Generative AI for Video Creation

Don Chan is a creative media educator, curriculum developer and industry practitioner whose work spans video production, photography, design and generative AI. He founded Pixel Cloud in 2012 and serves as its Lead Trainer and Creative Director, delivering creative media training alongside professional corporate videography and event and wedding photography and videography. As an adult trainer and curriculum developer under Pixel Cloud's NTUC LearningHub partnership since 2019, he has run more than 100 adult courses, typically for 10 to 25 learners, across public, SGUS and SCTP programmes, earning a 4.90/5 average trainer-effectiveness rating. He holds a BSc in Multimedia & Design from the Singapore University of Social Sciences and a Diploma in IT (Multimedia) from Republic Polytechnic, is a DaVinci Resolve Certified Trainer, and works with DaVinci Resolve, Premiere Pro, After Effects and generative AI tools such as ChatGPT, Adobe Firefly, Gemini, Canva AI and Suno.

In Generative AI for Video Creation, Don shows marketers, trainers, educators and content creators how to produce professional video faster by pairing generative AI with sound production fundamentals. The first topic covers creating and editing video scripts with generative AI, where learners research topics, write hooks and structure scripts that suit their audience and platform. In the second topic, improving video footage on AI-powered platforms, his background as a DaVinci Resolve Certified Trainer and corporate videographer helps participants tidy edits, generate captions, clean up audio and fix common footage problems with confidence. The final topic applies newer AI technologies to video production, including AI voices, avatars, B-roll and music, with Don drawing on his hands-on use of tools such as Suno and Adobe Firefly and his parallel experience as a music producer. His experience running classes of 10 to 25 adult learners means every participant gets practical feedback on their own work. Following his "Appreciate, Analyze, Apply" teaching approach, learners review strong examples, understand the techniques behind them and then produce their own polished videos.

Dr. Alfred Ang teaches this course from projects he has built, not from a tour of vendor demos. A full-stack AI developer and Agentic AI solution architect, he specialises in AI chatbots and voice and video agent deployment, and his GitHub portfolio of 300+ public repositories includes several projects that sit squarely in this course's territory. Videocreation turns any topic into a narrated video with AI-generated scripts, voiceover and animated scenes in TikTok and YouTube formats. Lipsyncdemo turns a portrait and a script into a talking avatar using three lip-sync engines, from an instant in-browser preview to MuseTalk for photoreal rendering on a local machine and HeyGen for cloud renders. Digitalhuman is a done-for-you service for building a branded, voice-enabled AI avatar with a cloned voice and RAG-trained knowledge that can be embedded on any website. Alongside this hands-on work, he is Managing Director, CIO, CTO and Chief Instructional Designer of Tertiary Infotech Academy Pte Ltd and the founder of Tertiary Courses. He holds a PhD in Electrical Engineering from NUS, an MSc in Electrical and Electronic Engineering from NTU and a B.Sc (Hons) in Physics from NUS, has published more than 20 peer-reviewed papers and co-invented more than 20 US patents. His certifications include Microsoft Certified AI Engineer Associate (AI-102), AWS Certified AI Practitioner and the Certificate in AI Ethics and Governance (Senior Professional) from NTU, which matters when synthetic voices and faces are involved.

Generative AI for Video Creation is built for marketers, social media managers, trainers, educators, communications staff and content creators who need more video without a bigger team, and Dr. Ang teaches it the way he builds: script first, then footage, then polish. In the first topic learners create and edit video scripts with generative AI, using tools such as ChatGPT and Claude to research a subject, write strong hooks and shape a clear structure. The second topic moves onto GAI-powered video platforms, where learners turn text into video, generate B-roll, add AI voices and avatars and improve existing footage. The third applies newer AI technologies to production itself, from background-noise removal and automatic captions to enhancement and repurposing for different channels. Because he has compared in-browser, local and cloud avatar rendering in his own projects, he can explain the trade-offs in quality, speed, cost and control that each platform choice brings, and he is careful to cover consent, disclosure, copyright and brand safety whenever learners clone voices or faces. As an ACTA-certified trainer and DACE-certified curriculum developer, he keeps the class hands-on: every participant leaves with scripts and finished clips they produced during the course, plus a practical workflow they can repeat on their own campaigns, lessons and announcements. To see the video, avatar and voice projects that inform his teaching, explore his GitHub portfolio at https://github.com/alfredang and connect with him on LinkedIn at https://www.linkedin.com/in/angchewhoe/

Allen Wong is a seasoned digital marketing strategist, ACTA-certified trainer and AI enthusiast who knows what engaging content has to achieve commercially. With more than eight years of experience across e-commerce, events, FMCG, real estate and finance, he has reached a career-wide return on ad spend of 300%, peaking at 1000% in events, and has generated $2M in e-commerce revenue and over $5M in sales. His data-driven approach centres on high-impact, cost-effective results, which is exactly the challenge facing teams that need to produce more video with smaller budgets.

Generative AI for Video Creation covers the full production chain. Learners create and edit video scripts with generative AI, improve footage on AI-powered video platforms, and apply new AI technologies such as text-to-video, AI avatars and voices, generated B-roll, noise removal and automated captions to raise production quality. Allen connects each technique to its marketing purpose, so participants consider audience, message and call to action before generating a single frame. Marketers, trainers and content creators leave able to plan and produce professional videos faster, while keeping the creative and commercial decisions in their own hands.

Kesston Tang is a consultant and trainer who provides coaching and consultation on online presence marketing and management, having begun his entrepreneurial journey in affiliate marketing. He also has more than two decades of experience in the ICT sector and in supply chain (warehouse management), including project management for multinational corporations and government agencies. Kesston is ACTA certified, holds certifications including PMP, ITIL, CEH, CHFI, SOC Analyst (CSA), MCSA and TOGAF, and has conducted numerous National WSQ and NICF trainings in Singapore. He is currently pursuing a Doctor of Business Administration and a Master in Education (NTU).

In Generative AI for Video Creation, Kesston brings his online marketing background to producing engaging videos faster with generative AI. Learners create and edit video scripts using generative AI, then improve footage on AI-powered video platforms that can turn text into video, generate AI avatars and voices, add B-roll, remove background noise and automate captions. The course finishes by applying new AI technologies to improve overall video production. His experience of helping clients manage their online presence keeps the focus on content that serves a clear marketing purpose. Marketers, trainers and content creators leave able to produce more professional video content with smaller teams and in less time.