Select an image on the slide and then select Generate image.
- Captivate User Guide
 - Get to know Captivate
 - Adobe Captivate releases
  
- Adobe Captivate 13
 - Adobe Captivate 12
 
 - Project setup
 - Import from PowerPoint
 - Generative AI in Captivate
  
- Generative AI overview
 - Generate text
 - Generate images
 - Generate avatar
 - Generate transcripts
 
 - Add and edit text
 - Add and edit images
 - Add and edit media
 - Interactive components
 - Create quizzes
 - Add widgets
 - Interactions and animations
 - Enhance your e-learning project
 - Simulation projects
 - Timeline and TOC
 - Review and collaborate
 - Preview and publish
 - Accessibility
 - Design options in Adobe Captivate
 - Additional resources
 
Learn to create custom visuals from text prompts with Adobe Captivate's AI-powered Generate image feature.
Overview
In Adobe Captivate, the Generate Image feature uses AI to convert text prompts into custom visuals that support your learning objectives. Its effectiveness depends heavily on the quality of your prompts. A well-crafted prompt guides the AI to produce images that are not only visually appealing but also instructionally relevant.
For eLearning creators, prompts are the creative bridge between concept and visual. Strong prompts include clear subjects, defined settings, and preferred styles.
Generate images from text prompts
Use text prompts to quickly create scenario illustrations, conceptual diagrams, or contextual backgrounds that support learner comprehension and engagement. This keeps visuals aligned with your course goals while eliminating the need for external sources or design tools.
For example, in a Fire Safety Training course, you can enter a simple prompt, and Captivate will generate relevant visuals that fit the course context and learning objectives. Here’s how to generate your first image:
- 
    
 - 
    
Enter your text prompt in the prompt field and provide a description of the image you wish to create.
The Generate image prompt field, where you enter descriptive text to create custom visuals for your eLearning content The Generate image prompt field, where you enter descriptive text to create custom visuals for your eLearning content  - 
    
Select Generate. Captivate generates and displays two image variations. Review both options and choose the image that best aligns with your course content and the target audience's needs.
Comparison between basic and refined prompt results demonstrating how detailed prompts produce more contextually relevant training visuals. Comparison between basic and refined prompt results demonstrating how detailed prompts produce more contextually relevant training visuals.  - 
    
Select an image variation to replace the current slide image.
 
Refine and improve prompts
For higher-quality outputs, refine your prompts by adding context and instructional intent. Learn more on the best practices for effective image generation.
For example, a fire safety training prompt with detailed context produces a more accurate image than a simple one.
- Basic prompt: “Fire extinguisher in office.”
 - Refined prompt: “Realistic photo of a workplace fire drill showing coworkers using fire extinguishers in a modern office setting, professional safety training style.”
 
The refined prompt creates a more instructional and scenario-based image, better suited for a training module.
Include subject, setting, and style in your description for more accurate results.
Use slide text as a prompt to generate images
Generate images from slide text to match your presentation’s theme and context. This helps streamline your workflow by creating visuals aligned with your content and branding, boosting engagement and reinforcing key training messages.
For example: If your slide title is Fire Risk Assessment, you can use this text, add context, and instantly create a relevant visual.
- 
    
Select the dropper icon inside the prompt field.
The text selection dropper tool enables quick conversion of existing slide content into image generation prompts. The text selection dropper tool enables quick conversion of existing slide content into image generation prompts.  - 
    
Select individual text objects or click Select all to use the entire slide text as your image prompt.
Select an individual text object or select all text objects on the slide Select an individual text object or select all text objects on the slide You can then refine the prompt by adding context or descriptive details to help the AI generate a more accurate and relevant image.
 - 
    
Select Generate and choose the most relevant image variant to insert as the slide image.
Insert the generated image as the slide image Insert the generated image as the slide image