Generative AI Leader Google Cloud's Generative AI Offerings Practice Question
A team needs to generate photorealistic product imagery for an e-commerce catalog from text descriptions, and later needs to edit existing photos by removing unwanted objects while preserving the rest of the scene. Which Google Cloud generative media capabilities should they use for these two tasks, respectively?
⚠ Common exam trap
The trap here is assuming that a model which can detect or analyze objects in an image can also remove them, when removal requires generative inpainting that reconstructs the background.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Imagen for text-to-image generation, and Imagen editing capabilities for object removal and inpainting
Text-to-image generation and masked image editing are distinct capabilities, and both are provided within the same generative media family. Using it for generation from product descriptions and for inpainting-based object removal keeps quality and tooling consistent. Analytics platforms, video pipelines and detection-only models each cover adjacent ground but cannot fulfill the complete pair of tasks described.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Gemini for text-to-image generation, and BigQuery for object removal
Why it's wrong here
BigQuery is an analytics data warehouse and offers no image editing functions, so it cannot remove objects from photos. While Gemini models handle multimodal understanding and some image workflows, the scenario asks for photorealistic catalog generation and masked editing, which are served by dedicated image generation and editing capabilities rather than a data warehouse.
- ✗
Vertex AI Vision for text-to-image generation, and Imagen for object removal
Why it's wrong here
Vertex AI Vision focuses on video and image analytics pipelines such as streaming analysis rather than creating photorealistic product images from prompts. Pairing it with Imagen for editing also splits the workflow unnecessarily, and the generation half would not deliver the catalog-quality text-to-image output the team needs.
- ✗
Imagen for text-to-image generation, and a custom-trained object detection model for removal
Why it's wrong here
Imagen correctly handles generation, but a custom object detection model only locates objects; it does not remove them or reconstruct the background. The team would still need an editing or inpainting capability to fill the vacated region convincingly, so this combination leaves the second task incomplete despite the correct choice for generation.
- ✓
Imagen for text-to-image generation, and Imagen editing capabilities for object removal and inpainting
Why this is correct
Imagen generates high-quality images from text prompts, which covers creating catalog imagery from product descriptions. Its editing capabilities, including inpainting and mask-based modification, allow unwanted objects to be removed while the surrounding scene is preserved. Using one family for both generation and editing keeps the workflow consistent and satisfies both stated tasks.
Go deeper
Related to this question
About these practice questions
One of 1,008 original Generative AI Leader practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Google Cloud exam blueprint
This Generative AI Leader practice question is part of Courseiva's free Google Cloud certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the Generative AI Leader exam.