Search papers, labs, and topics across Lattice.
Hunyuan3D-Buffalo 1.0 introduces a unified multimodal framework that integrates 3D understanding, text-to-3D generation, instruction-guided editing, and text-grounded part generation, addressing the limitations of existing models due to the scarcity of large-scale multimodal data. The model is trained on an extensive 87M-scale 3D multimodal corpus, which includes a diverse range of understanding, generation, and editing samples, thereby enhancing its capabilities. Experimental results demonstrate that this framework achieves state-of-the-art performance in text-to-3D generation and 3D editing tasks, while also showing that improved understanding and generation capabilities positively influence editing outcomes.
A single model can now seamlessly generate, understand, and edit 3D content, revolutionizing how we approach multimodal AI tasks.
Recent advances in image generation have demonstrated the potential of unified multimodal models that integrate understanding, generation, and editing. However, unified 3D modeling remains constrained by scarce multimodal data, particularly the lack of large-scale and geometrically consistent editing data. To address this limitation, we propose Hunyuan3D-Buffalo 1.0, a unified framework supporting 3D understanding, text-to-3D generation, instruction-guided 3D editing, and text-grounded part generation within a single architecture. To enable scalable training, we construct an 87M-scale 3D multimodal corpus, comprising 25M understanding samples, 50M text-to-3D pairs, and 12M editing pairs generated using Nano3D-v2. Architecturally, the framework combines Hunyuan3D-VLM for semantic, structural, and spatial understanding with Hunyuan3D DiT for high-fidelity 3D synthesis. The VLM provides multimodal semantic conditions for generation, while editing and part generation additionally condition the diffusion process on the source object representation to preserve its overall structure and unedited regions. Extensive experiments show that Hunyuan3D-Buffalo 1.0 achieves state-of-the-art or leading performance on text-to-3D generation and 3D editing benchmarks, while exhibiting strong understanding and part-generation capabilities. Our analysis further shows that both generation and understanding improve editing, demonstrating the effectiveness of unified 3D multimodal training. Project Page: https://tencent-hunyuan.github.io/Hunyuan3D-Buffalo1.0/
