Seedance 2.5 現已上線 | 在影片生成器中體驗 →

kwaivgi/

Kling 2.1 Master is a premium image-to-video endpoint delivering fluid motion, cinematic visuals, and precise prompt-driven control. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.

image-to-video
輸入

就緒

$1.3每次運行

下一步:

示例查看全部

A mysterious woman reading a spellbook in a dark forest, camera circles her, magical lights floating, trees slowly twisting, glowing runes appear

A ballerina dancing in an abandoned theater, spotlight follows her movements, dramatic angles, particles of dust in the air, emotional climax

Time-lapse of a bustling Tokyo street, fast-moving crowds, night turning into day, camera transitions to aerial view, dynamic rhythm

A steampunk train departing the station, close-up of gears turning, steam rising, transition to wide landscape shot with mechanical city

A sorcerer unleashing lightning into the sky, storm clouds swirl, cinematic lighting flashes, camera flies around the scene, slow motion impact

A dragon flying over a burning village, camera switches between ground panic and dragon POV, fire and wind effects, epic soundtrack feel

Two friends riding bicycles through the countryside, clouds moving overhead, smiling faces, grass swaying

A teenage boy sits by the window in the summer rain, headphones on, eyes closed, head bobbing to the music, raindrops streaming down the window glass

A lonely girl sitting on a swing at dusk, orange and pink sky behind her, gentle breeze moving the swing, camera stays at eye level with soft focus on her expression

A clay animation boy flying across a surreal rainbow sky on a paper airplane. The camera tracks from below as he glides over soft, fluffy clouds. The vibrant colors shift with the lighting, and the boy turns his head joyfully, waving to the viewer as stars twinkle around him.

A vibrant animated sequence featuring a stylized toy-like girl character with oversized sunglasses and a neon sports outfit. She confidently walks through a pastel-colored street filled with candy-shaped buildings. The camera follows her from behind, then swings around to reveal her smiling face under the flickering neon lights.

A cinematic slow zoom-in on a young Asian woman in a white shirt standing on the rooftop edge, her hair fluttering in the soft sunset breeze. The urban skyline stretches behind her, bathed in golden hour light. The camera gently shifts from her back to a side profile, capturing her calm expression as she overlooks the city.

相關模型

README

Kling v2.1 I2V Master — kwaivgi/kling-v2.1-i2v-master

Kling v2.1 I2V Master generates short, high-motion video clips from a single reference image plus a motion-focused prompt. Upload an image, describe what moves (subject, camera, environment), and the model animates the scene while keeping the source frame as the visual anchor. Built for stable production use with a ready-to-use REST API, no cold starts, and predictable pricing.

What it’s best at

  • Image-to-video generation with strong visual anchoring to the input image
  • Cinematic motion: camera moves, parallax, atmospheric effects, subtle facial/body motion
  • Prompt-controlled animation with optional negative_prompt to suppress artifacts
  • Fast iteration for 5-second clips (and longer durations if enabled)

Pricing

Equivalent unit price: $0.26 per second

Examples

DurationPrice
5s$1.30
10s$2.60
15s$3.90
20s$5.20

Inputs

  • image (required): the reference image used as the first-frame anchor
  • prompt (required): describe motion and camera behavior
  • negative_prompt (optional): describe what to avoid (blur, distortions, artifacts)

Parameters

  • prompt: the motion direction for the clip
  • negative_prompt: optional “avoid list” (quality issues, unwanted elements)
  • image: the input image (upload or URL)
  • guidance_scale: how strongly the motion follows the prompt (lower = more natural drift, higher = stricter prompt following)
  • duration: video length in seconds (commonly in 5-second steps)

Prompting guide (I2V)

Write prompts like a director’s brief, prioritizing motion over static description:

  • Subject motion: head turn, breathing, hair flutter, hand movement, walking, reading, etc.
  • Environment motion: wind in trees, dust, rain, fog, floating particles, light beams
  • Camera motion: slow push-in, orbit, handheld micro-shake, tilt up, dolly left, rack focus
  • Continuity constraints: keep identity, outfit, and scene layout consistent with the input image

Good pattern: A short description of the scene, then explicit motion cues, then camera movement, then mood/lighting continuity.

Example prompts

  • A mysterious woman reading a spellbook in a dark forest. Camera slowly circles her, faint magical lights float around, glowing runes appear, trees subtly twist in the background, cinematic mist and particles, moody low-key lighting, smooth motion, 5 seconds.
  • A street portrait at golden hour. Subtle breeze moves hair and clothes, soft lens flare, gentle handheld camera sway, shallow depth of field, natural facial micro-expressions, 5 seconds.
  • A product shot on a table. Camera slow push-in, specular highlights glide across the surface, light dust motes in the air, clean studio feel, crisp focus, 5 seconds.

Negative prompt examples

  • blur, distort, low quality
  • jitter, warping, melted details, extra limbs, duplicate face
  • watermark, logo, subtitles, text artifacts, compression blocks

Best practices

  • Use a sharp, well-lit reference image; the model can’t “invent” clean details that aren’t there.
  • Keep motion instructions compatible with the image (don’t ask for a full outfit change if you only want animation).
  • If results look unstable or over-animated, lower guidance_scale and simplify motion.
  • If motion is too subtle, add clearer action verbs (turns, steps, lifts, sways) and specify a camera move.
提示:本網站部分功能由第三方 AI 模型提供支援。文件價格僅供參考,可能已過時。Generate 按鈕顯示預估價格,最終以任務實際收費為準。

Kling v2.1 I2v Master API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/kwaivgi/kling-v2.1-i2v-master 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 Kling v2.1 I2v Master 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",
    "guidance_scale": 0.5,
    "duration": 5
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-v2.1-i2v-master" \
  -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/kwaivgi/kling-v2.1-i2v-master";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "guidance_scale": 0.5,
        "duration": 5
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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",
    "guidance_scale": 0.5,
    "duration": 5
}

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/kwaivgi/kling-v2.1-i2v-master", 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)

Kling v2.1 I2v Master API — Frequently asked questions

What is the Kling v2.1 I2v Master API?

Kling v2.1 I2v Master is a Kuaishou model for video generation from images, exposed as a REST API on WaveSpeedAI. Kling 2.1 Master is a premium image-to-video endpoint delivering fluid motion, cinematic visuals, and precise prompt-driven control. Ready-to-use REST API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Kling v2.1 I2v Master 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/kwaivgi/kwaivgi-kling-v2.1-i2v-master.

How much does Kling v2.1 I2v Master cost per run?

Kling v2.1 I2v Master starts at $1.30 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 Kling v2.1 I2v Master accept?

Key inputs: `prompt`, `image`, `duration`, `guidance_scale`, `negative_prompt`. 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/kwaivgi/kwaivgi-kling-v2.1-i2v-master.

How long does Kling v2.1 I2v Master take to generate?

Median end-to-end generation time on WaveSpeedAI is around 472 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 Kling v2.1 I2v Master outputs commercially?

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

Kling V2.1 I2V Master | Fast Image-to-Video API on WaveSpeedAI