Embracing AI isn’t just a competitive advantage anymore – it’s a fundamental skill for thriving in today’s workplace. This interactive intermediate course provides practical strategies and workflows to combine the power of three powerful AI tools – ChatGPT (or Gemini), MidJourney, and a leading video generation model, Runway.
Throughout the day, you'll enjoy a highly interactive learning environment with hands-on practice and experimentation, ensuring you can effectively combine the strengths of these powerful language and visual models to create sophisticated images and videos.
By the end of the session, you'll have deepened your understanding of the capabilities, limitations and fine-tuning potential of state-of-the-art AI tools, and will have the confidence to prototype end-to-end workflows that combine multiple modalities.
Our Advanced Gen AI Content Creation: ChatGPT, MidJourney & Runway course is available as a scheduled Virtual Classroom session. We also offer it as a private course that can be delivered virtually, at your offices, ours, or at any location that works best for you - whether in South Africa or internationally.
Course overview
Who should attend:
If you already have a grasp on Gen AI and want to further refine your skills, this intermediate course is perfect for you.
What you'll learn:
By the end of this course, you will be able to:
- Use advanced prompting techniques in ChatGPT / Gemini for generating sophisticated creative briefs and refining prompts for both visual and video AI
- Leverage ChatGPT / Gemini to develop consistent character descriptions and style guidelines for use across MidJourney and video generation models
- Confidently utilize advanced features of a leading video GenAI model (like Runway) for complex video, camera control, and transitions
- Design and implement effective workflows for integrating ChatGPT / Gemini, MidJourney, and video AI to create cohesive and compelling multi-modal stories
- Apply techniques to ensure visual consistency and narrative coherence across longer image and video projects
- Understand how these different AI models can be used together to create multi-modal content
- Understand how to strategically leverage the unique strengths of each AI tool to enhance the overall quality and impact of your content
- Troubleshoot common challenges encountered in advanced Gen AI content creation workflows
- Use advanced tips and tricks for refining and editing AI-generated text, images, and videos to achieve professional-level results
- Prompt engineer sophisticated and engaging multi-modal projects that effectively combine text, images, and video using these powerful Gen AI tools
Course agenda
- Crafting sophisticated prompts in ChatGPT / Gemini to develop detailed creative briefs and consistent character / style guides for images and videos
- Techniques for iterative prompting and refining outputs across text, image, and video AI
- Using ChatGPT / Gemini to generate complex scene descriptions and dialogue for video
- Utilizing advanced MidJourney parameters and prompt structures
- Techniques for ensuring visual consistency across multiple image generations for video
- Developing workflows for using ChatGPT / Gemini to generate highly specific and creative prompts for MidJourney based on detailed narrative requirements
- In-depth exploration of advanced animation controls, camera movements, and scene transitions within the chosen video AI platform
- Utilizing features for controlling video style, motion, and overall aesthetic
- Techniques for incorporating text prompts from ChatGPT / Gemini to influence video generation
- Best practices for preparing and importing MidJourney images into the video generation model
- Techniques for ensuring smooth transitions and visual coherence between AI-generated scenes
- Exploring advanced features for synchronizing visuals with AI-generated text or voice overs