After adding the Photoroom connector to Claude, you can use natural language prompts to generate images directly in your Claude conversations. Each generation uses credits from your subscription plan.
This article is for users who are using the MCP for Pro, Max, and Ultra subscriptions. If you use an API subscription, see What is the Photoroom MCP? for information.
Before you begin
Make sure you have:
A Photoroom Pro, Max, or Ultra subscription.
Added the Photoroom connector to Claude. See:
Note: If you are using an API subscription, see What is the Photoroom MCP?
Steps
To generate images using natural language with Claude and Photoroom:
Log in to Photoroom.
Select a Space that has a Pro, Max, or Ultra subscription.
Log in to Claude.
Make sure you select the profile that has the Photoroom connector set up.
Start a new chat.
Turn the Photoroom connector on:
Select + at the bottom left of the chat interface.
Select Connectors.
Find Photoroom and toggle it on.
Enter a prompt that describes what you want Photoroom to create:
Begin your prompt with "Use the Photoroom MCP to ...". See the example at the end of this section.
Describe what you want Photoroom to do. Include any parameters that you want to apply, for example, the name of the character you want to use or the style of background.
Use + to add source images for the AI to use as a starting point. For example, add a product photo.
Send your prompt and wait for Claude and Photoroom to generate your images.
Download the images.
Tip: You can build more complex prompts that use the Photoroom connector as part of a longer chain involving other products. That's how you can use Claude, Photoroom, and other apps to create efficient, automated workflows.
Example prompt
Here is an example of a prompt we used to generate 3 images:
Prompt:
Use the Photoroom MCP to create an AI Fashion Models image showing Alex in an urban stairwell. Also create a ghost mannequin image of the T-shirt and a flat lay image with a white background.
We used the prompt and also added a photo of a T-shirt as the source image (starting point).
Note how we are able to:
Use natural language to describe what we want
Specify the parameters we wanted, such as the particular AI Fashion Models character to use
Generate 3 images at the same time in Claude

