Vidu Q2 Text-to-Video turns text prompts into high-quality videos with exceptional visual fidelity and diverse motion. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Boşta
$0.1çalıştırma başına·~10 / $1
Style: anime, hand-drawn aesthetic, emotional lighting. Setting: high-school rooftop at sunset, wind blowing. Beats: [0–2.0s] two students stand apart, sky painted orange; [2.0–3.8s] girl’s hair and skirt sway, eyes shimmering; [3.8–5.0s] she smiles, mouths “thank you” as petals drift away. Lighting: soft sunset gradient, rim light on hair strands, cinematic depth. Negative: no crowd, no modern city ads, no noise artifacts.
Style: anime fantasy, glowing particle FX, fluid camera. Setting: a girl in a dark forest surrounded by floating runes. Beats: [0–1.5s] she opens her eyes, blue glyphs ignite around; [1.5–3.5s] hair rises, cloak flutters, runes orbit her body; [3.5–5.0s] camera pulls back as a massive energy ring bursts outward. Look: luminous blues and golds, strong rim lighting, spark trails. Negative: no smoke fog covering face, no flickering frame skip.
Style: Western fantasy animation, DreamWorks-style with soft realism. Setting: deep forest at dawn, glowing mushrooms and rays of light. Beats: [0–2.0s] a small elf wakes, blinking in sunlight through canopy; [2.0–4.0s] she touches a wilted flower—energy spark revives it; [4.0–6.5s] animals gather, curious and gentle; [6.5–8.0s] camera rises as forest glows emerald and gold. Lighting: natural volumetric rays, slight particle bloom, ethereal tone. Negative: no modern elements, no excessive motion blur, no shadows hiding face.
A continuous medium shot on a misty train platform. A younger hand lets go of an older person's hand. The younger person steps onto the train just as the doors close. As the train begins to pull away slowly, the camera slowly pushes in on the older person left standing alone on the platform, watching the train depart, their face full of emotion as steam from the train blows past them. Melancholy, minimalist piano melody. The loud, mournful sound of a steam train whistle, and the rhythmic chugging of the wheels.
A wizard's hand quickly sketches a circle in the air with a glowing finger; the circle flashes brightly and a real, tiny blue bird flies out of it. Mystical whoosh, fantasy sound effect, high-pitched harp arpeggio.
Vidu Q2 Text-to-Video turns your text prompts into short cinematic clips with coherent motion, balanced lighting, and reliable scene composition. It supports style presets, multiple aspect ratios, motion intensity control, and optional background music — ideal for ads, social posts, explainers, and animation creation.
Fast, stable motion Clear details and smooth camera paths without flicker or artifacts.
Style presets Choose between general and animate modes for different creative directions.
Animation optimized Specifically tuned for high-quality animation creation.
Motion amplitude control Dial in subtle vs. energetic movement to match your vision.
Optional background music Auto-generate BGM for instant, shareable clips.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Describe subject, setting, lighting, camera, and action |
| style | No | Style preset: general or animate |
| resolution | No | Output resolution: 540p, 720p, or 1080p |
| duration | No | Video length in seconds (1–10) |
| aspect_ratio | No | Aspect ratio: 4:3 or 3:4 |
| movement_amplitude | No | Motion intensity: low, medium, or high |
| bgm | No | Enable background music generation |
| seed | No | Random seed for reproducibility (-1 for random) |
| Resolution | Duration | Price |
|---|---|---|
| 540p | 1s | $0.05 |
| 540p | 2s | $0.06 |
| 540p | 3s | $0.07 |
| 540p | 4s | $0.08 |
| 540p | 5s | $0.09 |
| 540p | 6s | $0.10 |
| 540p | 7s | $0.11 |
| 540p | 8s | $0.12 |
| 540p | 9s | $0.22 |
| 540p | 10s | $0.32 |
| 720p | 1s | $0.075 |
| 720p | 2s | $0.10 |
| 720p | 3s | $0.125 |
| 720p | 4s | $0.15 |
| 720p | 5s | $0.175 |
| 720p | 6s | $0.20 |
| 720p | 7s | $0.225 |
| 720p | 8s | $0.25 |
| 720p | 9s | $0.35 |
| 720p | 10s | $0.45 |
| 1080p | 1s | $0.10 |
| 1080p | 2s | $0.15 |
| 1080p | 3s | $0.20 |
| 1080p | 4s | $0.25 |
| 1080p | 5s | $0.30 |
| 1080p | 6s | $0.35 |
| 1080p | 7s | $0.40 |
| 1080p | 8s | $0.45 |
| 1080p | 9s | $0.55 |
| 1080p | 10s | $0.60 |
540p: $0.05 for 1s, +$0.01/s up to 8s, then $0.22 for 9s, $0.32 for 10s
720p: $0.075 for 1s, +$0.025/s up to 8s, then $0.35 for 9s, $0.45 for 10s
1080p: $0.10 for 1s, +$0.05/s up to 8s, then $0.55 for 9s, $0.60 for 10s
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/vidu/text-to-video-q2 with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Text To Video Q2 below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"style": "general",
"resolution": "720p",
"duration": 5,
"aspect_ratio": "4:3",
"movement_amplitude": "auto",
"bgm": true
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/vidu/text-to-video-q2" \
-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/text-to-video-q2";
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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"style": "general",
"resolution": "720p",
"duration": 5,
"aspect_ratio": "4:3",
"movement_amplitude": "auto",
"bgm": true
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${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",
"style": "general",
"resolution": "720p",
"duration": 5,
"aspect_ratio": "4:3",
"movement_amplitude": "auto",
"bgm": 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/text-to-video-q2", 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)Text To Video Q2 is a Vidu model for video generation, exposed as a REST API on WaveSpeedAI. Vidu Q2 Text-to-Video turns text prompts into high-quality videos with exceptional visual fidelity and diverse motion. 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-text-to-video-q2.
Text To Video Q2 starts at $0.10 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`, `aspect_ratio`, `resolution`, `duration`, `seed`, `bgm`. 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-text-to-video-q2.
Median end-to-end generation time on WaveSpeedAI is around 45 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
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.