TTttapi

POST /flux/edits

Generate new images based on text prompts and uploaded reference images

Request

Request body multipart/form-data

promptstring required

Text prompt describing the desired edit. GPT Image models support up to 32,000 characters; dall-e-2 supports up to 1,000 characters.

background'transparent' | 'opaque' | 'auto'

Sets the transparency of the output image background. Applies only to GPT Image models. Choose transparent, opaque, or auto (default). Transparent backgrounds require png or webp output format.

input_fidelity'high' | 'low'

Controls how closely the output preserves details from the input image. Choose high or low; defaults to low. Applies only to GPT Image models.

model'gpt-image-1.5' | 'gpt-image-1' | 'gpt-image-2' required

The model to use for image editing.

moderation'low' | 'auto'

Moderation level for GPT Image models. Choose low or auto.

ninteger

Number of images to generate, default 1. Available range 1-10.

output_compressioninteger

Compression level for generated images (0-100). Applies only to GPT Image models with output_format set to webp or jpeg; defaults to 100.

output_format'png' | 'jpeg' | 'webp'

Return format for generated images. Applies only to GPT Image models. Choose png (default), jpeg, or webp.

partial_imagesinteger

Number of partial images to return in the streaming response, from 0 to 3; defaults to 0. Available only when stream is true.

qualitystring

Image quality. auto (default) automatically selects the best quality for the model.

GPT Image models support high, medium, and low;

dall-e-2 only supports standard.

response_format'url' | 'b64_json'

Return data format. Only dall-e-2 supports url or b64_json; URLs are valid for 60 minutes. GPT Image models always return b64_json.

sizestring

Image size.

GPT Image models support 1024x1024, 1536x1024, 1024x1536, and auto (default);

dall-e-2 supports 256x256, 512x512, 1024x1024.

streamboolean

Whether to stream edit progress. When enabled, use partial_images to receive partial image events.

userstring

A unique identifier representing your end-user, which can help OpenAI monitor and detect abuse.

Response

Request successful

statusstring required
messagestring required
dataobject required

Example response

{
  "status": "SUCCESS",
  "message": "success",
  "data": {
    "jobId": "jobId"
  }
}

Changes

No recorded changes to this operation across all 1 revision of this API.