Documentation Index

Fetch the complete documentation index at: https://cloudinary.com/documentation/llms.txt

Use this file to discover all available pages before exploring further.

Image & Video APIs

Generative AI transformations

Last updated: Jul-24-2026

Cloudinary's generative AI transformations let you create production-ready modifications to your images using natural language. Describe what you want in plain words and Cloudinary generates a realistic result on the fly, with no manual editing or design tools required.

Because each transformation is just a URL parameter, you can apply these modifications at scale across your entire media library. For example, generate the same product shot in multiple colors, remove unwanted items from a whole catalog of images, or extend thousands of images to new aspect ratios, all automatically.

You can use natural language in most of these transformations as prompts to guide the generation process.

Tip
To generate entirely new images from text prompts rather than transforming existing ones, see Image Generation.

Here are some examples of generative AI transformations on the same image. Click each image to see the URL parameters applied in each case:

Recolor the shorts Recolor the
shorts
Extend the image Extend the
image
Replace the shirt Replace the
shirt

The sections below introduce each generative AI transformation with an example. Follow the links for full how-to details and important considerations for each one.

Tip
See AI in Action for more uses of AI within Cloudinary.

Generative background replace (Beta)

Use AI to generate an alternative background for your images, with or without a natural language prompt. The new background takes into account the foreground elements, positioning them naturally within the scene.

Original image Original image Background replaced Replace background with "an old castle"

Learn more: Generative background replace.

Generative fill

Seamlessly extend an image into padded areas using generative AI, adding visually realistic pixels to either or both dimensions. Optionally specify a prompt to guide what appears in the extended region.

Original image of a moped in a street Original image Extended street Seamlessly fill the extended width

Learn more: Generative fill.

Generative recolor

Recolor specific elements of your images using generative AI. Use natural language to describe what you want to recolor, and the color you want it changed to.

Original image of three people in jackets Original image Right jacket recolored pink Right jacket recolored pink

Learn more: Generative recolor.

Generative remove

Use generative AI to remove an object from an image and fill in the space with artificially generated, visually realistic pixels. Use natural language to describe what you want to remove.

Original image of dog with stick Original image Dog with stick removed Remove the stick

Learn more: Generative remove.

Generative replace

Use generative AI to replace objects in images with other objects. Use natural language to describe what you want to replace, and what to replace it with.

Original image with a picture on the wall Original image Picture replaced with mirror Picture replaced with mirror

Learn more: Generative replace.

Generative restore

Revitalize degraded and poor quality images using generative AI, removing compression artifacts, reducing noise, and sharpening blurred images. Particularly useful for user-generated content (UGC).

Original degraded image Original image Restored image Restored image

Learn more: Generative restore.

✔️ Feedback sent!

Rate this page:

one star two stars three stars four stars five stars