batch_generate
Process a list of prompts in parallel batches to generate multiple images with consistent settings.
Instructions
Generate multiple images from a list of prompts efficiently.
Processes prompts in parallel batches for optimal performance. All images share the same generation settings.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| prompts | Yes | List of text descriptions for image generation | |
| batch_size | No | Parallel batch size (default: from config) | |
| image_size | No | Image resolution for all images (default: 2K) | 2K |
| aspect_ratio | No | Aspect ratio for all images (default: 1:1) | 1:1 |
| output_format | No | Image format for all images (default: png) | png |
| thinking_level | No | Thinking level - "minimal" or "high" | minimal |
| preserve_original | No | ||
| alpha_output_format | No | png | |
| enable_image_search | No | Enable Google Image Search | |
| response_modalities | No | Response types (TEXT, IMAGE) | |
| enable_google_search | No | Enable Google Web Search grounding | |
| reference_image_paths | No | Shared reference image path(s), up to 14. | |
| transparent_background | No | Set True to get ready-to-use transparent PNG/WebP cut-outs for EVERY prompt via the two-pass difference matte (each prompt costs a second edit-to-black model call). The alpha file for each image is returned as "transparent_path"; pick the alpha format with alpha_output_format ("png"/"webp"). |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |