Mastering AI Image & Video Generation
Overview
This 4-hour creative workshop is a deep dive into the rapidly evolving world of AI-generated images and video. You will gain hands-on experience with three powerful tools — Nano Banana for rapid creative exploration, Google Imagen for photorealistic and artistic image generation, and Google Veo for AI video production. From prompt crafting for visuals to understanding style, composition, and motion, this course gives you the skills to produce professional-grade visual content without a camera or studio.
Skills Acquired:
• Visual prompt engineering for images and video
• Google Imagen photorealistic image generation
• Style, composition, and lighting control via prompting
• AI-generated image and video ethical practices
• Mood board and marketing asset creation
• Nano Banana rapid concept visualisation
• Google Veo AI video clip production
• Negative prompting for refined visual outputs
• Creative visual workflow design
• SynthID watermarking and responsible disclosure
This course is included in the AI Annual Learning Pass.
Duration:
1/2 Day
Who Should Take This Course
Prerequisites
- A Google account for access to Imagen and Veo (via Google AI Studio or Gemini)
- A Nano Banana account (free tier available)
- Basic understanding of what a prompt is (completing Course 1 is helpful but not required)
- Interest in visual content creation — no design or art background needed
Why You Should Take This Course
By the end of this course, learners will be able to:
- Generate high-quality images using Imagen and Nano Banana with effective visual prompts
- Produce AI video clips using Veo with control over style, motion, and narrative
- Apply visual prompt engineering techniques: style, lighting, composition, and mood descriptors
- Iterate and refine visual outputs through negative prompting and parameter tuning
- Understand ethical and copyright considerations for AI-generated visual content
- Build a repeatable creative workflow combining image and video generation tools
Course Outline
Mastering AI Image & Video Generation
| Module 1: Visual Prompt Engineering — The Language of Images
50 minutes |
How Text-to-Image Models Work
- Diffusion models explained in plain language
- The role of the prompt: subject, style, lighting, composition, mood, and medium
- Aspect ratios, resolution settings, and output formats
Building Powerful Image Prompts
- The visual prompt formula: subject + style + lighting + camera + mood
- Style descriptors: photorealistic, cinematic, watercolour, oil painting, isometric, and more
- Negative prompts: excluding unwanted elements (blur, text, watermarks, extra limbs)
- Reference artists and aesthetics — and when to avoid them (copyright awareness)
Hands-On: Prompt ladder exercise: build a simple prompt into a richly detailed one in four iterations and observe the visual difference
| Module 2: Nano Banana — Rapid Visual Exploration
45 minutes |
Platform Introduction
- Nano Banana interface walkthrough and generation modes
- Batch generation and variation workflows
- Style presets and model selection
Hands-On: Creative sprint: generate 20 image variations of a concept in 10 minutes using batch mode
Practical Applications
- Rapid concept visualisation for presentations and pitches
- Mood board creation for creative projects
- Social media and marketing asset generation
Hands-On: Create a 6-image mood board for a brand, event, or personal project
| Module 3: Google Imagen — Photorealistic Image Generation
45 minutes |
Imagen Capabilities
- Imagen model strengths: photorealism, text rendering, and fine detail
- Prompt tuning for Imagen: what works and what does not
- Inpainting and outpainting concepts — editing parts of an image
- Image-to-image transformation with reference inputs
Hands-On: Product photography challenge: generate a hero product shot for a fictional brand using only text prompts
Responsible Use with Imagen
- Google’s safety filters and what triggers them
- Watermarking (SynthID) and identifying AI-generated images
- Ethical disclosure when publishing AI-generated images
| Module 4: Google Veo — AI Video Generation
60 minutes |
Introduction to Veo
- How text-to-video and image-to-video models work
- Veo interface and generation settings
- Video prompt structure: scene, action, camera movement, mood, and duration
- Camera movement descriptors: dolly, pan, zoom, tracking shot, aerial
Hands-On: Generate three 5-second video clips from the same prompt using different camera movement instructions and compare results
Creating a Visual Story
- Sequencing clips for short-form video content
- Consistency across clips: maintaining style, character, and setting
- Combining Imagen and Veo for a full visual production pipeline
- Exporting and post-processing AI video clips
Hands-On: Capstone project: produce a 4-shot, 20-second AI video story from concept to export