Skip to content

Change a picture with words

Stable Diffusion V3

Stable Diffusion 3 Medium (Image to Image) is a Multimodal Diffusion Transformer (MMDiT) model that improves image quality, typography, prompt understanding, and efficiency.

Made by Stability AI350 creditsper run Pro
What it needs

Opens the image studio with Stable Diffusion V3 ready to use. You can look around as a guest. Running it takes the Pro plan or higher.

Stable Diffusion V3 sample output
Sample output
Stable Diffusion V3 sample output

What Stable Diffusion V3 makes, what it needs and what you get

What it makes

Change a picture with words

Changes a picture from a written instruction.

What you need

  • The picture to change
  • What to change

What you get

An edited copy of your picture

About Stable Diffusion V3

Stable Diffusion V3 changes a picture from a written instruction. It is made by Stability AI.

To use it, you provide the picture to change and what to change. You get an edited copy of your picture.

A typical run costs 350 credits. It is included from the Pro plan and up. You run it in the image studio, in your browser.

Best for

Typical uses for this kind of model.

  • Changing colours, outfits or backgrounds
  • Adding or swapping objects
  • Quick touch-ups described in plain words

How to use Stable Diffusion V3

  1. 1

    Add the picture to change

    Upload your files, or pick them from your library, then write a line about what you want.

  2. 2

    Check the settings

    The defaults are a good start. If you change an option, the cost updates and is shown before you generate.

  3. 3

    Generate your picture

    An edited copy of your picture. Your result appears in the studio, ready to download.