gwang-kim / DATID-3D

[CVPR 2023] Official implementation of "DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model"

Home Page:https://gwang-kim.github.io/datid_3d/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

3D Mesh for real image inputs

minar09 opened this issue · comments

Hi, thank you for the amazing work. The model can nicely generate images and videos for real image inputs, however, it's generating the same 3D meshes for all real image inputs in a single style. Although, its not the case for the meshes generated from the seeds of the fine-tuned checkpoint. Can you please help? Thanks.