Vidu Q4

Vidu Q4 — start-frame or reference-driven video (up to 15 reference images + 3 MP3 voice/sound clips), native audio, 3-16s at 540p to 4K.

Credits

Use Vidu Q4 in Nodaro

Add one of these nodes to your canvas, open its settings, and choose Vidu Q4 as the model:

• Generate Video
• Generate Video Pro

Run Vidu Q4 from code

Each call starts a job and returns its jobId. Poll GET /v1/jobs/:id/status, or let the SDK wait for the result. A run costs the credits on this page. API reference

With Nodaro connected to Claude, ChatGPT or Cursor, ask in plain words, or have the assistant call the tool: “Use Vidu Q4 to make: A paper boat drifts down a rain-soaked street at dusk, slow dolly in”

curl -s -X POST https://app.nodaro.ai/v1/generate-video \  -H "Authorization: Bearer $NODARO_API_KEY" \  -H "Content-Type: application/json" \  -d '{        "imageUrl": "https://example.com/first-frame.png",        "prompt": "A paper boat drifts down a rain-soaked street at dusk, slow dolly in",        "provider": "vidu-q4",        "duration": 3      }'

import { createClient, StaticTokenAuth } from "@nodaro/sdk"const client = createClient({  baseUrl: "https://app.nodaro.ai",  auth: new StaticTokenAuth(process.env.NODARO_API_KEY!),})const output = await client.nodes.runAndWait("generate-video", {  imageUrl: "https://example.com/first-frame.png",  prompt: "A paper boat drifts down a rain-soaked street at dusk, slow dolly in",  provider: "vidu-q4",  duration: 3,})

{  "tool": "animate_image",  "arguments": {    "image_url": "https://example.com/first-frame.png",    "prompt": "A paper boat drifts down a rain-soaked street at dusk, slow dolly in",    "model": "vidu-q4",    "duration": 3  }}

Prompt tips

• A start frame alone animates that frame (prompt optional). Any reference image or audio switches to reference mode: the prompt is REQUIRED and the start frame joins the reference images.
• Reference mode: 1-15 images, up to 3 audio clips (MP3 only, 3-12s each). Name each by ordinal — "the man from @image_2 says … in the voice of @audio_1".
• No text-only runs and no end frame: wire a start frame or at least one reference image.
• 3-16s (default 5); 540p / 720p (default) / 1080p / 2K / 4K; reference runs take 16:9 / 9:16 / 1:1 / 4:3 / 3:4. Prompt cap 20,000 chars.
• Cue the sound you want or state the exclusion; dialogue is not verified here, so plan key lines as a TTS + lip-sync pass.

Similar models