Minimax Hailuo 02 I2V Pro
Playground
Try it on WavespeedAI!MiniMax Hailuo 02 Pro, an image-to-video model tuned for clear 1080P output and responsive handling of complex physics-driven scenes. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
Hailuo-02/i2v-pro
Hailuo 02 is a breakthrough in AI video generation, engineered for creators who demand cinematic realism, physical accuracy, and HD output — all with unmatched speed and cost-efficiency. Whether you’re making short-form content, cinematic sequences, or creative storytelling, Hailuo 02 transforms static images into vivid, motion-rich video scenes that look straight out of a movie.
🌟 Key Features
1. 1080P Native Output
Enjoy full HD quality straight from the model — not upscaled. Every frame maintains clarity and fine texture, delivering a professional-grade look ideal for ads, explainers, or cinematic shorts.
2. Multiple Duration Options
5-second video clips for flexible storytelling. Mix, merge, and prototype your ideas without sacrificing fidelity or wasting render time.
3. Enhanced Motion & Physics Simulation
Hailuo 02 understands movement like never before. It captures dynamic action, natural camera motion, and physical realism — from flying particles to dramatic lighting transitions — ensuring a smooth, film-like experience.
4. Intelligent Scene Transitions
Forget awkward cuts. Frame stitching and temporal blending have been improved to emulate real camera motion and continuity, creating seamless cinematic sequences.
5. Consistent & Reliable Generation
Hailuo 02 offers excellent prompt adherence and repeatability, giving professionals predictable output quality even across multiple runs or edits.
💰 Pricing
At just $0.49 per generation !!!
🎬 Recommended Use Cases
- Social Shorts: TikTok, Reels, YouTube Shorts — fast cinematic clips that grab attention.
- Advertising: Turn static product shots into motion-rich brand visuals.
- Game / Film Prototyping: Previsualize scenes, camera moves, and action choreography.
- Educational Content: Generate visual explainers for complex topics in seconds.
- Storytelling & Concept Art: Animate ideas and environments with rich atmosphere.
- Pitch & Presentation Support: Add motion visuals to strengthen creative or business pitches.
💡 How to use
- Prompt — Write a cinematic line (motion + lighting + mood).
- Image — Upload a clear JPG/PNG as the starting frame.
- End image (optional) — Add a final frame if you want a guided transition.
- Prompt expansion — Leave ON for smarter parsing & safety.
- Run — Click Run ($0.49) and wait ~30–90s.
🧠 FAQ
Q1: Does Hailuo 02 generate audio? No — visuals only. You can easily sync your generated clip with custom music or voiceovers.
Q2: Is it suitable for commercial projects? Yes, provided you comply with licensing and platform usage terms.
Q3: How long does it take to generate a clip? Typically 30–90 seconds, depending on prompt complexity and server load.
Q4: Can I use it on mobile? Yes — Hailuo 02 runs smoothly on most mobile browsers and interfaces.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/minimax/hailuo-02/i2v-pro" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"enable_prompt_expansion": true
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | No | - | The positive prompt for the generation. | |
| image | string | Yes | - | The model generates video with the picture passed in as the first frame.Base64 encoded strings in data:image/jpeg; base64,{data} format for incoming images, or URLs accessible via the public network. The uploaded image needs to meet the following conditions: Format is JPG/JPEG/PNG; The aspect ratio is greater than 2:5 and less than 5:2; Short side pixels greater than 300px; The image file size cannot exceed 20MB. | |
| end_image | string | No | - | - | The model generates video with the picture passed in as the first frame.Base64 encoded strings in data:image/jpeg; base64,{data} format for incoming images, or URLs accessible via the public network. The uploaded image needs to meet the following conditions: Format is JPG/JPEG/PNG; The aspect ratio is greater than 2:5 and less than 5:2; Short side pixels greater than 300px; The image file size cannot exceed 20MB. |
| enable_prompt_expansion | boolean | No | true | - | 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. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Array of URLs to the generated content (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |