Seedream 5.0 Pro jest już LIVE | Wypróbuj w Generator obrazów →

MiniMax H3 Image-to-Video Open Weights

wavespeed-ai/

MiniMax H3 Open Weights Image to Video animates a first-frame image, optionally with last-frame guidance, into coherent 480P / 768P videos with native stereo audio, 5-15 second duration, flexible aspect ratios, and per-second billing. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

image-to-video
Wejście

Bezczynny

$0.2za uruchomienie·~50 / $10

Dalej:

PrzykładyZobacz wszystkie

A cinematic 5-second boxing training video. Maintain the exact same female boxer from the reference image: a blonde female athlete with braided hair, white hand wraps, white sports top, realistic athletic physique, detailed skin texture, visible sweat, focused and determined expression. Keep the exact same: - face identity - hairstyle - outfit - body proportions - character appearance SCENE: Inside the same old-school boxing gym. A large brown heavy punching bag hangs in front of her. Background: boxing ring, worn concrete walls, old training equipment, soft sunlight coming through the windows, floating dust particles, realistic cinematic atmosphere. --- 0-1.5s: Side medium close-up shot. The female boxer stands in front of the heavy bag in a professional boxing stance. She takes a deep breath and focuses intensely on the target. Her shoulders and arms are tense. Sweat reflects naturally on her skin. The camera slowly pushes in with a cinematic handheld feeling. --- 1.5-4s: She launches into a fast and powerful boxing combination. She performs: - quick jab - strong cross punch - rapid follow-up combination Every punch has realistic body mechanics: shoulder rotation, hip movement, foot adjustment, proper boxing technique. The heavy bag reacts naturally to each impact and swings realistically. Her blonde braids move with the motion. The white hand wraps remain detailed and realistic. Camera: dynamic tracking shot following her punches, slight handheld movement, cinematic sports advertisement style. --- 4-5s: Low-angle cinematic hero shot. She lands one final powerful punch. The heavy bag swings backward from the impact. She returns to her boxing stance, breathing heavily. She looks forward with confidence and determination. The camera makes a subtle orbit around her as sunlight highlights her face and sweat. --- STYLE: Ultra-realistic cinematic sports film. Hollywood boxing training scene. Premium sports advertisement visual style. Realistic human movement and body mechanics. Detailed sweat, skin texture, muscle movement. 35mm film lens. Shallow depth of field. Natural dramatic lighting. Handheld camera feeling. Smooth continuous motion. NEGATIVE PROMPT: No character change. No face change. No hairstyle change. No clothing change. No extra people. No distorted hands. No deformed fingers. No unrealistic punching movements. No changing background. No random camera cuts. No cartoon style. No exaggerated visual effects. Maintain realistic boxing motion and cinematic continuity.

A cinematic wildlife macro video of a green jungle lizard hiding among tropical leaves. The camera stays extremely close to the lizard's face. The lizard slowly blinks, its eye moves naturally watching the camera, tiny facial muscles move, then it quickly sticks out its long tongue to taste the air and retracts it. The head slightly turns, showing detailed scales and realistic reptile movement. Dense rainforest background, soft natural sunlight, realistic wildlife documentary footage, macro lens, shallow depth of field, ultra realistic.

Powiązane modele

README

MiniMax H3 Image-to-Video (Open Weights)

Run the open-weights edition of MiniMax H3 on WaveSpeedAI's own GPU infrastructure. This endpoint is separate from the official minimax/h3 API: same model family, independently hosted, with its own 480p/768p resolutions and per-second pricing.

MiniMax H3 is an omni-modal video model that generates picture and native stereo audio in a single pass — dialogue, sound effects, and music are produced together during generation, never added as a separate dubbing step. Give it a first-frame image plus a prompt and it animates the scene with a matching soundtrack.

How to Write a Great Prompt

The image sets the look; the prompt directs the motion and the sound over time. Write it as a timeline, not a one-line description:

  1. Motion timeline — timestamped beats: "[0s-2s] she breathes and blinks … [2s-5s] a warm smile as the camera pushes in …". Beats keep the animation moving instead of drifting.
  2. Camera — state it explicitly, including when it should hold: "slow push-in, then lock off, no cuts".
  3. Audio — put every sound in an Audio: line with entrance cues: "Audio: quiet room tone, a soft piano melody that swells at 3s." Omit this and the model picks a soundtrack for you.
  4. On-screen text — spell out any readable words in quotes and add "do not add other text, no subtitles."

First / last frame (optional) — supply last_image to lock the ending; the model generates the motion between the first and last frames. Great for a controlled emotional arc.

Tips

  • Use clear, well-lit images; the output canvas follows the input image's aspect ratio.
  • Verbs beat adjectives — write the action, not just the mood.
  • Iterate at 5s, then deliver at your final length; a short negative list ("no extra people, no cuts") is free.

Parameters

ParameterRequiredDescription
promptYesDesired motion, camera movement, and an Audio: line for the soundtrack.
imageYesFirst-frame image URL. The output canvas follows this image's aspect ratio.
last_imageNoOptional last-frame image URL. When set, the video interpolates from the first frame to this frame.
resolutionNo480p (faster, lower cost) or 768p (native canvas). Default: 480p.
durationNoOutput length in seconds, 515. Default: 5.
seedNoFixed seed for reproducible output.

Specifications

ItemDetail
OutputMP4 with native stereo audio
Frame rate24 fps
Resolution480p or 768p
Duration515 seconds (snaps to the model's frame grid, so a 5s request lands at ~5.2s)
InputFirst-frame image (optional last frame for interpolation)
SeedSupported

Pricing

Billed per generated second:

ResolutionPrice per second5s15s
480p$0.04$0.20$0.60
768p$0.08$0.40$1.20
Uwaga:Ta strona korzysta z modeli AI udostępnianych przez podmioty trzecie.

Minimax H3 Image To Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/minimax-h3/image-to-video 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 Minimax H3 Image To Video 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",
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "resolution": "480p",
    "duration": 5,
    "seed": -1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/minimax-h3/image-to-video" \
  -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/wavespeed-ai/minimax-h3/image-to-video";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "resolution": "480p",
        "duration": 5,
        "seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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",
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "resolution": "480p",
    "duration": 5,
    "seed": -1
}

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/wavespeed-ai/minimax-h3/image-to-video", 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)

Minimax H3 Image To Video API — Frequently asked questions

What is the Minimax H3 Image To Video API?

Minimax H3 Image To Video is a WaveSpeedAI model for video generation from images, exposed as a REST API on WaveSpeedAI. MiniMax H3 Open Weights Image to Video animates a first-frame image, optionally with last-frame guidance, into coherent 480P / 768P videos with native stereo audio, 5-15 second duration, flexible aspect ratios, and per-second billing. 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 Minimax H3 Image To Video 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/wavespeed-ai/minimax-h3-image-to-video.

How much does Minimax H3 Image To Video cost per run?

Minimax H3 Image To Video starts at $0.20 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 Minimax H3 Image To Video accept?

Key inputs: `prompt`, `image`, `resolution`, `duration`, `seed`, `last_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/wavespeed-ai/minimax-h3-image-to-video.

How long does Minimax H3 Image To Video take to generate?

Median end-to-end generation time on WaveSpeedAI is around 222 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 Minimax H3 Image To Video outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

MiniMax H3 Image-to-Video Open Weights API on WaveSpeedAI