Recent advances in 3D-native generative models have accelerated asset creation for games, film, and design. However, most methods still rely primarily on image or text conditioning and lack fine-grained, cross-modal controls, which limits controllability and practical adoption. To address this gap, we present Hunyuan3D-Omni, a unified framework for fine-grained, controllable 3D asset generation built on Hunyuan3D 2.1. In addition to images, Hunyuan3D-Omni accepts point clouds, voxels, bounding boxes, and skeletal pose priors as conditioning signals, enabling precise control over geometry, topology, and pose. Instead of separate heads for each modality, our model unifies all signals in a single cross-modal architecture. We train with a progressive, difficulty-aware sampling strategy that selects one control modality per example and biases sampling toward harder signals (e.g., skeletal pose) while downweighting easier ones (e.g., point clouds), encouraging robust multi-modal fusion and graceful handling of missing inputs. Experiments show that these additional controls improve generation accuracy, enable geometry-aware transformations, and increase robustness for production workflows.
@article{arxiv.2509.21245,
title = {Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets},
author = {Team Hunyuan3D and : and Bowen Zhang and Chunchao Guo and Haolin Liu and Hongyu Yan and Huiwen Shi and Jingwei Huang and Junlin Yu and Kunhong Li and Linus and Penghao Wang and Qingxiang Lin and Sicong Liu and Xianghui Yang and Yixuan Tang and Yunfei Zhao and Zeqiang Lai and Zhihao Liang and Zibo Zhao},
journal= {arXiv preprint arXiv:2509.21245},
year = {2025}
}