Instructor
AMCC 5160 · Fall 2026/27
AI-Driven Animation
& Video Generation
An art-and-technology course for creating, directing, understanding, and critically rethinking generative media—from images to interactive worlds.
Teaching team
People, not prompts.
Teaching assistant
Yaofu Liu
AMCC 5160yliuls@connect.ust.hk ↗Course at a glance
When
Tuesdays · 18:30–21:20
Where
MIL13002
Credits
3
Class size
80
Course description
This course treats generative AI as both a technical system and an artistic medium. Students learn how contemporary image, animation, video, audio, and world models work; use them to direct purposeful creative experiments; situate the work in visual culture; and evaluate authorship, provenance, consent, bias, and audience experience.
Understand systems
Build mental models that outlast individual products.
Direct experience
Connect technical choices to intention and audience.
Evaluate evidence
Make limitations and responsible use part of the work.
By the end, students can
explain a pipeline · direct a coherent work · build and document an experiment · critique with evidence · account for AI use · present a refined project
Assessment
A clear path from sharing to showcase.
Letter grades · 100% total
Weeks 2–11
Weekly presentation
10%Due at the end of the semester
All weekly quizzes combined
20%15% each
Assignments 1–3
45%Nov 17 or 24
Final presentation
25%Assignment deadlines Assignment 1 brief → · Assignments 2–3 will be announced later.
Weekly presentation10%
Share ongoing
or past work.
Around 10 minutes. This is a friendly sharing session: bring ongoing or past artistic, design, research, or technical work and tell us what you are exploring.
Live capacity by weekChoose a slot →- Share the context, your intention, and how you approached the work.
- Bring one lesson, limitation, question, or idea you would enjoy discussing.
- Please add your slides link on the sign-up page before or after your presentation.
Final presentation25%
Present one
course project.
The projects will be announced soon. They will most likely explore generative AI and AIGC, AI filmmaking, world models, agents, avatars, and related creative directions.
Live capacity for both datesChoose a slot →- Choose one course project and develop it into a thoughtful final presentation.
- Share your intention, process, experiments, and what you learned along the way.
- For inspiration, you are welcome to look at projects from past courses on Harry’s website.
Tentative weekly schedule
Thirteen weeks.
One evolving medium.
Open a week to see its focus.
01Sep 1Neural networks to AI filmmakingSeeing + systems＋
FocusQuiz 01 · Complete when readyFive short questions based on Lecture 01Due by semester end · Take quiz →
From neurons and CNNs to transformers, diffusion, current video foundation models, and a step-by-step AI filmmaking workflow.
Narrated lectureWatch 102 slides ▶Lecture videoMP4 ↓Lecture audioMP3 ↓SlidesPowerPoint ↓Transcript PDFOpen ↗Full transcriptDOCX ↓
Further reading · 3 current conversationsPeople, ideas, and a viral AI-video benchmark
Interview · Aug 2026Fei-Fei Li with Emily Chang: What’s Beyond ChatGPT?Bloomberg Originals · YouTube ↗Interview · Feb 2025Satya Nadella on Microsoft’s AGI planDwarkesh Patel · YouTube ↗Viral discussion · May 2026The Will Smith spaghetti benchmark: 2023 → 202617M+ views · X ↗02Sep 8Generative editing: images, art direction, and videoTechnique + intention＋
FocusQuiz 02 · Complete when readyFive short questions based on Lecture 02Due by semester end · Take quiz →
How generative editing works, how to direct it creatively, and how to keep images consistent through video. Explore ControlNet, artistic choices, and recent research through practical examples.
Narrated lectureWatch 123 slides ▶Lecture videoMP4 ↓SlidesPowerPoint ↓Slide PDFOpen ↗Transcript PDFOpen ↗Full transcriptEnglish / 中文 →
Lecture 02 · Three readingsAI capability, human direction, and video editing
6 September 2026An Alien MindJakub Pachocki / OpenAI ↗23 December 2025How to fix your entire life in 1 dayDan Koe ↗21 May 2026Introducing Aleph 2.0 and Edit StudioRunway ↗03Sep 15Inside the generator: why does it produce this?Technique + intention＋
FocusQuiz 03 · Complete when readyFive short questions based on Lecture 03Due by semester end · Take quiz →
How image generators work, and how seeds, guidance, and editing choices affect an artwork. Explore diffusion, attention, video, world models, and robot actions.
