Seedream 5.0 Pro ya está aquí | Pruébalo en el Generador de Imágenes →

Vidu Reference to Video Q1

vidu /

Generate videos from reference images while keeping characters, objects, and scene identity consistent using Multi-Entity Consistency. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

image-to-video
Entrada

Inactivo

$0.4por ejecución·~25 / $10

Siguiente:

EjemplosVer todo

the girl in image 2 wear the glasses in image 1

A man is catwalking with a bag that has a reference picture.

A beautiful woman wearing clothes similar to the reference image, paired with jeans, walks towards the camera.

Figure 1 is fixed on the tea tray in Figure 2, the teapot is stationary, the size ratio refers to the white teapot in Figure 2, the lens slowly zooms in, focusing on the teapot in Figure 1.

The same product with the background changed to image 2.

A character walks two steps naturally towards the camera, then strikes some poses.

A character walks two steps naturally.

A character wearing the clothes from Figure 1 walks two steps naturally towards the camera, then strikes some poses.

The model in Figure 1, with a fairer complexion and a very thin figure, wears the clothes in Figure 2, walks naturally in front of a solid color background, and poses with the camera fixed, showing the whole body

the girl in image one wear the necklace in image 2

the girl in image 1 wear the cloth in image 2

Modelos relacionados

README

Vidu Reference-to-Video Q1

Vidu Reference-to-Video Q1 generates high-quality 5-second videos guided by multiple reference images. It combines advanced appearance preservation and motion synthesis, allowing creators to animate characters, products, or scenes while maintaining their original identity and style.

🌟 Key Features

🔁 Multi-Entity Consistency

  • Preserves the visual identity, color tone, and texture of all reference subjects.
  • Supports consistent appearance across dynamic motion sequences.
  • Ideal for animating characters, fashion items, or branded products.

🧩 Flexible Input Options

  • Accepts 1–7 reference images to define the subject, outfit, or style.
  • Supports aspect ratios 16:9, 9:16, and 1:1.
  • Adjustable movement amplitude (auto, small, medium, large) for customized motion intensity.

🎥 Cinematic Motion Generation

  • Adds smooth camera motion and ambient scene transitions.
  • Creates realistic parallax effects and subject movement.
  • Works well with both portraits and product shots.

⚙️ Requirements

Images

  • Count: 1–7 reference images
  • Formats: PNG, JPEG, JPG
  • Aspect ratio: Between 1:4 and 4:1
  • Max file size: 50 MB per image

Prompt

  • Max length: 1500 characters
  • Describe desired motion, scene, or style.

Example: “The girl in image 2 wears the glasses from image 1 and walks through a sunny street, soft natural light, cinematic color tone.”

💰 Price

DurationResolutionCost per job
5 seconds720p$0.40

💡 Best Practices

  1. Use clear, high-resolution reference images for optimal appearance consistency.
  2. Describe the desired motion and scene context in detail.
  3. Experiment with movement amplitude to adjust animation style.
  4. Include multiple reference images for complex scenes or multi-object compositions.
  5. Keep visual themes consistent (lighting, color palette, resolution).

⚠️ Effect Boundaries

  • Works best with realistic, well-lit images.
  • Overly stylized or low-quality inputs may cause flickering or distortion.
  • Movement amplitude directly affects scene dynamics and smoothness.
  • Complex multi-character prompts may require more references for stability.

📝 Notes

  • Make sure each uploaded image is accessible and properly formatted.
  • Check that the prompt and image order correspond correctly (e.g., “image 1,” “image 2”).
  • If outputs look inconsistent, simplify the scene or reduce reference count.
  • Simple, focused prompts yield the best alignment and motion results.
Nota:Este sitio web utiliza modelos de IA proporcionados por terceros.

Reference To Video Q1 API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/vidu/reference-to-video-q1 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 Reference To Video Q1 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",
    "movement_amplitude": "auto",
    "seed": 0
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/vidu/reference-to-video-q1" \
  -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/vidu/reference-to-video-q1";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "images": [
                "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
        ],
        "aspect_ratio": "16:9",
        "movement_amplitude": "auto",
        "seed": 0
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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",
    "movement_amplitude": "auto",
    "seed": 0
}

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/vidu/reference-to-video-q1", 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)

Reference To Video Q1 API — Frequently asked questions

What is the Reference To Video Q1 API?

Reference To Video Q1 is a Vidu model for video generation from images, exposed as a REST API on WaveSpeedAI. Generate videos from reference images while keeping characters, objects, and scene identity consistent using Multi-Entity Consistency. 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 Reference To Video Q1 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/vidu/vidu-reference-to-video-q1.

How much does Reference To Video Q1 cost per run?

Reference To Video Q1 starts at $0.40 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 Reference To Video Q1 accept?

Key inputs: `prompt`, `images`, `aspect_ratio`, `seed`, `movement_amplitude`. 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/vidu/vidu-reference-to-video-q1.

How long does Reference To Video Q1 take to generate?

Median end-to-end generation time on WaveSpeedAI is around 169 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 Reference To Video Q1 outputs commercially?

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

Vidu Reference to Video Q1 | Fast Image-to-Video API | WaveSpeedAI