Example 1

Subtle cinematic portrait motion: the character breathes naturally, eyes shift slightly toward camera, soft daylight changes across the face, background stays minimal, no exaggerated expression, no camera shake.
6
768p
true
A fast, low-latency image-to-video model preserving motion quality and visual consistency for efficient iteration.
A fast, low-latency image-to-video model preserving motion quality and visual consistency for efficient iteration.
MiniMax-Hailuo-2.3-Fast is an optimized variant of the MiniMax-Hailuo-2.3 video generation model family designed specifically for lower latency and faster iteration cycles. It generates video from a single image input combined with a text prompt, producing stylized, visually consistent video sequences that maintain realistic motion dynamics.
Compared to the core MiniMax-Hailuo-2.3 model, this fast variant reduces latency and computational load while preserving essential qualities like motion realism and stylization, facilitating quicker prototyping and iteration in video generation workflows.

Subtle cinematic portrait motion: the character breathes naturally, eyes shift slightly toward camera, soft daylight changes across the face, background stays minimal, no exaggerated expression, no camera shake.
6
768p
true
Text prompt for generation
First frame image for video generation. The output video will have the same aspect ratio as this image.
Text prompt for generation
Duration of the video in seconds. 10 seconds is only available for 768p resolution.
6Pick between 768p or 1080p resolution. 1080p supports only 6-second duration.
768pUse prompt optimizer
trueOutput
Type
Node
Status
Official
Package
Nodespell AI
Category
AI / Video / MinimaxInput
Output