Skip to content

Fast & easy AI image generation Stable Diffusion API

[NEW] The high-resolution Stable Diffusion XL model is now available! Generate images with breathtaking clarity and unparalleled detail.

See API Reference section at /text2image_sdxl for more details.

This API provides fast priority processing by utilizing the same infrastructure that drives the web app.

  • Fast: powered by datacenter-grade GPUs
  • 📈 Scalable: your requests are automatically distributed to multiple machines
  • ⛱️ Easy to use: no need to manage complex hardware or software configuration, we take care of everything
  • 🖌️ 72 models: ready to use, covering a wide range of styles.
  • 🎨 Customizable: import Lora models to guide the AI towards custom characters, styles, objects or concepts.
  • 💸 Pay-As-You-Go: only pay for the resources that you use, no recurring monthly payments, no expiring credits

Enjoy several awesome AI's like:

  • text-to-image: create a brand new image from a text description
  • controlnet: create an image that matches the structure of a sample image
  • image-to-image: reshape an existing image according to a text description
  • inpainting / text-inpainting: replace a part of an existing image by something else
  • edit-image : edit an image according to text instructions, while preserving its structure
  • upscaling : increase image resolution in a smart way


With default settings:

  • $0.0019 USD - 512x512 pixels with /text2image
  • $0.0179 USD - 1024x1024 pixels with /text2image_sdxl

Find more details on the Pricing page.