Picsart API Platform
← All models

Wan 2.7 Ref-to-Video

Popular

Wan · Video · Video → Video

Wan 2.7 R2V — generate video from reference images/video with style direction.

Model ID: wan-2.7-r2vWorkflow: wan/v2/reference-to-video
Multi-Image InputVideo Input1080P5/10 sec
Try on Playground ↗

Overview

Alongside the unified model APIs, we expose compatibility APIs that take each vendor's original parameters exactly as the vendor defines them — nothing renamed, nothing reshaped on the way through.

That makes them the shortest path onto Picsart if you already work with the vendor directly: the request bodies you've already written keep working as they are. You keep their parameter names and defaults, and you get the vendor's full parameter set rather than the subset that is shared across every model.

The cost is that a request is written for one vendor — switching models later means rewriting it, and results come back in the vendor's own shape. When you'd rather write once and change models freely, use the unified API.

Make a request

Call the workflow with ai.apis.run() in TypeScript, or hit /workflows/{workflow}/execute directly — params is passed through untouched either way.

These endpoints are addressed by workflow name rather than model id: the one in this model's header, since one model runs as one workflow. Authentication is unchanged — your Picsart API key as a bearer token (see Authentication).

ts
import { createClient, ApiRunMode } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY,
  apiUrl: 'https://api.green-salad-4efd.toolsminati.workers.dev',
});

// Calls the 'wan/v2/reference-to-video' workflow directly — params are sent as-is.
const { result, usage } = await ai.apis.run('wan/v2/reference-to-video', {
  prompt: "A serene mountain lake at golden hour, ultra detailed",
  media: [
    {
      type: "reference_image",
      url: "your value here"
    }
  ]
}, {
  mode: ApiRunMode.SYNC,
});

console.log(result); // workflow-specific output
console.log(usage?.credits); // credits charged

Async (submit & poll)

This model can run longer than the sync limit (~20s). In TypeScript, ai.apis.run(…, { mode: ApiRunMode.ASYNC }) polls for you; over HTTP, submit and poll yourself.

ts
import { createClient, ApiRunMode } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY,
  apiUrl: 'https://api.green-salad-4efd.toolsminati.workers.dev',
});

// mode: ASYNC submits the job and polls under the hood — you just await.
const { result } = await ai.apis.run('wan/v2/reference-to-video', {
  prompt: "A serene mountain lake at golden hour, ultra detailed",
  media: [
    {
      type: "reference_image",
      url: "your value here"
    }
  ]
}, {
  mode: ApiRunMode.ASYNC,
});

console.log(result);

Parameters

11 parameters, sent inside params. These are the vendor's own names, so they line up one-for-one with the vendor's documentation. Required ones must be supplied; the rest fall back to their defaults.

ParameterTypeRequiredDefaultDetails
prompt
Text prompt describing desired video content and character actions. Use "Image 1", "Image 2", "Video 1" to reference characters by order in media array. Chinese and English supported. Max 5000 chars, auto-truncated if exceeded.
stringyes
media
Array of reference media (images and/or videos) for character appearance and voice. reference_image: JPEG/JPG/PNG/BMP/WEBP, [240-8000]px, max 20 MB. reference_video: MP4/MOV, 1-30s, [240-4096]px, max 100 MB. Total reference images + videos <= 5. At most 1 first_frame.
WanV2R2VMediaItem[]yes
type
Media asset type. reference_image: character/scene reference image. reference_video: character + voice reference video. first_frame: optional first frame to generate from.
stringyes
reference_imagereference_videofirst_frame
url
URL of the media asset (HTTP/HTTPS).
stringyes
reference_voice
Optional voice reference audio attached to this media item. Formats: WAV, MP3. Duration: 1-10s. Max size: 15 MB.
objectno
url
URL of the voice reference audio file. Formats: WAV, MP3. Duration: 1-10s. Max size: 15 MB. Takes precedence over reference_video audio.
stringyes
negative_prompt
Negative prompt to exclude unwanted content. Max 500 chars, auto-truncated if exceeded.
stringno
prompt_extend
Enable LLM prompt rewriting for quality improvement. Vendor default: true.
booleanno
model
Model name. Deployed in the International (Singapore) region.
stringnowan2.7-r2v
wan2.7-r2v
resolution
Resolution tier controlling video clarity. Default: 1080P. Affects cost.
stringno1080P
720P1080P
ratio
Aspect ratio of the generated video. Default: 16:9. Ignored if first_frame is provided.
stringno16:9
16:99:161:14:33:4
duration
Video duration in seconds. Range: 2-10 with a reference_video, 2-15 with image-only references. Default: 5. Affects cost.
numberno
watermark
Add "AI Generated" watermark in the lower-right corner. Default: false.
booleannofalse
seed
Random seed for reproducibility (0-2147483647). If omitted, system generates a random seed. Identical seeds do not guarantee identical results.
numberno
options
GenAI options for safety checks and Drive saving.
objectno
safety_checks
Safety check settings
objectno
enabled
Whether to run content moderation. Defaults to true.
booleanno
drive
Save result to Picsart Drive
objectno
name
File name in Picsart Drive
stringyes
attributes
Custom attributes to attach to the file
objectno
folder
Target folder in Picsart Drive
objectno
inputs_transformation
Input transformation settings
objectno
downscale_oversized_images
Whether to downscale oversized input images. Defaults to false.
booleanno

Response

Over HTTP the output arrives inside a status envelope, at response.result. ai.apis.run() unwraps that envelope for you and resolves to { result, usage } instead. Either way the resultitself is the vendor's own shape.

json
{
  "result": {
    "url": "https://cdn.green-salad-4efd.toolsminati.workers.dev/…/result.mp4",
    "mimeType": "video/mp4",
    "driveFile": {}
  },
  "usage": {
    "credits": 3
  }
}