GPT Image 1.5 Edit

gpt_image_1_5_edit

High-quality image editing model for generating edited images from input images and text prompts.

Endpoints

POST /v1/queue/gpt_image_1_5_edit # Create task

GET /v1/queue/gpt_image_1_5_edit/requests/{request_id}/status # Check status

GET /v1/queue/gpt_image_1_5_edit/requests/{request_id}/response # Get result

PUT /v1/queue/gpt_image_1_5_edit/requests/{request_id}/cancel # Cancel task

Request parameters

curl --location "https://cloud.seaart.ai/model/v1/queue/gpt_image_1_5_edit" \
  --header "Authorization: Bearer YOUR_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "prompt": "A clean product photo of a red apple on a white table, soft studio lighting.",
    "images": ["https://example.com/input.png"],
    "background": "auto",
    "n": 1,
    "output_compression": 90,
    "output_format": "jpeg",
    "quality": "medium",
    "size": "1024x1024",
    "moderation": "auto"
  }'

prompt string required

Text description of the desired edited image, with a maximum length of 32000 characters.

images any required

Input image references for editing, with up to 16 input images supported.

mask any

Mask image reference for selecting editable regions. Transparent areas are treated as editable. Provide either file_id or image_url. The mask should match the edited image format and dimensions and include an alpha channel. The maximum length of image_url is 20971520.

background string

Background transparency setting.

Options: transparent, opaque, auto

Default: auto

input_fidelity string

Controls how strongly original input image details are preserved.

Options: high, low

Default: low

n int

Number of edited images to generate.

Range: 1 - 10

Default: 1

output_compression int

Output compression level. Only applies when output_format is jpeg or webp. For example, output_compression=50 compresses the output image by 50%.

Range: 0 - 100

Default: 100

output_format string

Returned image format. jpeg is usually faster than png/webp. When output_format is jpeg or webp, use output_compression to control compression.

Options: png, jpeg, webp

Default: png

quality string

Image quality level.

Options: low, medium, high, auto

Default: auto

size string

Generated image size.

Options: 1024x1024, 1024x1536, 1536x1024, auto

Default: auto

moderation string

Content moderation strictness for GPT Image generation requests.

Options: auto, low

Default: auto

user string

Unique identifier representing the end user.

Response parameters

{
  "request_id": "mmsu_01hxyz...",
  "response_url": "https://cloud.seaart.ai/model/v1/queue/gpt_image_1_5_edit/requests/mmsu_01hxyz.../response",
  "status_url": "https://cloud.seaart.ai/model/v1/queue/gpt_image_1_5_edit/requests/mmsu_01hxyz.../status",
  "cancel_url": "https://cloud.seaart.ai/model/v1/queue/gpt_image_1_5_edit/requests/mmsu_01hxyz.../cancel",
  "queue_position": 0
}

Field	Type	Description
`request_id`	string	Task ID used for all follow-up operations.
`response_url`	string	URL to fetch the final result.
`status_url`	string	URL to query task status.
`cancel_url`	string	URL to cancel the task.
`queue_position`	int	Current queue position.

Follow-up operations

Check status

Get result

Cancel task

Error handling