post-reframe-inferences
Reframe images to new sizes while intelligently filling extra space based on context, using AI to maintain visual coherence during resizing.
Instructions
Reframe a given image to new sizes. Extra space is filled based on the context.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| originalAssets | No | If set to true, returns the original asset without transformation | |
| dryRun | No | ||
| image | Yes | The image to reframe. Must reference an existing AssetId or be a data URL. | |
| inputLocation | No | Location of the input image in the output. | |
| seed | No | Used to reproduce previous results. Default: randomly generated number. | |
| horizontalExpansionRatio | No | (deprecated) Horizontal expansion ratio. | |
| negativePrompt | No | (deprecated) A negative full text prompt that discourages the repaint from generating certain characteristics. It is recommended to test without using a negative prompt. | |
| resizeOption | No | Size proportion of the input image in the output. | |
| verticalExpansionRatio | No | (deprecated) Vertical expansion ratio. | |
| targetHeight | Yes | The target height of the output image. | |
| concepts | No | ||
| numInferenceSteps | No | The number of denoising steps for each image generation. | |
| promptFidelity | No | Increase the fidelity to the prompt during the restyle. | |
| overlapPercentage | No | Overlap percentage for the output image. | |
| prompt | No | A full text prompt to guide the repaint process. | |
| targetWidth | Yes | The target width of the output image. |