Picsart API Platform
← All models

Luma Ray 3.2

Luma · Video · Text → Video

Luma Ray 3.2 — high-fidelity video generation with start/end frames, HDR, and looping (early access).

Model ID: luma-ray-3.2Workflow: luma-ray32-video
Image InputStart/End FrameHDR5/10 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 'luma-ray32-video' workflow directly — params are sent as-is.
const { result, usage } = await ai.apis.run('luma-ray32-video', {
  prompt: "A serene mountain lake at golden hour, ultra detailed"
}, {
  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('luma-ray32-video', {
  prompt: "A serene mountain lake at golden hour, ultra detailed"
}, {
  mode: ApiRunMode.ASYNC,
});

console.log(result);

Parameters

5 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
Prompt describing the video (1-6000 characters)
stringyes
aspect_ratio
Output aspect ratio. Model selects when omitted.
stringno
9:163:41:14:316:921:9
user_id
Stable opaque end-user identifier (no PII), ≤256 chars.
stringno
video
Video output options
objectno
resolution
Output resolution. 540p is not available with hdr=true.
stringno
540p720p1080p
duration
Clip duration. 10s is not supported with hdr, start_frame, or end_frame.
stringno
5s10s
hdr
Generate an HDR-encoded MP4. Access-gated; requires 720p/1080p; not supported with 10s, loop, or extend.
booleanno
exr_export
Export an EXR file alongside the MP4. Requires hdr=true; not supported on extend/reframe.
booleanno
loop
Generate a seamless loop. Not supported with 10s, hdr, or end_frame; on extend, forward-only.
booleanno
start_frame
First frame: image ref ({url}|{data,media_type}) or {generation_id} for forward extend. Not supported with 10s.
objectno
url
Publicly accessible URL of the frame image
stringno
data
Base64-encoded frame image data. Requires media_type.
stringno
media_type
Media type when data is provided (e.g. "image/png")
stringno
generation_id
Chain reference to a prior generation (extend / keyframe)
stringno
end_frame
Last frame: image ref ({url}|{data,media_type}) or {generation_id} for backward extend. Generation-only; not supported with 10s. Two generation_id keyframes are rejected (interpolate-from-generation unsupported).
objectno
url
Publicly accessible URL of the frame image
stringno
data
Base64-encoded frame image data. Requires media_type.
stringno
media_type
Media type when data is provided (e.g. "image/png")
stringno
generation_id
Chain reference to a prior generation (extend / keyframe)
stringno
options
GenAI options (safety checks, Picsart Drive)
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": 1
  }
}