generateImage

function generateImage<TAdapter, TStream>(options): ImageActivityResult<TStream>;

Defined in: packages/ai/src/activities/generateImage/index.ts:249

Image activity - generates images from text prompts.

Uses AI image generation models to create images based on natural language descriptions.

Type Parameters

TAdapter

TAdapter extends ImageAdapter<string, any, any, any, ModelInputModalitiesByName>

TStream

TStream extends boolean = false

Parameters

options

ImageActivityOptions<TAdapter, TStream>

Returns

ImageActivityResult<TStream>

Examples

Generate a single image

import { generateImage } from '@tanstack/ai'
import { openaiImage } from '@tanstack/ai-openai'

const result = await generateImage({
  adapter: openaiImage('gpt-image-2.5-flare'),
  prompt: 'A serene mountain landscape at sunset',
  threadId,
})

console.log(result.images[0].b64Json)

Generate multiple images

const result = await generateImage({
  adapter: openaiImage('gpt-image-1-mini'),
  prompt: 'A cute robot mascot',
  threadId,
  numberOfImages: 4,
  size: '1024x1024'
})

result.images.forEach((image, i) => {
  console.log(`Image ${i + 1}: ${image.b64Json}`)
})

With provider-specific options

const result = await generateImage({
  adapter: openaiImage('gpt-image-2.5-flare'),
  prompt: 'A professional headshot photo',
  threadId,
  size: '1024x1024',
  modelOptions: {
    quality: 'high',
    background: 'transparent'
  }
})