Vidu Q4 is ShengShu's newest video model, released in November 2026. It works two ways: it animates a single image used as the first frame, or it builds a clip from 2-15 reference images - characters, products, places - that you call out in the prompt by order. Reference mode also takes up to 3 audio clips (MP3, 3-12 s each). Clips run 3 to 16 seconds at 540p, 720p, 1080p, 2K or 4K, with generated audio on by default. It does not do pure text-to-video - use Vidu Q3 Pro for that.
Best for
- Keeping one character or product consistent across shots from several photos
- Bringing a packshot or a photo to life without changing the framing
- 9:16 and 16:9 ads with sound in one pass
- 2K and 4K shots for big-screen edits
Prompting tips
- With references, be explicit: "the character from image 1 holds the product from image 2" - order matters.
- With a single start frame the prompt is optional; describe motion and camera. The image sets the aspect ratio.
- A single image in
image_urlsis treated as a first frame - send at least 2 for reference mode. - Test motion at 540p, render the final at 1080p or 4K.
FAQ
How much does the Vidu Q4 API cost?
The rate depends on resolution, from $0.116 per second at 720p. Audio does not change it and failed generations are not charged. The cost calculator shows 540p, 2K and 4K.
Can Vidu Q4 make video from text only?
No. It needs at least one image - a start frame or references.
How many reference images does it take?
From 2 to 15.
How to call Vidu Q4 via API
curl https://jantaris.com/v1/generate?wait=60 \
-H "Authorization: Bearer $JANTARIS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "vidu-q4",
"input": {
"prompt": "A slow dolly shot through a neon-lit night market in the rain, reflections on wet asphalt, cinematic",
"aspect_ratio": "16:9",
"resolution": "720p",
"duration": 5
}
}'import os, time, requests
API = "https://jantaris.com/v1"
H = {"Authorization": f"Bearer {os.environ['JANTARIS_API_KEY']}"}
task = requests.post(f"{API}/generate", headers=H, json={
"model": "vidu-q4",
"input": {
"prompt": "A slow dolly shot through a neon-lit night market in the rain, reflections on wet asphalt, cinematic",
"aspect_ratio": "16:9",
"resolution": "720p",
"duration": 5
}
}).json()
while task["status"] in ("queued", "running"):
time.sleep(3)
task = requests.get(f"{API}/tasks/{task['id']}", headers=H).json()
print(task["status"], task["cost"], [o["url"] for o in task["output"]])const API = "https://jantaris.com/v1";
const headers = { Authorization: `Bearer ${process.env.JANTARIS_API_KEY}`, "Content-Type": "application/json" };
let task = await (await fetch(`${API}/generate`, {
method: "POST",
headers,
body: JSON.stringify({
"model": "vidu-q4",
"input": {
"prompt": "A slow dolly shot through a neon-lit night market in the rain, reflections on wet asphalt, cinematic",
"aspect_ratio": "16:9",
"resolution": "720p",
"duration": 5
}
}),
})).json();
while (task.status === "queued" || task.status === "running") {
await new Promise((r) => setTimeout(r, 3000));
task = await (await fetch(`${API}/tasks/${task.id}`, { headers })).json();
}
console.log(task.status, task.cost, task.output.map((o) => o.url));Parameters
| Parameter | Type | Allowed | Default |
|---|---|---|---|
prompt | string | ≤ 20000 chars | |
aspect_ratio | string | 16:9 9:16 1:1 4:3 3:4 | 16:9 |
resolution | string | 540p 720p 1080p 2K 4K | 720p |
duration | integer | 3-16 | 5 |
generate_audio | boolean | true | |
image_url | string | ||
image_urls | array | max 15 | |
audio_urls | array | max 3 | |
seed | integer |
The same schema is available from GET /v1/models/vidu-q4.