← Back to all generators
minimax/hailuo-2.3
OfficialView on Replicate →
A high-fidelity video generation model optimized for realistic human motion, cinematic VFX, expressive characters, and strong prompt and style adherence across both text-to-video and image-to-video workflows
Capabilities
No capability data available
Cost
$0.560 / image
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
prompt* | string | Text prompt for generation | — | — |
duration | integer | Duration of the video in seconds. 10 seconds is only available for 768p resolution. | 6 | 610 |
first_frame_image | string(uri) | First frame image for video generation. The output video will have the same aspect ratio as this image. | — | — |
prompt_optimizer | boolean | Use prompt optimizer | true | — |
resolution | string | Pick between 768p or 1080p resolution. 1080p supports only 6-second duration. | "768p" | 768p1080p |
promptrequiredstringText prompt for generation
durationintegerDuration of the video in seconds. 10 seconds is only available for 768p resolution.
Default:
6610
first_frame_imagestringFirst frame image for video generation. The output video will have the same aspect ratio as this image.
prompt_optimizerbooleanUse prompt optimizer
Default:
trueresolutionstringPick between 768p or 1080p resolution. 1080p supports only 6-second duration.
Default:
"768p"768p1080p
Version:
23a02633b5a4Updated: 8/1/2026112.5K runs
cinemasetfree