×
Tencent’s new open AI model turns images and text to 3D models
Written by
Published on
Join our daily newsletter for breaking news, product launches and deals, research breakdowns, and other industry-leading AI coverage
Join Now

Tencent has released Hunyuan3D 2.0, an artificial intelligence system that transforms single images or text descriptions into detailed 3D models within seconds, dramatically reducing a process that traditionally takes skilled artists days or weeks to complete.

Key innovation: The system employs a two-component architecture that creates basic shapes and adds surface details while ensuring consistency across all viewpoints of the generated 3D models.

  • The Hunyuan3D-DiT component handles basic shape generation
  • Hunyuan3D-Paint adds detailed surface textures and features
  • A new guidance system ensures coherence across multiple viewpoints of the object
  • Strategic camera positioning captures maximum visible area, including traditionally difficult areas like tops and bottoms

Technical achievements: Hunyuan3D 2.0 demonstrates significant performance improvements over existing solutions while maintaining accessibility.

  • The standard version generates complete 3D models in approximately 25 seconds
  • A lightweight version completes the process in just 10 seconds
  • The system achieves a CLIP score of 0.809, outperforming both open-source and proprietary alternatives
  • New methods for increasing detail while managing computational requirements make the system more practical for widespread adoption

Industry applications: The technology offers practical benefits across multiple sectors requiring 3D content creation.

  • Game developers can rapidly prototype characters and environments
  • E-commerce platforms can generate 3D product visualizations
  • Film studios can preview special effects more efficiently
  • The system works with standard design software, enabling immediate professional implementation

Accessibility and distribution: Tencent has made the technology widely available through popular development platforms.

  • The complete system is available as an open-source project
  • Code and models are accessible through both Hugging Face and GitHub
  • Developers can integrate the technology into existing workflows
  • The system accepts both text and image inputs for enhanced versatility

Future implications: While this advancement represents a significant step forward in automated 3D content creation, it raises important considerations about the evolving role of artists and creators.

  • Tencent positions the technology as a complementary tool rather than a replacement for human artists
  • The system handles technical aspects, allowing creators to focus on artistic decisions
  • The technology could democratize 3D content creation across industries
  • Questions remain about how this will impact traditional 3D modeling workflows

Looking ahead: As the demand for 3D content continues to grow across gaming, e-commerce, and entertainment sectors, tools like Hunyuan3D 2.0 suggest a future where technical barriers to 3D creation are significantly reduced, shifting the focus from how to create 3D content to how to best utilize these new capabilities for innovative applications.

Tencent introduces ‘Hunyuan3D 2.0’ AI that speeds up 3D design from days to seconds

Recent News

Royally pained: King Charles’ charity warns AI could widen global digital divide

Despite AI advancements championed by King Charles III's charity, millions worldwide lack basic digital access, threatening to deepen global inequality unless governments and businesses implement inclusive technology policies.

AI chatbots are transforming mental health care amid global therapist shortage

AI chatbots provide 24/7, stigma-free mental health support amid a global shortage of professionals, though they remain better suited for mild to moderate issues than severe conditions.

Crunchy AI: Softmax’s “organic alignment” approach draws from nature to reimagine AI-human collaboration

Inspired by ant colonies and natural systems, Softmax aims to develop AI that collaborates with humans through coordination principles rather than hierarchical control.