mdarhdarz

Results 7 comments of mdarhdarz

> https://arxiv.org/abs/2305.18766 > > And now another loss function comes to light :) > > Seems very interesting and it's able to skip the refinement stage. I implement BGT+ loss...

You can take some inspiration from the repo pinned in my profile.

I guess what you want is this "https://github.com/liuyuan-pal/SyncDreamer".

yes, I have done sufficient experiments with SDXL successfully. Maybe I will share this if threestudio does not try SDXL.

Some basic suggestions: 1. Use fp16 fixed vae 2. Prepare gpus with more than 32G vram 3. Text encoder and text embeddings are different from sd1.5, and unet forward needs...

> @YG256Li Yeah I also facing the same issue where the 3D shape cannot converge when switching to SDXL. Moreover, when I use fp16 precision, sometimes the VAE will output...

> Hope to see more of this one day :D @g-l-i-t-c-h-o-r-s-e Here: https://github.com/fudan-zvg/PGC-3D