MiniMaxpremiumText → VideoImage → Video
Hailuo 2.3
minimax/hailuo-2.3
Estimated
$0.50 / 5s @ 720p
High-fidelity video generation optimized for realistic human motion, cinematic VFX and expressive characters across text-to-video and image-to-video workflows.
720p 1080p 6s/10s Cinematic
Duration is limited to 6 or 10 seconds.
Input schema
The exact fields accepted by this model. Values are validated before a generation starts.
promptstringText prompt describing the video.
Range: −∞ — 2000
first_frame_imageimageImage used as the first frame for image-to-video.
durationintegerrequireddefault: 6Clip length.
6 · 6 seconds10 · 10 secondsresolutionstringrequireddefault: "768P"Output resolution.
768P1080Pprompt_optimizerbooleanrequireddefault: trueAuto-enhances the prompt.
fast_pretreatmentbooleanrequireddefault: falseFaster pre-processing for quicker results.
Default values
{
"duration": 6,
"resolution": "768P",
"prompt_optimizer": true,
"fast_pretreatment": false
}