Creating Videos In Gemini (Omni)
Are you intimidated by AI video creation or worried about producing unusable content? Join our hands-on workshop to master the Gemini Omni model and start creating professional, structured videos with confidence.
Book this courseCourse Overview
3 hour course
Certificate of Attendance
Private
This practical half-day workshop demystifies AI video generation, helping you move beyond the hype and create structured, professional videos using Gemini Omni.
Designed for anyone who has seen AI video demos but feels unsure where to start, this session gives you a clear, practical path forward. You’ll explore how and where to create videos across the Google ecosystem, including Gemini, Google Vids, Google Flow, or any platform where you can access the Gemini Omni model.
You’ll learn how to move beyond basic standalone prompts by feeding character, prop and environment references into the model, helping you shape your story before a single frame is generated.
Using our practical “listen, see, do” approach, you’ll hear key concepts explained, watch live demonstrations, and immediately apply what you’ve learned through interactive exercises.
By the end of the session, you’ll understand Gemini Omni’s core capabilities, know how to experiment with video generation parameters, and feel confident creating cohesive, sequential videos.
Our Creating Videos In Gemini (Omni) workshop is available as a private training session that can be delivered virtually or at a location of your choice in South Africa.
What you'll learn
By the end of this course, you will be able to:
Navigate the Google ecosystem to create videos directly in the Gemini app, Google Vids, and Google Flow
Apply conversational and structured prompting techniques to influence video outputs
Work alongside AI to storyboard and develop narratives before generating frames
Understand how audio and video can work together effectively
Understand how to build sequential videos rather than just standalone, discrete clips
Understand the unique capabilities and features of the Gemini Omni model
Utilize consistent characters, props, and environment references throughout the video creation process
How to make edits to elements in a video
Deconstruct prompts and assess videos for prompt adherence
Navigate token limits and understand the parameters of daily video generation
Course agenda
Introduction to Video in Gemini
- Moving past the hype to understand what Gemini Omni can realistically do
- Navigating the tools: A tour of the Gemini app, Google Vids, and Google Flow - where else can you find Google Omni
- Understanding token limits and the parameters of video generation
The Mechanics of AI Video
- Aspect ratios and different video mediums
- Understanding external references and art styles
- How audio and video can work together
- Figuring out where to get references from (a quick primer on Nano Banana)
The Strategy of Prompting for Video
- Conversational prompts versus structured prompts
- Deconstructing prompts and critiquing prompt adherence
- Working with the AI to develop a story before generating frames
- Understanding that videos do not have to be built from standalone prompts
Practical Application (Listen, See, Do)
- Generating ingredients (characters, props, environments, first frames) to use inside a video prompt
- Using a conversation to design a video
- Using structured prompts and references
- Iterating on existing prompts to make changes to the video
- Referencing external styles in a prompt and building a sequential videos
Who it's for
This course is designed for general business users who want to understand and utilise AI video creation within the Google suite. It will specifically appeal to anyone who feels intimidated by the complexity of AI video or is concerned about producing low-quality content.
No prior video editing or AI experience is required.
BOOK THIS COURSE
Enquire for a team or large group
For private sessions call our sales team