Seedream 5.0 Pro अब लाइव है | Image Generator में आज़माएं →
साइन इन

Video 02

minimax /

Hailuo 02 is an AI video generation model fine-tuned for ultra-clear 1080P output and handling complex physics-driven scenes. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

image-to-video
इनपुट

निष्क्रिय

$0.25प्रति रन·~40 / $10

आगे:

उदाहरणसभी देखें

Circus Scene. The camera follows a clown riding unicycle while jugging balls. The camera pulls back, tracks left, and tilts loft

The character in the frame juggles throwing knives with fast and fluid motion.Circus Scene

Circus Scene. A lion jumps through a flaming hoop. The camera puls back and follows, then tracks the lion running throuah the circus ring

Circus Scene. A bear n a vest does three consecutive somersaults on a mat, the movements are smooth and fast.

Circus Scene. The character waves a torch quickly, the camera pushes in for a close-up of their face.

Circus Scene. Acrooatic performance: performer swings rapidly on an aerial hoop, executing high-difficulty moves as the camera folows

A black cat leaps across rooftops under a full moon. [Side-scrolling style], reminiscent of a 2D platformer game. The rooftops have different textures—tiles, bricks, wooden planks. The background slowly scrolls to reveal more of the stylized nighttime cityscape.

Inside a massive library with impossibly tall shelves, books fly off on their own, fluttering like birds. A young girl with round glasses floats gently upward, reaching for a glowing book at the top. Warm golden light pours through stained-glass windows.

A sad clown in vintage makeup stands alone under a dim spotlight in an empty circus tent, fog swirling around his shoes, camera slowly zooming in on his teary eyes. Cinematic lighting, melancholic tone.

A fashion editorial scene set in a barren desert. A tall woman in a futuristic metallic dress walks down a cracked salt flat. The sky is bright white, almost overexposed, and the dress reflects the environment like liquid metal. [Slow panning shot] captures her silhouette against the endless horizon.

A female gymnast performs a flawless floor routine under dramatic spotlight, slow-motion close-ups highlight her elegant spins, flips, and landings, cinematic lighting and smooth camera transitions

The character in the frame juggles throwing knives with fast and fluid motion.Circus Scene

संबंधित मॉडल

README

MiniMax Video-02 — minimax/video-02

MiniMax Video-02 generates short video clips from a text prompt, with optional image guidance. Describe the subject, action, scene, and camera movement, and the model produces a coherent, motion-rich clip suitable for story beats, ads, and creative prototyping.

Key capabilities

  • Text-to-video generation with strong motion and scene coherence
  • Optional image input to anchor composition and style
  • Camera-direction friendly prompting (follow, pull back, track, tilt, orbit)
  • Prompt expansion option to automatically enhance prompts and enable the safety checker

Use cases

  • Cinematic shot generation (camera moves, blocking, atmosphere)
  • Storyboarding and pre-visualization for short scenes
  • Marketing creatives and social clips with clear action cues
  • Image-guided variants (keep a reference look while changing motion/camera)

Pricing

ResolutionPrice per video
720p$0.0625
1080p$0.11

Parameters

  • prompt (required): What happens in the video (subject, action, scene, camera, style)
  • image (optional): Reference image to guide composition/style
  • resolution: Output resolution (e.g., 720p, 1080p)
  • duration: Video length (seconds)
  • enable_prompt_expansion: Enhances the prompt automatically and enables the safety checker

Prompting tips

  • Lead with action verbs (runs, spins, juggles, turns, laughs), then add camera language (pull back, track left, tilt up).
  • Keep one “main event” per clip; add atmosphere as a second layer (dust, fog, rim light, crowd).
  • If using an image, state what must stay consistent (character identity, outfit, composition) and what should change (motion, camera path, mood).
नोट:यह वेबसाइट तृतीय पक्षों द्वारा प्रदान किए गए AI मॉडलों का उपयोग करती है।

Video 02 API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/minimax/video-02 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 Video 02 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",
    "resolution": "768p",
    "duration": 6,
    "enable_prompt_expansion": false
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/minimax/video-02" \
  -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/video-02";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "resolution": "768p",
        "duration": 6,
        "enable_prompt_expansion": false
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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",
    "resolution": "768p",
    "duration": 6,
    "enable_prompt_expansion": False
}

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/video-02", 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)

Video 02 API — Frequently asked questions

What is the Video 02 API?

Video 02 is a MiniMax model for video generation from images, exposed as a REST API on WaveSpeedAI. Hailuo 02 is an AI video generation model fine-tuned for ultra-clear 1080P output and handling complex 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 Video 02 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-video-02.

How much does Video 02 cost per run?

Video 02 starts at $0.25 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 Video 02 accept?

Key inputs: `prompt`, `image`, `resolution`, `duration`, `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-video-02.

How long does Video 02 take to generate?

Median end-to-end generation time on WaveSpeedAI is around 137 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 Video 02 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.

Video 02 | Fast Image-to-Video API | WaveSpeedAI