Hailuo 02 by Hailuo AI is an image-to-video model delivering ultra-clear 768P video with responsive handling of physics-driven scenes. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
ว่าง
$0.23ต่อครั้ง·~43 / $10
ตัวอย่างดูทั้งหมด
An epic scene, a colossal ancient dragon perched atop a jagged volcanic peak, smoke billowing, lava flowing, storm clouds gathering, dramatic lighting, fantasy art, cinematic, highly detailed scales, breathtaking.
The girl in the image begins performing a graceful ballet solo on a grand theater stage, she twirls and lifts one leg into an arabesque, soft spotlight follows her every move, cinematic lighting, slow camera pan from left to right, elegant and fluid motion
The girl in the image starts moving gracefully through a misty forest, twirling slowly, extending her arms as leaves swirl around her, camera rotates gently around her body, cinematic lighting, realistic motion
The girl in the image performs a powerful contemporary dance on a dimly lit stage, her arms sweep dramatically, her body spins and contracts with emotion, moody spotlight and rotating camera, fast yet expressive motion
The boy in the image breaks into a high-energy hip-hop dance on an urban rooftop, spinning, body popping, footwork fast and rhythmic, wide-angle drone camera sweeps across the scene, cinematic tone
The dancer in the image gracefully moves across the stage with a flowing silk ribbon, spinning and leaping, ribbon twirls through the air, elegant camera dolly-in, warm stage lighting
The man in the image performs a slow and controlled Tai Chi sequence in a misty mountain setting, his hands flow like water, camera slowly zooms and pans, peaceful and meditative motion
A playful puppy, excitedly chasing a rolling ball across a lush green park. Its ears flap in the wind, and its tail wags furiously. Low-angle tracking shot, bright daylight, energetic and cheerful ambiance.
Pixel art style,An inquisitive squirrel, busily burying nuts in a sun-dappled forest floor. Leaves crunch softly under its tiny paws, and dappled light filters through the canopy. Close-up, natural lighting, peaceful and lively ambiance.
Masterpiece, ultra-detailed, photorealistic portrait of an ancient wise wizard with glowing eyes, dramatic volumetric lighting, cinematic, studio shot, sharp focus, 8k, award-winning photography.
Close-up, high-definition shot of a rusty, weathered vintage car in a desolate desert, cinematic dust clouds, harsh sunlight, intricate textures, dust particles in air, 100mm lens, professional automotive photography.
โมเดลที่เกี่ยวข้อง
README
minimax/hailuo-02/i2v-standard — Image-to-Video
Hailuo 02 (Standard, I2V) is Hailuo AI’s image-to-video model built on MiniMax’s evolving framework. It’s fine-tuned for ultra-clear 768p output, high prompt responsiveness, and robust physics—even in chaotic, action-heavy scenes.
Why it’s great
- Native 768p clarity – crisp frames without upscaling.
- Strong motion & physics – believable debris, cloth, impacts, and handheld shake.
- Cinematic continuity – smoother frame-to-frame transitions, fewer artifacts.
- Prompt-responsive – follows detailed scene and camera directions reliably.
Parameters
- prompt (optional) – Describe scene, lighting, and camera moves.
- image* – Starting frame (JPG/PNG).
- end_image (optional) – Target frame for a guided transition.
- duration – 6s or 10s.
- enable_prompt_expansion – Auto-refines the prompt and applies safety checks.
How to use (short)
- Upload image (and optional end_image).
- Add a concise prompt with motion + lighting + mood.
- Choose duration (6s / 10s).
- (Optional) Keep prompt expansion on for cleaner results.
- Click Run.
Pricing
| Duration | Price |
|---|---|
| 6 s | $0.23 |
| 10 s | $0.56 |
Example prompts
- Slow dolly-in on a playful puppy sprinting across a sunny field, shallow depth of field, soft grass motion, warm backlight.
- Moody sci-fi corridor; camera orbits a robot as sparks fall, volumetric fog, blue rim-light, cinematic grade.
Hailuo 02 I2v Standard API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/minimax/hailuo-02/i2v-standard with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Hailuo 02 I2v Standard below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/minimax/hailuo-02/i2v-standard" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"image": "https://example.com/your-input.jpg",
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 6,
"enable_prompt_expansion": false
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("minimax/hailuo-02/i2v-standard", {
"image": "https://example.com/your-input.jpg",
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 6,
"enable_prompt_expansion": false
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"minimax/hailuo-02/i2v-standard",
{
"image": "https://example.com/your-input.jpg",
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 6,
"enable_prompt_expansion": false
}
)
print(output["outputs"][0]) # → URL of the generated outputHailuo 02 I2v Standard API — Frequently asked questions
What is the Hailuo 02 I2v Standard API?
Hailuo 02 I2v Standard is a MiniMax model for video generation from images, exposed as a REST API on WaveSpeedAI. Hailuo 02 by Hailuo AI is an image-to-video model delivering ultra-clear 768P video with responsive handling of physics-driven scenes. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Hailuo 02 I2v Standard API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/minimax/minimax-hailuo-02-i2v-standard.
How much does Hailuo 02 I2v Standard cost per run?
Hailuo 02 I2v Standard starts at $0.23 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Hailuo 02 I2v Standard accept?
Key inputs: `prompt`, `image`, `duration`, `enable_prompt_expansion`, `end_image`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/minimax/minimax-hailuo-02-i2v-standard.
How long does Hailuo 02 I2v Standard take to generate?
Average end-to-end generation time on WaveSpeedAI is around 117 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Hailuo 02 I2v Standard outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (MiniMax). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.