Vidu Q3 Reference-to-Video Mix generates multi-entity consistent videos from 1-4 reference images with text prompt guidance. Supports 360p to 1080p resolutions, up to 16 seconds duration, multiple aspect ratios, and optional audio generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.35per run·~28 / $10
The violinist plays, eyes unfocused — until he glances down and sees the girl watching. He falters for just a fraction of a second, then plays more deliberately. His posture changes slightly. The girl doesn't blink. Her mother gently tugs her hand to leave, but she resists, planted. The musician's expression softens almost imperceptibly. Camera slowly racks focus from the crowd to the two of them. The world rushes on around a quiet moment of connection.
Her hands tremble almost imperceptibly as she reads. A single tear escapes and falls onto the letter, blurring the ink. She closes her eyes briefly, lips pressed together. The candle flame flickers in a draft. Rain intensifies against the window. Camera slowly pushes in toward her face. No music needed — silence tells the story. Emotionally devastating, restrained performance.
He taps the delivery app frantically — the estimated arrival time keeps going up. The dragon in front exhales a small frustrated puff of smoke. A witch cuts in from the side lane; he honks his broom (a little bell rings). He looks into the camera with dead eyes. Camera slowly pulls back to reveal how insane the aerial traffic jam is. Somewhere below, a customer is leaving a 1-star review in real time.
Vidu Q3 Reference-to-Video generates cinematic video guided by multiple reference images and a text prompt. Upload one or more reference images to establish character identity, style, or scene elements — the model produces a cohesive, motion-consistent video that blends all provided references into a new scene.
Multi-image reference generation Upload multiple reference images to combine characters, styles, or visual elements from different sources into a single coherent video.
Character-consistent output The model preserves the identity, appearance, and style of subjects from your reference images throughout the generated clip.
Optional audio generation Enable generate_audio to produce synchronized ambient sound and atmosphere alongside the video.
Flexible resolution options Generate at 480p, 720p, or 1080p to match your quality and budget requirements.
Reproducible results Use the seed parameter to lock in a specific output for exact reproduction.
Prompt Enhancer Built-in tool to automatically improve your scene descriptions for richer output.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the scene, action, and atmosphere. |
| images | Yes | One or more reference images. Click Add Item to include additional images. |
| aspect_ratio | No | Output aspect ratio. Default: 16:9. |
| resolution | No | Output resolution: 480p, 720p (default), or 1080p. |
| duration | No | Clip length in seconds. Default: 5. |
| generate_audio | No | Whether to generate synchronized audio for the video. Default: enabled. |
| seed | No | Random seed for reproducible results. |
| Duration | 480p | 720p / 1080p |
|---|---|---|
| 5s | $0.35 | $0.77 |
| 10s | $0.70 | $1.54 |
| 15s | $1.05 | $2.31 |
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/vidu/q3/reference-to-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Q3 Reference To Video below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"aspect_ratio": "16:9",
"resolution": "720p",
"duration": 5,
"generate_audio": true
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/vidu/q3/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
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/vidu/q3/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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"aspect_ratio": "16:9",
"resolution": "720p",
"duration": 5,
"generate_audio": true
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${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));
}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",
"duration": 5,
"generate_audio": True
}
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/q3/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)Q3 Reference To Video is a Vidu model for video generation from images, exposed as a REST API on WaveSpeedAI. Vidu Q3 Reference-to-Video Mix generates multi-entity consistent videos from 1-4 reference images with text prompt guidance. Supports 360p to 1080p resolutions, up to 16 seconds duration, multiple aspect ratios, and optional audio generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
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-q3-reference-to-video.
Q3 Reference To Video starts at $0.35 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.
Key inputs: `prompt`, `images`, `aspect_ratio`, `resolution`, `duration`, `seed`. 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-q3-reference-to-video.
Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.
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.