img2img
Function
Interacts with foundation model services to generate images and obtains the model inference result. The format of the data sent to a foundation model is as follows:
The request body data format is as follows:
{
"prompt": prompt for generating an image,
"image": Base64-encoded image data,
"size": image size,
"model_name": model name
}
Prototype
def img2img(prompt, image_content, size)
Parameters
Parameter |
Data Type |
Required/Optional |
Description |
|---|---|---|---|
prompt |
str |
Required |
Prompt for generating an image. The length range is [1, 1024 × 1024]. |
image_content |
str |
Required |
Character string corresponding to the Base64 encoded image data. The length range is (0, 10 × 1024 × 1024]. |
size |
str |
Optional |
Image size, in the format of "height × width". The supported size depends on the corresponding foundation model. The value needs to meet the regular expression requirement "^\d{1,5}\*\d{1,5}$". The default value is 512 × 512. |
Return Value
Data Type |
Description |
|---|---|
dict |
The return format is {"prompt": prompt, "result": data}, where prompt indicates the prompt for generating an image, and result indicates the Base64-encoded image data of the foundation model inference result. |