Asynchronous Image Editing Call 2.5

Positive prompt, used to describe the desired elements and visual features to be included in the generated image. Supports Chinese and English, with a maximum length of 2000 characters, where each Chinese character or letter counts as one character, and any excess will be automatically truncated.

Negative prompt, used to describe unwanted content in the image to constrain the generation. Supports both Chinese and English, with a maximum length of 500 characters; any excess will be automatically truncated. Example values: low resolution, errors, worst quality, low quality, deformed, extra fingers, bad proportions, etc.

Set the resolution of the output image in the format of widthheight. The default value is 12801280. Image resolution: total pixels must be within [768768, 12801280], and the aspect ratio must be within [1:4, 4:1]. Example value: 12801280. Recommended resolutions and corresponding aspect ratios: 12801280: 1:1, 10241024: 1:1, 8001200: 2:3, 1200800: 3:2, 9601280: 3:4, 1280960: 4:3, 7201280: 9:16, 1280720: 16:9, 1344576: 21:9. If size is not specified, the system will default to generating an image with a total of 1280*1280 pixels and maintain the aspect ratio (approximate) according to the following rules: Single-image input: the aspect ratio matches the input image; Multi-image input: the aspect ratio matches the last input image.

The number of images to generate. Valid values range from 1 to 4, with a default of 4. To control costs, it is recommended to explicitly set this to 1 during testing.

Specifies whether to add a watermark. The watermark is located in the bottom right corner of the image with the fixed text "AI-generated". false: Default value, no watermark is added. true: Watermark is added.

Whether to enable intelligent prompt rewriting. When enabled, a large model intelligently rewrites the input prompt to improve overall performance, but it increases latency. true: Default value, enables intelligent rewriting. false: Disables intelligent rewriting.

The random seed, with a value range of [0, 2147483647]. If not provided, the algorithm automatically generates a random number as the seed. If provided, the seed parameter is generated for each of the n images based on the value of n; for example, if n=4, the algorithm will generate images using seed, seed+1, seed+2, and seed+3 as parameters, respectively. To improve the reproducibility of the generated results, it is recommended to use a fixed seed value. Please note that due to the probabilistic nature of model generation, identical results cannot be guaranteed every time even with the same seed.