Introduction

Dust agents can generate images from text prompts using the Image Generation capability. This powerful feature allows your agents to create custom visuals based on natural language descriptions, enabling a wide range of creative and practical applications.

The Image Generation capability uses the gemini-2.5-flash-image model to transform your text descriptions into high-quality images. Whether you need illustrations, concept art, mockups, or visual aids, your agents can create them on demand.

How to Enable Image Generation

When creating or editing an agent:

In the Agent Builder, click on Add Tools
Select the Image Generation capability
Save your agent

That's it! Your agent can now generate images when needed.

How to Use Image Generation

As a tool in an agent

When the Image Generation capability is enabled, your agent can autonomously decide to generate images when it determines they would be helpful for the task at hand. The agent evaluates your request and uses image generation when it's appropriate to create visual content.

For example, if you ask an agent with Image Generation enabled to "help me design a logo concept," the agent will automatically use the image generation tool to create visual proposals.

In conversations

You can directly ask any agent with Image Generation enabled to create images in your conversations. Simply describe what you want to see, and the agent will generate the image for you.

Safety features

All generated images are watermarked with SynthID
NSFW and images including celebrities won't be accepted

Example Prompts

Here are some practical examples of prompts you can use:

Illustration:

Create an illustration of a modern workspace with a computer, coffee cup, and natural lighting

Concept Art:

Generate a futuristic cityscape at sunset with flying vehicles and tall buildings

Product Mockup:

Design a minimalist product packaging for a tech gadget, using blue and white colors

Visual Aid:

Create a diagram showing the flow of data between a client, server, and database

💡
Tip: Be specific in your descriptions. Include details about style, colors, composition, and mood to get better results.

Advanced Usage

Best Practices

Be descriptive: Provide clear, detailed descriptions of what you want to see
Specify style: Mention artistic styles, color schemes, or reference styles when relevant
Iterate: Don't hesitate to ask for modifications if the first result isn't quite right
Context matters: Explain the purpose of the image to help the agent make better creative decisions

Tips for Better Results

Include information about lighting, perspective, and composition
Mention specific objects, colors, and their relationships
Describe the mood or atmosphere you want to convey
Reference specific artistic styles or techniques when applicable

📘
Note: Generated images are subject to content policies and may not be appropriate for all use cases. Review the generated content to ensure it meets your needs.

Image Editing

In addition to generating images from scratch, Dust agents can also edit existing images using text instructions with the edit_image tool. This allows you to make modifications to images that have been shared in the conversation.

Supported Formats

Image editing supports the following input formats:

PNG
JPEG
WebP
HEIC
HEIF

Maximum file size: 5MB

Example Editing Prompts

Here are some practical examples of image editing prompts:

Style Transfer:

Change the image to a watercolor painting style with soft, flowing colors

Object Modification:

Replace the background with a sunset beach scene while keeping the main subject

Color Adjustment:

Make the image warmer and more vibrant, increase contrast and saturation

Creative Transformation:

Transform this photo into a vintage 1950s poster style with retro typography

Use Cases

Image Generation and Editing open up numerous possibilities:

Marketing materials: Create visuals for presentations, social media, and campaigns
Concept development: Quickly visualize ideas and iterate on designs
Educational content: Generate diagrams, illustrations, and visual aids
Product design: Explore visual concepts and mockups
Creative projects: Generate artwork, illustrations, and creative visuals
Concept development: Quickly visualize ideas and iterate on designs with editing capabilities
Educational content: Generate and modify diagrams, illustrations, and visual aids
Product design: Explore visual concepts, mockups, and refine them through editing
Creative projects: Generate artwork, illustrations, and apply creative transformations
Photo enhancement: Edit and improve existing images with AI-powered modifications

For any questions about using Image Generation or Image Editing with your Dust agents, please contact us at [email protected]