GPT Image 2 is LIVE Now. Try in Image Generator→
首页/探索/Minimax Hailuo Models/minimax/hailuo-02/t2v-pro

Hailuo 02 T2V-Pro

minimax /

Hailuo 02 T2V-Pro is a text-to-video model fine-tuned for ultra-clear 1080P video and responsive handling of physics-driven scenes. Ready-to-use REST API, no coldstarts, best performance, affordable pricing.

text-to-video
输入
The model automatically optimizes incoming prompts to enhance output quality. This also activates the safety checker, which ensures content safety by detecting and filtering potential risks.

就绪

您的请求将花费 $0.48 每次运行。

使用 $10 您可以运行此模型大约 20 次。

还有一件事:

示例查看全部

README

Hailuo 02 — Text-to-Video (T2V Pro)

minimax/hailuo-02/t2v-pro turns plain text into cinematic 1080p video with strong prompt adherence, realistic physics, and smooth camera motion. It’s built for creators who want film-like shots without hand-animating or storyboarding.

Why it stands out

  • 1080p native output – Full-HD frames straight from the model (not upscaled).
  • Enhanced motion & physics – Handles debris, cloth, impacts, and handheld shake with believable dynamics.
  • Cinematic transitions – Temporal consistency reduces flicker and “slideshow” artifacts.
  • Reliable prompt following – Low randomness and stable re-runs make it production-friendly.

Typical use cases

  • Short-form social clips (Reels/TikTok/Shorts) with cinematic look.
  • Ads & product showcases that need camera moves and physical realism.
  • Film/game previz for scenes, shots, and mood boards.
  • Education & explainers where motion clarifies complex ideas.
  • AI storytelling—build micro-scenes purely from text.

Parameters

NameDescription
prompt*Describe scene, subjects, lighting, motion, and camera (e.g., “dolly-in through rainy neon alley, steam rising, reflections on wet pavement, moody synth score vibe”).
enable_prompt_expansionWhen on, the model refines the prompt for quality and runs a safety check.

Pricing

  • Fixed price $0.48 per run.

Tips

  • Write like a director: include shot type (wide/close-up), camera moves (pan/tilt/dolly/orbit), lighting, and mood.
  • Use motion verbs: “drifts,” “whips,” “racks focus,” “particles swirl,” “fog rolls.”
  • Iterate fast: start at 6s to nail motion/lighting, then switch to 10s for the hero take.
  • Keep style consistent: repeat key style words at the start and end of the prompt.

How to use (super short)

  1. Prompt – Write a cinematic description (motion + lighting + mood).
  2. Prompt expansion – Keep ON for smarter parsing & safety.
  3. Run – Generate, review, tweak prompt/seed, and iterate.

Example prompts

  • Epic aerial of glacial cliffs at dawn, low clouds hugging the ice; camera orbits slowly, sun flare blooms; photoreal, crisp 1080p, cinematic grade.
  • Retro-futuristic race through neon tunnel, camera dolly-zoom, motion-blur streaks, sparks from hover-wheels, synthwave palette, dramatic backlight.
  • Cozy study room, golden hour; slow push-in to a steaming mug, dust motes in sunbeam, shallow depth of field, warm film emulation.