To create an image, you can, of course, use the "text to image" method, which means writing a prompt that describes what you have in mind (see the article

Create an Image with a Text Prompt), but you can also use a reference image to create variations or edit the image

This method is very effective for having more control over what you produce, stylizing an image in another style, or creating variations of a generated image.

Adding a Reference Image

To add a reference image, you can either:

* Add an image from the creation flow

Simply click on the "Input Image" button that appears when you hover over the image. The image will then be sent to the "Reference Image" block in the left column, below the model section.

* Upload an image from your computer

Simply click on the image shown above and select the image you want from your computer or mobile device.

Different image-to-image modes available

You have 3 different modes that you can use to create visuals from an image:

Flux Kontext

A powerful context-aware editing mode that uses both text and image inputs to smartly transform visuals—changing elements while preserving composition, style, and character details. It’s intuitive, localized, and truly next-level.

More information about Flux Kontext in this article Flux Kontext – Image-to-Image Prompting Guide

Structure Reference

This mode leverages structural algorithms, such as edge detection or depth mapping, to recreate new images maintaining the original layout and depth of your reference. Ideal for generating variations while preserving the scene’s fundamental composition.

Remix

Seelab analyzes your input image to generate prompts that recreate or reimagine it in a new style or context. It’s perfect for generating creative variations when you're not sure how to phrase the prompt yourself.

Updated on: 12/08/2025