Reimagine XL

Create multiple variations from a single image with Stable Diffusion.

Click or drop a file here to start

All tools

Generative Fill

Replace, remove & fix any element from your pictures

Swap

Swap people in any image

Stable Diffusion XL Turbo

Real-Time Text-to-Image Generation

Jasper AI

Text generation for millions of use cases. Free for 7 days.

Replace background

Teleport anything, anywhere with AI

Remove background

Extract the main subject from a picture with incredible accuracy. It's like magic.

Cleanup

Remove objects, people, text and defects from your pictures automatically.

Uncrop

Uncrop your photos to any image format

Image upscaler

Upscale your images by 2x or 4x in seconds. It can also remove noise and recover beautiful details.

Sketch to Image

Transform your doodles into real images in seconds

Reimagine XL

Create multiple variants of an image with Stable Diffusion

Frequently Asked Questions

What is Reimagine XL?

Reimagine XL is a new algorithm based on the open source Stability Stable unCLIP model. It creates images variations from an image.


Stability Stable unCLIP model is open-sourced and available on StabilityAI’s GitHub.

How does Reimagine XL work?

The classical text-to-image Stable Diffusion XL model is trained to be conditioned on text inputs.


This version replaces the original text encoder with an image encoder. So instead of generating images based on text input, images are generated from an image. Some noise is added to generate variation after the encoder.


This approach produces similar-looking images with different details and compositions. Unlike the image-to-image algorithm, the source image is first fully encoded, so the generator does not use a single pixel from the original one!

How do I get started with Reimagine XL?

You just need to upload an image, and Reimagine XL will automatically create three variations for you.