Consistent123: One Image to Highly Consistent 3D Asset Using Case-Aware Diffusion Priors

Yukang Lin^* Haonan Han^* Chaoqun Gong Zunnan Xu Yachao Zhang⁺ Xiu Li⁺

SIGS, Tsinghua University

^*equal contribution ⁺corresponding author

Comparison

3D objects from a single image of RealFusion15 dataset.

Input

Comparison

3D objects from a single image of C10 dataset.

Input

Example generated assets

Consistent123 generates highly consistent 3D objects from a single image.