Platform
Checking your session…
← All models

MiniMaxMiniMax H3 Context IRVideo → Text

MiniMax H3 Context IR — enhances a video prompt from text plus optional first/last frame, reference images, videos, and audio. Returns an enhanced prompt, not a video.

VisionVideo InputAudio InputStart/End Frame

Install the SDK

The SDK targets Node 20+ and ships with TypeScript types.

npm install @picsart/ai-sdk

Authenticate

Create a client once with your API key — it's sent as a bearer token on every request.

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

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY, // sent as: Authorization: Bearer <key>
  apiUrl: 'https://api.picsart.com',
});

Run the model

Call the model with its parameters. This example uses the required ones.

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

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY,
  apiUrl: 'https://api.picsart.com',
});

const { text } = await ai.generateText('minimax-h3-context-ir', {
  prompt: "A serene mountain lake at golden hour, ultra detailed",
  duration: 5,
  aspectRatio: "adaptive"
});

console.log(text);

Parameters

8 parameters. Required ones must be supplied; the rest fall back to their defaults. The API takes these same names over HTTP.

ParameterTypeRequiredDefaultDetails
prompt
Prompt
textyes——
startFrame
Start Frame
file (image)no——
endFrame
End Frame
file (image)no——
imageUrls
Reference Images
file (image[])no——
videoUrls
Reference Videos
file (video[])no——
audioUrls
Reference Audios
file (audio[])no——
durationrangeno54–15 (step 1)
aspectRatioenumnoadaptiveadaptive, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16

Output

generateText() resolves to the generated text plus the raw response.

Result
{
  "text": "…generated text…",
  "model": "minimax-h3-context-ir"
}