search

EnVision-Research / LucidDreamer

Official implementation of "LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching"
MIT License
749 stars 32 forks source link

How to finetune？ #27

Closed JAMESYJL closed 7 months ago

JAMESYJL commented 8 months ago

I want to load the trained LucidDreamer model and then proceed with further finetune, what should I do?

YixunLiang commented 8 months ago

Hi, sorry for the late reply, if you want to use other tech for finetuning, you can get the generated results in the “/output/” folder. If you want to further use our pipeline, you can add the path of generated results here to load the model: https://github.com/EnVision-Research/LucidDreamer/blob/fe499c0c2b1c070331ac54469eced2ad4aeda451/arguments/__init__.py#L117