Seedream 5.0 Pro 정식 출시 | 이미지 생성기에서 사용해보기 →

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
입력

대기 중

$0.48실행당·~20 / $10

다음:

예시전체 보기

A majestic dragon with shimmering emerald scales soars through a cloud-filled sky at dusk, its powerful wings beating rhythmically. The camera follows closely behind, then swoops around to reveal a sweeping panoramic view of a fantasy kingdom below, with towering castles and winding rivers, all bathed in the warm glow of the setting sun. Cinematic, high fantasy, volumetric lighting.

The girl in the image performs a traditional martial arts staff routine, spinning and striking with precision, desert setting, camera sweeps side to side

The martial artist in the image opens a stage show with a spinning jump kick, slow motion on impact, audience gasps, camera tilts up from the ground

On a sunny afternoon, a father is teaching his little daughter how to knead dough in the kitchen, with flour scattered everywhere. They laugh happily as sunlight streams through the window, illuminating the dust motes dancing in the air. Handheld camera style, warm natural light, capturing an intimate family moment.

An anime-style video of a pink-haired high school girl walking slowly under cherry blossom trees. The petals fall gently around her as the camera follows her from the side with a soft dolly shot. Her expression is peaceful, her skirt and hair moving naturally in the spring breeze. The background is softly blurred, with warm pastel lighting.

관련 모델

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.
참고:이 웹사이트는 제3자가 제공하는 AI 모델을 사용합니다.

Hailuo 02 T2v Pro API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/minimax/hailuo-02/t2v-pro with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Hailuo 02 T2v Pro below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "enable_prompt_expansion": true
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/minimax/hailuo-02/t2v-pro" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/minimax/hailuo-02/t2v-pro";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "enable_prompt_expansion": true
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "enable_prompt_expansion": True
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/minimax/hailuo-02/t2v-pro", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Hailuo 02 T2v Pro API — Frequently asked questions

What is the Hailuo 02 T2v Pro API?

Hailuo 02 T2v Pro is a MiniMax model for video generation, exposed as a REST API on WaveSpeedAI. 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. You can call it programmatically or try it from the playground above.

How do I call the Hailuo 02 T2v Pro 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 result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/minimax/minimax-hailuo-02-t2v-pro.

How much does Hailuo 02 T2v Pro cost per run?

Hailuo 02 T2v Pro starts at $0.48 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 T2v Pro accept?

Key inputs: `prompt`, `enable_prompt_expansion`. 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-t2v-pro.

How long does Hailuo 02 T2v Pro take to generate?

Median end-to-end generation time on WaveSpeedAI is around 176 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Hailuo 02 T2v Pro 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.

Hailuo 02 T2V Pro | Powerful Text-to-Video API | WaveSpeedAI