Course Objective & Scope
While generative video models can create striking isolated clips, telling a coherent story with consistent characters, locations and camera language requires a disciplined production pipeline. This course teaches how to build a controllable AI video workflow from script to final edit rather than relying on random text-to-video prompts.
Preparing first/last keyframe stills, image-to-video and camera control with Google Veo, OpenAI Sora, Runway Gen-4 and Kling, voiceover and sound design with ElevenLabs, multilingual presenter videos with HeyGen, and assembly in Premiere/CapCut are practised hands-on. Participants produce a publish-ready short video for their organisation.
Who Should Attend?
- Video producers, motion designers and video editors
- Creative directors, art directors and social media content teams
- Corporate communications and L&D video creators
- Prerequisite: basic familiarity with image generation or video editing
Key Takeaways
- Break a script into a storyboard and shot list suited to AI video model strengths
- Maintain scene-to-scene consistency using image-to-video and keyframe anchoring
- Direct camera movement, pacing and motion using prompts and motion controls
- Integrate voiceover, lip-sync and sound effects seamlessly with generated footage
- Deliver broadcast- or social-ready video through editing, colour grading and upscaling
Curriculum
AI Video Ecosystem and Pre-Production
- Comparing Google Veo, Sora, Runway, Kling and Luma models
- Script breakdown, shot lists and storyboard preparation with reference stills
Image-to-Video and Scene Consistency
- Character and location continuity via first/last frame anchoring
- Camera moves (pan, tilt, dolly, orbit) and motion brush controls
Avatars, Presenters and Multilingual Video
- Corporate training and product explainer videos with HeyGen and Synthesia
- Video translation, voice-cloning permissions and lip-sync
Sound Design, Music and Edit Integration
- Voiceover and scene-matched SFX generation with ElevenLabs
- Pacing, colour matching and video upscaling in Premiere Pro / CapCut
End-to-End Short Ad / Corporate Video Lab
- Producing a 30–60 second video from an organisational brief
- Copyright, C2PA labelling and pre-publication quality checks
Other Courses in This Category
-
Introductory programme for design teams covering AI-assisted research, ideation, image generation with Midjourney and Adobe Firefly, prototyping with Figma AI and copyright-safe use, ending with a personal AI design workflow.
- Live Course
- 6 modules
-
Market, competitor and trend research with Perplexity and ChatGPT/Gemini deep research, plus moodboard creation with Midjourney style references and FigJam. Designers produce a source-checked research brief and visual direction board.
- Live Course
- 5 modules
-
Divergent ideation with LLMs using SCAMPER, How Might We and Crazy 8s, persona-based critique and concept selection. Creative teams turn a brief into three justified concept routes with supporting concept boards.
- Live Course
- 5 modules
-
Prompt anatomy for image models, style and character references, image-to-image and ControlNet for pose and composition control. Designers build a prompt and reference library that reproduces a target art direction reliably.
- Live Course
- 5 modules
-
Producing campaign, social media and web visuals with Midjourney, Adobe Firefly, GPT image and Gemini image models, covering formats, series consistency, basic editing and upscaling. Teams deliver a publish-ready visual content set.
- Live Course
- 5 modules
-
Hands-on training in producing A/B test, localisation and format variants from existing images using Photoshop Generative Fill, inpainting/outpainting, background replacement, prompt-based editing (GPT image, Gemini) and upscaling.
- Live Course
- 5 modules
Get in touch
