---
title: "How to use image generation with your AI Agents and what the integration can be used for"
last_updated: "2026-03-16T11:55:29.441Z"
category: "AI Agent How-tos"
canonical_url: "https://maybeclients.com/h/mash-help-centre/how-to-use-image-generation-with-your-ai-agents-and-what-the-integration-can-be-"
help_centre: "MaSH! Help Centre"
---

# How to use image generation with your AI Agents and what the integration can be used for

### What this article covers

This guide covers the integration of advanced image generation capabilities into your AI Agents using Stable Diffusion 3. This integration enables the creation of high-quality, realistic images, providing a powerful tool for creative, marketing, and visual content needs.

### What is image generation?

Image generation within your AI Agents uses Stable Diffusion 3, an advanced image generation model. This capability allows users to create highly detailed and realistic images from text prompts, supporting creative projects, marketing assets, and visual storytelling.

### Key features

- Realistic image creation: Generate photorealistic images using simple or detailed text prompts.
- Versatile outputs: Supports a wide range of image types, from natural environments to dynamic human activities.
- High-resolution images: Capable of producing images in up to 4K resolution for detailed visual content.

### Example use cases

- Marketing campaigns: Create custom visuals for advertising without the need for traditional photo shoots.
- Content creation: Enhance blog posts, articles, or social media with unique AI-generated images.
- Product visualisation: Produce realistic product imagery for digital storefronts and promotional materials.

### Step-by-step instructions

1. Enter your prompt:
In the chat interface, type a detailed description of the image you want to generate, for example:

“Create an image of a whale shark cruising through blue water.”

1. Review the image:
Review the generated image. If it doesn’t meet your expectations, you can request another version by refining your prompt.

1. Download the image:
Once satisfied, select Click to view to download the image.

### Using image generation in your AI Agents

- Incorporate into workflows: Use image generation within automated workflows to streamline content creation.
- Customise outputs: Refine prompts and settings to control image style, detail, and composition.
- Export and share: Download generated images for use in marketing materials, presentations, websites, and more.

### Best Practices

- Refine prompts: Use clear, descriptive prompts to achieve more accurate and relevant image results.
- Experiment with styles: Try different styles and modifiers such as 4K, cartoon, oil painting, or comic book to explore creative variations.
- Enable the integration: Ensure the Stable Diffusion 3 plugin is enabled for your AI Agent, or use a preconfigured image-generation agent where available.

### Common issues

|  | Suggested Solution | Issue | Possible Cause |
|  | Add more descriptive details to the prompt | Image does not match expectations | Prompt is too vague |
|  | Retry the request or contact support if the issue persists | Error during image generation | Temporary service issue |
### FAQs

- Can image generation be used in automations?
Yes, image generation can be integrated into automated workflows to support scalable content creation.

- Can I disable or remove this integration from an agent later?
Yes, integrations can be managed or removed through the AI Agent’s settings.

- What image sizes are supported?
Supported sizes include 1024×1024, 1536×1024 (landscape), 1024×1536 (portrait), and auto (default).



This action can’t be completed from Teams or Slack - please log in to your account.