Generate Image with API

Generate and edit images and variations

The Generate Image with AI step allows you to create, edit, or generate variations of images directly within your AirOps workflows.

Generate Image

Popular AI Models for Image Generation

AirOps offers the following AI models for image generation:

Model	Provider	Description
GPT Image 2.5 Sunburst	OpenAI	Image generation and editing focused on precision
GPT Image 2.5 Flare	OpenAI	Fast image generation and editing for everyday use
GPT Image 2	OpenAI	Image generation with existing GPT Image 2 controls
GPT Image 1.5	OpenAI	Previous-generation OpenAI text-to-image model
Nano Banana Pro (gemini-3-pro-image)	Google	Advanced text-to-image with 4K support and superior text rendering
Nano Banana 2 (gemini-3.1-flash-image)	Google	Fast image generation with image-editing support
Stable Image Ultra	Stability AI	Highest quality photorealistic image generation
Stable Diffusion 3.5 Large	Stability AI	Balanced speed and quality for digital content

Nano Banana Pro offers multiple resolutions up to 4K, improved text rendering, and better style consistency. Note that it is approximately 4x more expensive than other image generation models.

The Gemini 3 preview model IDs have been retired. Workflows that used gemini-3-pro-image-preview or gemini-3.1-flash-image-preview automatically move to the corresponding GA model listed above.

DALL·E models have been deprecated and are no longer available in the model picker. Workflows that previously generated images, edited images, or generated variations with DALL·E should migrate to one of the models listed above.

GPT Image 2.5 controls

Choose GPT Image 2.5 Sunburst or GPT Image 2.5 Flare, then select dimensions and Low, Medium, High, or Auto quality. The 16:9 and 9:16 1K presets use 1536×864 and 864×1536, respectively.

Existing GPT Image 2 steps keep their model and configuration. Select a GPT Image 2.5 model explicitly when you want to use it in a Workflow.

Edit Images

Choose an image-editing-capable model, such as GPT Image 2.5 Sunburst, GPT Image 2.5 Flare, or Nano Banana 2, when you want to revise an existing image. Available controls can vary by model.

Provide the source image as either:

1. A "File Media" Workflow Input variable
2. A publicly accessible URL with a .png endpoint

For models that support mask-based editing, provide an Image Mask URL with the same dimensions as the source image. Transparent areas identify where the image can change.

Generate Variations

The DALL·E 2-specific variations flow is no longer available. To produce alternate versions, generate again with a revised prompt or use an image-editing-capable model when you need to preserve elements of a source image.

If you choose to generate multiple images, the output is returned as JSON with an accessible URL for each generated image.