This workshop is for the 8th installment of the AI for Creative Visual Content Generation Editing and Understanding (CVEU), which follows its success on the previous launch at SIGGRAPH'25, CVPR'25, CVPR'24, ICCV'23, ECCV'22, ICCV'21, a Generative Models Course at SIGGRAPH'24, 2023 Paris ShortFest AI Film Festival, and 2025 Hong Kong HKUST AI Film Festival.
It brings together researchers, artists and entrepreneurs working on computer graphics, human computer interaction, computer vision, machine learning, and cognitive research. It aims to bring awareness of recent advances in machine learning technologies to enable assisted creative visual content creation and understanding. Find more at the SIGGRAPH ASIA'25 official link.
Schedule | Hong Kong Time 2025-12-15 |
---|---|
Unit 1: Diffusion & Multimodal Foundations
• Latent diffusion, cross-attention, LoRA/ControlNet, image-text alignment • Rapid Colab demo |
|
Unit 2A: Prompt Craft & Style Control
• Prompt taxonomy (subject, camera, lighting, mood), negative prompts, classifier-free guidance • Hands-on: multiple distinct shot styles |
|
Unit 2B: Mixed-Initiative Tool-Chains & Lab
• Group task: build a six-shot sequence from a log-line • Export contact sheet |
|
Unit 3A: The Aesthetics of Noise in Generative AI
• Metastability, indexicality, multiplanarity; temporality in predictive generation • Illustrated talk with case study |
|
Unit 3B: VR Storytelling & AI Collaboration
• Cinematic VR virtual reality education, production workflow, emerging AI tools • Comparative case discussion |
If you want to explore with us more about how AI is shaping the future of filmmaking, we invite you to tune in to podcast Empowering Storytellers .
Governor, Asia-Pacific Region, Society of Motion Picture and Television Engineers (SMPTE)
Senior 3D Generalist & Technical Advisor, Wētā Workshop
Art Director, Wētā Workshop
Dean, School of Film and Television, The Hong Kong Academy for Performing Arts
2D Animator & Motion Designer