Options for the Image Generation tool.
interface ImageGenerationOptionsWhether to generate a new image or edit an existing image.
generate: Generate a new image from scratchedit: Edit an existing imageauto: Let the model decide based on the inputBackground type for the generated image.
transparent: Generate image with transparent backgroundopaque: Generate image with opaque backgroundauto: Let the model decide based on the promptControl how much effort the model will exert to match the style and features,
especially facial features, of input images. This parameter is only supported
for gpt-image-1. Unsupported for gpt-image-1-mini.
high: Higher fidelity to input imageslow: Lower fidelity to input imagesOptional mask for inpainting. Use this to specify areas of an image that should be regenerated.
The image generation model to use.
Moderation level for the generated image.
auto: Standard moderationlow: Less restrictive moderationCompression level for the output image (0-100). Only applies to JPEG and WebP formats.
The output format of the generated image.
Number of partial images to generate in streaming mode (0-3). When set, the model will return partial images as they are generated, providing faster visual feedback.
The quality of the generated image.
low: Faster generation, lower qualitymedium: Balanced generation time and qualityhigh: Slower generation, higher qualityauto: Let the model decide based on the promptThe size of the generated image.
1024x1024: Square format1024x1536: Portrait format1536x1024: Landscape formatauto: Let the model decide based on the prompt