Seedance 2.5 अब उपलब्ध | वीडियो जनरेटर में आज़माएँ →
साइन इन

google/

Google Veo 3.1 Fast Reference to Video is a fast AI reference-to-video generation model that creates 8-second videos from up to three reference images using the official Veo predictLongRunning endpoint with referenceImages assets. Ready-to-use REST inference API for product videos, character consistency, branded visual storytelling, social media clips, advertising creatives, and professional reference-based video generation workflows with simple integration, no coldstarts, and affordable pricing.

image-to-video
इनपुट

निष्क्रिय

$0.64प्रति रन·~15 / $10

आगे:

उदाहरणसभी देखें

Use the first image as the main subject reference and the second image as the outfit reference. Preserve the same male model, pose, body proportions, camera angle, studio background, and lighting from the first image. Replace his current black leather outfit with the clothing from the second image: a clean white T-shirt, navy blue shorts, white sneakers, and a beige straw hat. Make the outfit fit naturally on his body while keeping the dynamic fashion pose. Maintain realistic fabric texture, natural folds, accurate shadows, and commercial fashion photography quality. The final image should look like a polished summer casual menswear campaign, photorealistic, high detail, clean studio look, no distortion, no extra limbs, no text, no logo.

संबंधित मॉडल

README

Google Veo 3.1 Fast Reference-to-Video

Google Veo 3.1 Fast Reference-to-Video generates an 8-second video guided by up to three reference images and a text prompt. It is designed for subject, object, and product consistency, making it useful for character-led shots, product motion, style-guided generation, and other reference-driven video workflows.

Why Choose This?

  • Reference-guided generation Use up to three reference images to preserve subject, object, or product identity in the generated video.

  • Fast Veo workflow Built on Google Veo 3.1 Fast for quicker turnaround and efficient iteration.

  • Consistent 8-second output Generates a fixed-length 8s MP4, making duration predictable for planning and pricing.

  • Flexible aspect ratio Supports both 16:9 and 9:16 for landscape and vertical video use cases.

  • Optional audio generation Enable generate_audio when you want the output to include generated sound.

  • Simple pricing Pricing depends only on resolution and whether audio generation is enabled.

Parameters

ParameterRequiredDescription
promptYesMotion, scene, and camera instructions.
imagesYes1–3 reference images. These are sent as asset reference images.
aspect_ratioNo16:9 or 9:16. Default: 16:9.
resolutionNo720p or 1080p. Default: 720p.
generate_audioNoWhether to generate audio. Default: false.
negative_promptNoThings to avoid in the video.
seedNoRandom seed for reproducibility.

How to Use

  1. Upload your reference images — provide 1–3 images for subject, style, or product guidance.
  2. Write your prompt — describe the motion, scene progression, camera movement, and overall visual intent.
  3. Set aspect ratio — choose 16:9 for landscape or 9:16 for vertical output.
  4. Choose resolution — use 720p for lower cost or 1080p for higher quality.
  5. Enable audio (optional) — turn on generate_audio if you want generated sound in the result.
  6. Add a negative prompt (optional) — describe elements or artifacts you want to avoid.
  7. Set a seed (optional) — use a fixed seed for more reproducible outputs.
  8. Submit — run the model and download the generated 8-second video.

Example Prompt

A cinematic product reveal of the same luxury watch from the reference images, rotating slowly on a reflective black surface, dramatic studio lighting, soft camera push-in, premium commercial style

Pricing

This model generates a fixed 8-second video.

ModeCost
720p without audio$0.64
720p with audio$0.80
1080p without audio$0.80
1080p with audio$0.96

Billing Rules

  • Output length is fixed at 8 seconds
  • 720p without audio costs $0.64
  • 720p with audio costs $0.80
  • 1080p without audio costs $0.80
  • 1080p with audio costs $0.96
  • Pricing depends only on resolution and generate_audio
  • aspect_ratio, negative_prompt, seed, and the number of reference images do not affect pricing

Best Use Cases

  • Product motion videos — Generate controlled product shots from reference images.
  • Character consistency — Keep the same subject identity across a short generated clip.
  • Style-guided generation — Use references to anchor visual style, mood, or composition.
  • Marketing creatives — Produce short polished clips for ads, social media, and promotional assets.
  • Vertical content — Generate 9:16 outputs for short-form mobile platforms.

Pro Tips

  • Use clear, high-quality reference images for stronger identity preservation.
  • Keep the reference images visually consistent when you want the subject or product to remain stable.
  • Be specific in your prompt about motion, camera movement, and scene intent.
  • Use negative_prompt to reduce unwanted style drift or artifacts.
  • Enable audio only when you actually need it, since it changes pricing.
  • Reuse the same seed when you want more reproducible generations.

Notes

  • Both prompt and images are required.
  • This workflow supports up to 3 reference images.
  • The model uses the official Veo 3.1 Fast long-running generation flow with referenceImages added to the request payload.
  • Output duration is fixed at 8 seconds.
  • generate_audio defaults to false.

Related Models

  • Other Google Veo 3.1 Fast video generation variants may be useful when you need text-to-video or non-reference workflows.
नोट:यह वेबसाइट तृतीय पक्षों द्वारा प्रदान किए गए AI मॉडलों का उपयोग करती है। दस्तावेज़ की कीमतें केवल संदर्भ के लिए हैं और पुरानी हो सकती हैं। Generate बटन अनुमान दिखाता है; टास्क का अंतिम शुल्क ही मान्य होगा।

Veo3.1 Fast Reference To Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/google/veo3.1-fast/reference-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 Veo3.1 Fast Reference 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",
    "images": [
        "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
    ],
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "generate_audio": false,
    "seed": -1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/google/veo3.1-fast/reference-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/google/veo3.1-fast/reference-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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "images": [
                "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
        ],
        "aspect_ratio": "16:9",
        "resolution": "720p",
        "generate_audio": false,
        "seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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",
    "images": [
        "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
    ],
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "generate_audio": False,
    "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/google/veo3.1-fast/reference-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)

Veo3.1 Fast Reference To Video API — Frequently asked questions

What is the Veo3.1 Fast Reference To Video API?

Veo3.1 Fast Reference To Video is a Google model for video generation from images, exposed as a REST API on WaveSpeedAI. Google Veo 3.1 Fast Reference to Video is a fast AI reference-to-video generation model that creates 8-second videos from up to three reference images using the official Veo predictLongRunning endpoint with referenceImages assets. Ready-to-use REST inference API for product videos, character consistency, branded visual storytelling, social media clips, advertising creatives, and professional reference-based video generation workflows with simple integration, no coldstarts, and affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Veo3.1 Fast Reference 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/google/google-veo3.1-fast-reference-to-video.

How much does Veo3.1 Fast Reference To Video cost per run?

Veo3.1 Fast Reference To Video starts at $0.64 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 Veo3.1 Fast Reference To Video accept?

Key inputs: `prompt`, `images`, `aspect_ratio`, `resolution`, `seed`, `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/google/google-veo3.1-fast-reference-to-video.

How long does Veo3.1 Fast Reference To Video take to generate?

Median end-to-end generation time on WaveSpeedAI is around 55 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 Veo3.1 Fast Reference To Video outputs commercially?

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

Veo3.1 Fast Reference to Video | Fast Image-to-Video API on WaveSpeedAI