Amazon Web Services AWS Certified AI Practitioner Exam AIF-C01 Question # 79 Topic 8 Discussion
AIF-C01 Exam Topic 8 Question 79 Discussion:
Question #: 79
Topic #: 8
A company is using an Amazon Nova Canvas model to generate images. The model generates images successfully. The company needs to prevent the model from including specific items in the generated images.
The correct answer is C – Use a negative prompt. Negative prompts instruct a generative image model to avoid certain features, objects, or styles in the output. This technique is fully supported by models like Amazon Nova Canvas on Bedrock, which are based on diffusion or image generation architectures. According to AWS documentation, negative prompts refine output control by telling the model what not to include, thereby improving brand alignment, compliance, or creative direction. A higher temperature increases randomness, not control. A detailed prompt helps, but without exclusion instructions, the model may still include unwanted elements. Changing the model may yield better output but doesn’t directly solve this control requirement. Negative prompts are purpose-built for this scenario.
Referenced AWS AI/ML Documents and Study Guides:
Amazon Bedrock Documentation – Prompt Engineering for Image Models
AWS Generative AI Guide – Controlled Generation with Negative Prompts
Contribute your Thoughts:
Chosen Answer:
This is a voting comment (?). You can switch to a simple comment. It is better to Upvote an existing comment if you don't have anything to add.
Submit