GCP Generative AI Leader Practice Question 1: Video Generation Model Choice
Google Cloud Generative AI Leader · Test 1 · question 1 of 10
A marketing director wants her team to produce short promotional video clips from written creative briefs and a few product photos, without hiring a video production agency. She asks which of Google's foundation models is built for this job.
Which model should the team evaluate first?
Show answer and explanation
Answer:
Picking a foundation model starts with modality: what goes in and what comes out. The output here is video, and Veo is Google's video generation model. On Gemini Enterprise Agent Platform (formerly Vertex AI), Veo creates video from a text prompt, or from an image used as the first frame. That matches "written briefs plus product photos" exactly.
Option A is the closest distractor. Imagen is Google's image generation model, so it produces still images, not motion video. It could make stills for a storyboard, but it cannot produce the clips themselves.
Option C, Gemma, is a family of lightweight open models. Organizations choose it when they want to run and customize a model on infrastructure they control. It is not a video generator.
Option D, Chirp, is a speech model used to turn audio into text. That solves a different problem, such as captioning a finished video.
Reference: Generate videos with Agent Platform