Stable diffusion reimagine

Stable Diffusion Reimagine is a new algorithm created by stability.ai that creates images variation from an image.

This model will soon be open-sourced in StabilityAI’s GitHub.

The classical text-to-image Stable Diffusion 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!

You just need to upload an image, and Stable Diffusion reimagine will automatically create three variations for you.