create-visual
Generate images from text, edit existing visuals, or search for inspiration on the web and academic papers. Supports standard sizes and formats.
Instructions
Create, edit, or search for visual content. Supports three modes: generate (create images from text), edit (modify existing images), and search (find visual inspiration from the web). Note: Supported image sizes are 1024x1024, 1536x1024, 1024x1536, or auto - custom sizes like 512x512 are not available.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | Yes | Operation mode: generate new images, edit existing images, or search for visual inspiration | |
| prompt | Yes | Text description of the desired visual or search query | |
| model | No | Image model to use (generate/edit modes only) | |
| size | No | Image dimensions (generate/edit modes only). IMPORTANT: Only these sizes are supported by the GPT Image API. Other sizes like 512x512 are not available. Use 1024x1024 for square images. | |
| quality | No | Rendering quality (generate/edit modes only) | |
| background | No | Background transparency (generate/edit modes only) | |
| outputFormat | No | Output image format (generate/edit modes only) | |
| outputCompression | No | Compression level for JPEG/WebP (generate/edit modes only) | |
| partialImages | No | Number of partial images for streaming (generate/edit modes only) | |
| n | No | Number of images to generate (generate/edit modes only) | |
| inputImages | No | Input images as base64 strings or file IDs (edit mode only) | |
| inputImageMask | No | Optional mask image for inpainting (edit mode only) | |
| inputFidelity | No | Input image detail preservation level (edit mode only) | |
| searchMode | No | Search domain: web or academic papers (search mode only) | |
| searchRecencyFilter | No | Filter results by recency (search mode only) |