describe

Describes an image with an LLM Interrogator.

Signature:

client.images.describe(input: DescribePredictionRequest): Promise<DescribePredictionResponse>

• input: { run_id: string; model?: string }
  • run_id: The ID of the run whose image should be described
  • model (optional): The model to use for description (e.g., 'llava13b', 'clip')
• Returns: { replicate_output: any } (see types for full schema)
• Throws: On validation, network, or API error.

Example

const client = new ImagineoAIClient(apiUrl, { apiKey: 'sk-...' });
const result = await client.images.describe({
  run_id: '123e4567-e89b-12d3-a456-426614174000',
  model: 'llava13b',
});
console.log(result.replicate_output);

Notes

• Input is validated with Zod (DescribePredictionRequestSchema).
• Makes a POST request to /api/v1/describe.
• See the API Reference for details.