Question 21
Domain 2: Fundamentals of Generative AIA company is building a generative AI application on AWS. The application will help improve reading comprehension for students. The application must give students the ability to add illustrations to stories. Which solution will meet this requirement?
Correct answer: A
Explanation
Stable Diffusion is an image-generation diffusion model, and the source says diffusion models “generate outputs” and are “the basis for image generation capabilities.” Amazon Bedrock includes Stability AI’s Stable Diffusion, so using Stable Diffusion 3.5 Large to generate images from text inputs lets students add illustrations to stories.
Why each option is right or wrong
A. Use Amazon Bedrock Stable Diffusion 3.5 Large to generate images based on text inputs.
Amazon Bedrock exposes Stability AI models as managed foundation models, and the cited material specifically places Stable Diffusion in the image-generation category under Bedrock. The relevant section explains that diffusion models are used to generate images from text prompts, so the student-facing requirement to add illustrations is satisfied by invoking a Bedrock image model rather than a text-only LLM. Because Bedrock is fully managed, the company can call the model API directly without provisioning GPUs or managing model infrastructure.
B. Use Amazon Polly to create an audiobook based on story texts.
Amazon Polly converts text into spoken audio, not visual illustrations.
C. Use Amazon Rekognition to analyze image contents and detect text attributes.
Amazon Rekognition analyzes images and detects attributes; it does not generate new images.
D. Create a standard prompt template. Use Amazon Q Business to illustrate stories.
Amazon Q Business is for enterprise question answering, not story illustration generation.