Narrated lectureWatch 100 slides ▶Lecture videoMP4 ↓SlidesPowerPoint ↓Slide PDFOpen ↗Transcript PDFOpen ↗Full transcriptEnglish / 中文 →
Lecture 03 · Three readingsAI safety, open models, and image workflows
Reading 1We Must Pace the FrontierDario Amodei · Guide PDF ↗Reading 2open the frontierJack Dorsey · Guide PDF ↗Reading 3Controlled image workflowTechnical reading · Guide PDF ↗04Sep 22Image generation, editing, and art directionImage + direction＋
Focus
Subject and style control, reference grounding, masks, iterative editing, visual prompting, and agent-assisted workflows. Build a coherent visual system—not a bag of adjectives.
05Sep 29Adaptation, creative workflows, and authorshipCraft + workflow＋
Focus
LoRA and adapters, distillation, quantization, open versus hosted models, node and code pipelines, dataset curation, reproducibility, appropriation, and artistic voice.
06Oct 6Video foundations: time, motion, and cinematographyTime + motion＋
Focus
Video latents, temporal attention, motion representation, camera control, shot scale, blocking, rhythm, montage, and current open and hosted model families.
07Oct 13Controllable motion, choreography, and video-as-promptControl + choreography＋
Focus
Identity, pose, trajectory, depth, optical flow, and reference-video semantics—applied to performance, choreography, camera movement, continuity, and failure diagnosis.
08Oct 20Native audio-video, performance, and real-time charactersSound + performance＋
Focus
Synchronized sound, dialogue, lip-sync, expressive avatars, low-latency generation, voice, soundscape, performance direction, and cross-modal evaluation.
09Oct 27Critique, evaluation, provenance, and responsible releaseCritique + responsibility＋
Focus
Human preference and technical metrics meet studio critique. Prompt alignment, consistency, physics, synchronization, model cards, consent, copyright, and disclosure.
10Nov 3Interactive world models and explorable artWorlds + interaction＋
Focus
Action-conditioned prediction, explorable environments, persistent scenes, real-time simulation, installation, games, and physical-AI data. Case studies include Genie 3 and Cosmos 3.
11Nov 10Video reasoning, creative agents, and speculative practiceReasoning + speculation＋
Focus
Generation as a reasoning tool, multimodal agents, limits of treating video generators as world models, speculative futures, exhibition strategy, and presentation coaching.
12Nov 17Final presentations IShowcase＋
Focus
Students present one selected assignment as a refined showcase, followed by peer critique and discussion.
13Nov 24Final presentations IIShowcase＋
Focus
The second showcase session, peer critique, course synthesis, and future directions.
Frequently asked questions
A few friendly notes
for the semester.
Please learn in the way that works best for you. These quick answers explain presentations, attendance, the waitlist, and how we balance application with theory.
01What should I share for the weekly and final presentations?
Weekly presentation · 10%: you are very welcome to share ongoing work or something you made in the past. It can be artistic, design-based, research-oriented, or technical. The emphasis is simply on sharing—tell us what you explored, what you learned, and anything you would enjoy discussing with the class. Please add your slides link on the sign-up page before or after your presentation so everyone can revisit them; you can return at any time and update your booking.
Final presentation · 25%: present one of the course projects. The projects will be announced soon and will most likely involve generative AI and AIGC, AI filmmaking, world models, agents, avatars, or related creative directions. You can also look at past courses on Harry’s website for examples and inspiration.
02Do I need to attend every class?
No—you do not need to attend every class. All materials, including lecture videos, transcripts, slides, audio, readings, and quizzes, will be available online so you can learn at your own pace. Please feel free to skip a class when you are already familiar with the topic or when you have other responsibilities. The one important exception is the week when you are giving your presentation—we would love to have you there to share with the class. Please also check Canvas for time-sensitive announcements.
Open the weekly schedule and course materials →03Is the course focused on application or theory?
Both—and everyone is welcome. We know that many students come from art and design backgrounds, while others bring more technical experience. We will introduce enough theory to help everyone understand what is happening, but we will not go deeply into mathematics. The course focuses more on application, recent advances, creative workflows, making and experimentation, and critical thinking about AI in general.
04I’m on the waitlist. What should I do?
Thank you so much for your interest in the course—we are genuinely thrilled by the incredible enthusiasm. The initial enrollment quota was 30, and we have worked closely with the department to expand it to 80. Unfortunately, we are unable to accommodate more than 80 students. Please remain on the official waitlist; if a place becomes available, enrollment will be handled through the department’s official process. There is no additional action you need to take for now, and you are very welcome to explore the publicly available course materials on this website.
Explore the course materials →05How is the workload for this course?
We expect the course to be lightweight, flexible, and enjoyable. There is no attendance requirement, and you are very welcome to use AI tools to support your learning and coursework. What matters most is that you understand the important ideas, gain genuine hands-on experience, share proactively with the class, and enjoy the process. AI can assist your work, but you should still be able to explain the choices you made and what you learned along the way.