Leveraging generative AI for 3D content generation | Moritz Schwind - Entagma | OFFF HIVE 2025
109This talk demonstrates how cutting‑edge generative‑AI tools — Trellis, Hunyuan, and curated Hugging Face/Civitai models — can be leveraged inside Houdini’s procedural system to yield prompt‑driven meshes. We cover how generative AI amplifies procedural workflows, unlocking rapid iteration, flexible & controllable stylistic exploration, and on‑the‑fly design variations unattainable through traditional methods. Attendees leave with a principled methodology for deploying scalable, exploratory 3‑D pipelines in design driven production environments.
Moritz Schwind is gonna take part in it all - Be it pixels, hardware, code or cameras. And sometimes even reassemble it. In his spare time, he likes to dabble with code and create generative artwork. He claims his early exposure to QBasic is no help at all when working in Houdini, Blender, Processing or Arduino. But it might have been what started his fascination for the boundaries of code and art. When not wreaking havoc to any intriguing devices around him, he works as a freelance Technical and Art Director. His more recent areas of interest cover the use of scientific algorithms in generative design and the application of AI in creative fields.
https://entagma.com/
00:00:00 – Intro & Setup
00:06:11 – Image-to-Mesh with AI
00:12:22 – Gradio & Virtualization Layers
00:18:36 – Houdini Integration & Asset Texturing
00:24:48 – Mesh Refinement & Quick Mockups
00:30:59 – Tools, Research, & Creative Use
00:37:12 – AI Bias, Fear, & Future Pipelines