HiAPI
21:9 高调光宽幅 Hero 图:右侧虹彩玻璃胶片光带蜿蜒,青色、珊瑚粉与薰衣草光斑浮动,玻璃上立体发光的 hailuo-2.3 字样;左侧为奶油色柔光留白。

MiniMax

Hailuo 2.3

hailuo-2.3/text-to-video

A video generation model launched by MiniMax that supports both text-to-video and image-to-video, with improvements over the previous generation in anime-style consistency, full-body motion rendering, and the realism of subtle facial expressions, making it suitable for anime shorts and live-action-feel commercial videos

Try hailuo-2.3/text-to-video

Input

Output

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

Pricing

hailuo-2.3/text-to-video per video

Specifications Unit Price
6S $0.400
10S $0.800

Overview

Hailuo 2.3 is a video generation model series from MiniMax, and this route is its text-to-video version: input a text description and directly produce video material. It continues the series' emphasis on smooth motion and character performance, making it suitable for developers who need to quickly turn creative scripts into dynamic visuals, such as anime-style short films, character performance content, and preliminary test shoots for commercial promos. Call it through the unified HiAPI.ai interface without integrating with upstream providers separately.

Core Highlights

  • Direct text-to-video, covering the pure creative workflow — A single prompt is enough to generate a video, making it suitable for creative pipelines that start from the script stage without existing footage.
  • More complete character motion and facial performance — This series has targeted optimizations for complex full-body movements and realistic micro-expressions, making close-up character shots more usable in final cuts.
  • Improved stability for stylized subjects such as anime — Generation quality and consistency for special art styles such as 2D anime have been strengthened, facilitating serialized content production.
  • Duration can be selected according to material use — Supports generating 6-second or 10-second videos; short material for test shoots, long material for final-cut segments.

Capabilities

Text-to-video generation: Describe the scene content with a prompt of up to 2000 characters and directly obtain a video file, suitable for building shots from scratch.

Two duration outputs: You can specify 6 seconds or 10 seconds, with 6 seconds as the default, making it easy to choose material length according to placement or editing rhythm.

Automatic prompt optimization: prompt_optimizer is enabled by default and can complete short descriptions into more executable generation instructions, reducing tuning costs.

Character and stylized performance: The series' capabilities cover full-body movements such as dance and anime styles, suitable for content that requires character performance or consistent style.

Use Cases

  • Script-to-video for anime and 2D creators — Input stylized plot descriptions to produce short-film shots for social platform serials or style test clips.
  • Script test shoots for advertising and product promos — Input product selling points and scene descriptions to produce dynamic sample videos for proposal presentations and direction confirmation before shooting.
  • Shot generation for character performance content — Input dance or action descriptions to produce video clips with complete body movements for editing and material filling.

Limitations and Selection Advice

Only text-to-video is supported; images cannot be used as the first frame to drive the visuals. First and last frame control is not supported, so the starting and ending points of a shot cannot be precisely specified. The prompt limit is 2000 characters, and the maximum duration per generation is 10 seconds; longer narratives need to be generated in segments and then spliced together. If you already have reference images and want to maintain subject consistency, you should use the image-to-video route instead; if you value output speed and cost more than text-to-video capability, consider the lightweight version in the same series.

  • New model New model available: hailuo-2.3-fast/image-to-video

Frequently asked questions

View all FAQs →
  • Does Hailuo 2.3 Image to Video require an input image?

    Yes. hailuo-2.3/image-to-video is an image-to-video route. The image establishes the subject and opening composition; the prompt directs motion, camera, and environmental change.

  • Which durations and resolutions does Hailuo 2.3 Image to Video support?

    The current HiAPI contract supports 6s / 10s. Check the page controls and API docs for the current options.

  • How is Hailuo 2.3 Image to Video billed?

    Each generated video is billed at the selected duration tier. The page follows the global display unit, while the successful task record contains the final charge.

  • How can I improve subject consistency?

    Use a clear, unobstructed source with a complete composition. Describe the main action and camera first, then name the appearance, material, and background relationships that must remain stable. Validate a short clip first.

Related Models

View all models →

Same Type