AI Agents for Image and Video Generation
by DeepLearning.AI
Build agents that generate images and video and automatically evaluate the results, taught by Google engineers.
Overview
Taught by Google's Katie Nguyen (Developer Relations Engineer, Google Cloud AI) and Wafae Bakkali (Staff Generative AI Specialist), this DeepLearning.AI short course spans nine video lessons (about 1 hour 34 minutes) with six code examples and a graded assignment. Learners build AI agents that produce images and video and, critically, evaluate the outputs automatically using three techniques: image-text similarity, LLM-based judges, and structured rubrics. The course walks through prompt engineering for both image and video generation, building a UI-mockup agent guided by brand guidelines, and developing a multi-scene video-explainer agent with synchronized audio. It also shows how to use the Gemini CLI to build a generative-media agent in natural language and how to package reusable agent skills for media workflows. Free to audit during the DeepLearning.AI platform beta; a completion certificate is available on the PRO membership tier.
At a Glance
- Topic
- Agentic
- Level
- Intermediate
- Format
- Course
- Cost
- Freemium
- Duration
- ~1 hr 34 min, self-paced
- Provider
- DeepLearning.AI
- Hands-on
- Yes — code/exercises
- Certificate
- Available
What You’ll Learn
- ✓Build AI agents that generate images and video end to end
- ✓Automatically evaluate generated media with image-text similarity, LLM judges, and rubrics
- ✓Engineer prompts for image and video generation models
- ✓Create a brand-guided UI-mockup agent and a multi-scene video explainer with synced audio
- ✓Use the Gemini CLI and package reusable agent skills for media generation
Highlights
- •Taught by working Google Cloud AI engineers, built in partnership with Google
- •Emphasizes automatic evaluation of generative media, not just generation
- •Hands-on code examples plus a graded assignment
Who It’s For
Best For
- ✓Developers building generative-media or creative-tooling agents
- ✓Engineers who need reliable evaluation for image/video output
- ✓Practitioners exploring Gemini for agentic media workflows
Prerequisites
- •Intermediate Python
- •Basic familiarity with LLMs and agents
FAQ
What is AI Agents for Image and Video Generation?
A hands-on DeepLearning.AI short course, built with Google, on constructing AI agents that generate images and video and grade their own output. It is for developers who want to build generative-media agents with real evaluation instead of eyeballing results.
Is AI Agents for Image and Video Generation free?
AI Agents for Image and Video Generation offers free content, with paid options for certificates or premium features.
What level is AI Agents for Image and Video Generation for?
AI Agents for Image and Video Generation is aimed at a intermediate audience. Recommended background: Intermediate Python, Basic familiarity with LLMs and agents.
How long does AI Agents for Image and Video Generation take?
Expect roughly ~1 hr 34 min, self-paced. Most learners work through it at their own pace.
What will I learn from AI Agents for Image and Video Generation?
You'll learn: Build AI agents that generate images and video end to end; Automatically evaluate generated media with image-text similarity, LLM judges, and rubrics; Engineer prompts for image and video generation models; Create a brand-guided UI-mockup agent and a multi-scene video explainer with synced audio; Use the Gemini CLI and package reusable agent skills for media generation.