LIliara-cloud
Image Generations

Generate images

Generates images from a text prompt. Supports models from OpenAI (gpt-image-1, gpt-image-2) and Google Gemini (Gemini image models).

OpenAI models accept size values like 1024x1024, 1536x1024, 1024x1536, or auto. Gemini models accept aspect ratio values like 1:1, 2:3, 16:9, etc.

post/api/{workspaceID}/v1/images/generations

Request

  • Base URL
    https://ai.liara.ir
  • URL
    https://ai.liara.ir/api/{workspaceID}/v1/images/generations
  • Auth
    API key in header Authorization

Path parameters

workspaceIDstring required

The workspace ID

Request body

promptstring required

Text description of the desired image

modelstring required

Image generation model ID. Supported models:

  • google/gemini-2.5-flash-image
  • google/gemini-3-pro-image-preview
  • openai/gpt-image-2
  • openai/gpt-image-1.5
  • openai/gpt-image-1
  • openai/gpt-image-1-mini
nnumber

Number of images to generate (1-10)

sizestring

Image size. OpenAI: auto, 1024x1024, 1536x1024, 1024x1536. Gemini: aspect ratios like 1:1, 2:3, 16:9.

qualitystring

Image quality. OpenAI: auto, low, medium, high. Gemini: 1K, 2K, 4K.

backgroundstring

Background setting

moderationstring

Content moderation level

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

Output image format

output_compressionnumber

Compression level for jpeg/webp

partial_imagesnumber

Number of partial images for progressive loading

response_formatstring

Response format (url or b64_json)

streamboolean

Enable streaming

stylestring

Image style

userstring

End-user identifier

Response

Successful response

idstring

Log ID

createdinteger

Changes

No recorded changes to this operation across all 4 revisions of this API.