Minimax Hailuo 02 I2V Standard

Minimax Hailuo 02 I2V Standard

Playground

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.

Features

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)

1. Upload image (and optional end_image).
2. Add a concise prompt with motion + lighting + mood.
3. Choose duration (6s / 10s).
4. (Optional) Keep prompt expansion on for cleaner results.
5. Click Run.

Pricing

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.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "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/hailuo-02/i2v-standard" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(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' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  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

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters