promptstring·required- The positive prompt for the generation.
imageslist of string·required- The images to edit. A maximum of 10 reference images can be uploaded.Up to 10 items
aspect_ratiochoice- The aspect ratio of the generated image. Leave empty to automatically use the closest supported aspect ratio based on the first input image.One of: 1:1, 1:2, 2:1, 1:3, 3:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 9:21, 21:9
resolutionchoice- The output resolution tier used for billing. 1k is the lower-cost tier; 2k is the higher-cost tier.One of: 1k, 1.5k, 2kDefault: 1k
output_formatchoice- The format of the output image.One of: jpeg, pngDefault: jpeg
prompt_optimization_modechoice- Prompt optimization mode. The model rewrites your prompt before generating. 'standard' uses the full rewrite; 'fast' uses a lighter one that generates several times quicker but follows long or intricate prompts less closely.One of: standard, fastDefault: standard
enable_sync_modeboolean- If set to `true`, the request attempts to wait for the generated result and return outputs in the same response. If the result is not ready within the sync wait window, the API can return a timeout body while the task continues processing. This option is only available via the API and is supported only by some models.Default: false
enable_base64_outputboolean- If set to `true`, the prediction's `output` strings are returned as **naked base64** (no `data:<mime>;base64,` prefix). When `false` (default), outputs are returned as URLs pointing to our CDN.Default: false