Skip to main content
DeepInfra supports the OpenAI-compatible image generation API. The default model is FLUX Schnell. The endpoint is:
Browse all text-to-image models.

Example

Supported parameters

ParameterNotes
promptText description of the image
modelDefaults to FLUX Schnell
sizeImage dimensions (e.g., "1024x1024")
nNumber of images to generate
response_formatOnly b64_json supported
quality, styleAvailable for compatibility only

LoRA image adapters

You can also use custom LoRA adapters for image generation — see LoRA for Image Generation.

Tutorial

For a deeper example including advanced options, see the Stable Diffusion tutorial.