post-prompt-inferences
Generate, complete, or invent new prompts for AI image generation using various modes like completion, contextual, inventive, or structured approaches.
Instructions
Generate, complete or invent new prompts.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| dryRun | No | ||
| mode | Yes | The mode used to generate new prompt(s). | |
| ensureIPCleared | No | Whether we try to ensure IP removal for new prompt generation. | |
| image | No | The input image as a data URL (example: "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVQYV2NgYAAAAAMAAWgmWQ0AAAAASUVORK5CYII=") or the asset ID (example: "asset_GTrL3mq4SXWyMxkOHRxlpw") Required when `mode` is `image-editing-prompt`. | |
| images | No | ||
| seed | No | If specified, the API will make a best effort to produce the same results, such that repeated requests with the same `seed` and parameters should return the same outputs. Must be used along with the same parameters including prompt, model's state, etc.. | |
| modelId | No | The modelId used to condition the generation. When provided, the generation will take into account model's training images, examples. Only supports 'gemini-2.0-flash', 'gemini-2.5-flash', 'gpt-image-1', 'flux-kontext' and 'runway-gen4-image' for now when `mode` is `image-editing-prompt`. | |
| temperature | No | The sampling temperature to use. Higher values like `0.8` will make the output more random, while lower values like `0.2` will make it more focused and deterministic. We generally recommend altering this or `topP` but not both. | |
| assetIds | No | ||
| numResults | No | The number of results to return. | |
| prompt | No | The initial prompt spark feed to `completion`, `inventive` or `structured` modes. | |
| topP | No | An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So `0.1` means only the tokens comprising the top `10%` probability mass are considered. We generally recommend altering this or `temperature` but not both. |