Wan 2.7 T2V

Wan 2.7 text-to-video — 2–15s at 720p/1080p.

Credits

Use Wan 2.7 T2V in Nodaro

Add one of these nodes to your canvas, open its settings, and choose Wan 2.7 T2V as the model:

• Generate Video

Run Wan 2.7 T2V 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 2.7 T2V 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-2.7-t2v",        "duration": 2      }'

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-2.7-t2v",  duration: 2,})

{  "tool": "generate_video",  "arguments": {    "prompt": "A paper boat drifts down a rain-soaked street at dusk, slow dolly in",    "model": "wan-2.7-t2v",    "duration": 2  }}

Prompt tips

• Alibaba's official formula: Entity + Scene + Motion (basic) → add Aesthetic control + Stylization (advanced). Image-to-video: Motion + Camera only — the image already defines entity and scene.
• Sound (2.5+): append a sound description block — voice / sound effects / background music. Avoid scripting EXACT lip-synced lines (official anti-pattern); describe the voice and intent instead.
• Multi-shot (2.6/2.7): Overall description + shot number + timestamp + per-shot content. For ONE continuous take write 'Generate single shot' (the shot_type parameter is gone in 2.7).
• References go by 'Image 1' / 'Video 1' (capitalized, with a space). Anti-patterns: naming real people, demanding exact legible text, rapid scene changes in one clip, very long choreography.
• Style words are strong levers: cyberpunk, claymation, pixel style, felt style, tilt-shift, time-lapse. wan-videoedit: describe the transform, keep motion + identity.

Similar models