Wan 3.0

Wan 3.0 — multimodal: first/last frame or image/video/audio references, native audio, 2-30s at 480p/720p/1080p.

Wan 3.0 examples

Credits

Use Wan 3.0 in Nodaro

Add one of these nodes to your canvas, open its settings, and choose Wan 3.0 as the model:

• Generate Video
• Generate Video Pro

Run Wan 3.0 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 Wan 3.0 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/text-to-video \  -H "Authorization: Bearer $NODARO_API_KEY" \  -H "Content-Type: application/json" \  -d '{        "prompt": "A paper boat drifts down a rain-soaked street at dusk, slow dolly in",        "provider": "wan-3",        "duration": 5      }'

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("text-to-video", {  prompt: "A paper boat drifts down a rain-soaked street at dusk, slow dolly in",  provider: "wan-3",  duration: 5,})

{  "tool": "generate_video",  "arguments": {    "prompt": "A paper boat drifts down a rain-soaked street at dusk, slow dolly in",    "model": "wan-3",    "duration": 5  }}

Prompt tips

• Two INPUT MODES, exclusive on the wire: first/last frame, OR reference mode (images + videos + audio). With any reference wired the platform folds the frame into the references and names it in the prompt.
• References bind by ordinal token in array order: Image1, Image2, Video1, Audio1 — no space, unlike Wan 2.x's "Image 1". Name every wired asset or it may be ignored.
• Reference caps: 10 images / 5 videos / 5 audio clips; each video and each audio clip 1-15s, with ≤15s combined per array. With reference videos, input seconds + output duration ≤ 30.
• 2-30 seconds (default 5); 480p/720p/1080p; aspect adaptive (default, matches the input media) or 16:9 / 4:3 / 1:1 / 3:4 / 9:16. Prompt cap 20,000 chars — excess is truncated silently.
• Cue the sound you want in the prompt, or state the exclusion ("no music") — it is not a dialogue guarantee.
• wan-3-prime is the HIGH-SPEED tier: identical surface and limits, faster turnaround at a higher per-second rate. It is not a quality upgrade — choose it for latency, not for looks.

Similar models