“Rodin: 3D Asset Creation with a Text/Image/3D-Conditioned Large Generative Model for Creative Frontier” by Zhang, Zhang, Wang, Xu and Yu
Conference:
Type(s):
Entry Number: real_114
Title:
- Rodin: 3D Asset Creation with a Text/Image/3D-Conditioned Large Generative Model for Creative Frontier
Developer(s):
Description:
Rodin advances 3D creative frontier with its 3.0B-parameter generative model, incorporating a Latent Diffusion Transformer (DiT) architecture. Its scalable 3D ControlNet enables artists to create 3D assets with quad-faces and PBR textures through text/images, and even interactive 3D inputs (i.e., BoundingBox), bringing 3D GenAI closer to production-ready than ever before.
ACM Digital Library Publication:
Submit a story:
If you would like to submit a story about this experience or presentation, please contact us: historyarchives@siggraph.org