only 6-second duration.

  • 768p

  • 1080p

Prompt Optimizer

prompt_optimizer
Optional

Use prompt optimizer

Default: true

First Frame Image

first_frame_image
Optional

First frame image for video generation. The output video will have the same aspect ratio as this image.

2.3 FastAvailable

Hailuo 2.3Fast

Fast is the image-driven Hailuo 2.3 variant: the source image establishes appearance and composition, while the prompt directs motion, expression, and camera behavior. Use the same image and prompt when comparing it with the non-Fast version.

Try now

Properties

  • Fast image-to-video variant requiring a first-frame image.
  • Duration and resolution availability depends on the selected output combination.

How to use this model

  1. 1

    Upload a clean first frame with the intended subject and composition.

  2. 2

    Describe motion, expression, camera direction, and shot progression.

  3. 3

    Select a supported duration and resolution combination.

  4. 4

    Inspect the transition from the source and compare identical inputs with Hailuo 2.3 if needed.

Examples

A six-second image-to-video result generated with Hailuo 2.3 Fast.

Parameters

Prompt

prompt
Required

Text prompt for generation

duration

duration
Required

Duration of the video in seconds. 10 seconds is only available for 768p resolution.

  • 6

  • 10

resolution

resolution
Required

Pick between 768p or 1080p resolution. 1080p supports only 6-second duration.

  • 768p

  • 1080p

Prompt Optimizer

prompt_optimizer
Optional

Use prompt optimizer

Default: true

First Frame Image

first_frame_image
Required

First frame image for video generation. The output video will have the same aspect ratio as this image.