Overview
Create an edited or extended version of an existing image. Upload an image and provide a text prompt describing the desired changes.
The image to edit. Must be a valid PNG file, less than 4MB, and square. If
mask is not provided, image must have transparency.
A text description of the desired edit (Prompt) (max 1000 characters)
An additional image whose fully transparent areas indicate where to edit
(Mask)
The model to use (e.g. dall-e-2)
The number of images to generate (1-10)
The size of the generated images: 256x256, 512x512 or 1024x1024
The format in which the generated images are returned: url or b64_json
curl -X POST "https://api.applerouter.ai/v1/images/edits/" \
-H "Authorization: Bearer sk-your-api-key" \
-F "image=@image.png" \
-F "prompt=A cute baby sea otter wearing a beret" \
-F "n=1" \
-F "size=1024x1024"
{
"created": 1713833628,
"data": [
{
"url": "https://example.com/edited-image.png"
}
]
}
使用 Bearer Token 认证。格式: Authorization: Bearer sk-xxxxxx
要编辑的图像。必须是有效的 PNG 文件,小于 4MB,并且是方形的。如果未提供遮罩,图像必须具有透明度,将用作遮罩。
所需图像的文本描述。最大长度为 1000 个字符。
Example:"A cute baby sea otter wearing a beret."
附加图像,其完全透明区域(例如,alpha 为零的区域)指示image应编辑的位置。必须是有效的 PNG 文件,小于 4MB,并且尺寸与原始image相同。
生成图像的大小。必须是256x256、512x512或 1024x1024之一。
生成的图像返回的格式。必须是url或b64_json。
代表您的最终用户的唯一标识符,可以帮助 OpenAI 监控和检测滥用行为。了解更多。
The response is of type object.