image-to-video
Hailuo 02 is an AI video-generation model delivering 768P output with fast responsiveness and strong handling of complex physics scenes. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Input
Idle
Ihre Anfrage kostet $0.23 pro Durchlauf.
Für $10 können Sie dieses Modell ungefähr 43 Mal ausführen.
Noch etwas:
BeispieleAlle anzeigen
README
minimax/hailuo-02/standard
Hailuo 02 Standard is the unified model on MiniMax’s framework. It generates cinematic clips with 768p clarity, strong prompt adherence, believable physics, and smooth temporal transitions. Use it as pure T2V (text only) or guided I2V (add a start image, optional end image for a planned transition).
Why creators like it
- One endpoint, two modes — Text-to-Video or Image-guided Video.
- Native 768p — crisp frames, not upscaled.
- 6s / 10s clips — quick iteration or trailer pacing.
- Physics & motion — debris, cloth, water, handheld shake look natural.
- Stable & repeatable — good consistency across re-runs.
Parameters
| Name | Description |
|---|---|
| prompt* | Describe scene, lighting, motion, and camera. |
| image | (Optional) Use a reference/first frame (JPG/PNG) to lock composition & style. |
| end_image | (Optional) Target frame for a guided transition. |
| duration | 6s or 10s. |
| enable_prompt_expansion | Auto-refines prompt and runs a safety check. |
Pricing
| Duration | Cost per job | Resolution |
|---|---|---|
| 6 s | $0.23 | 768p |
| 10 s | $0.56 | 768p |
How to use (short)
- Write a prompt (include camera + motion + lighting).
- (Optional) Add image (and end_image for a transition).
- Pick duration (6s/10s), keep prompt expansion on.
- Run → review → tweak prompt → re-run.
Example prompts
- A boy and his dog race along the beach at sunset; camera tracks low and wide, warm reflections on wet sand, gentle spray, cinematic grade.
- Slow orbit around a neon-lit street food stall in the rain; steam and bokeh, handheld vibe, rack focus to the chef’s hands.