search

Tangshitao / MVDiffusion

MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion, NeurIPS 2023 (spotlight)
480 stars 25 forks source link

Questions about implementing code for panoramic generation #29

Closed 666666yl closed 11 months ago

666666yl commented 11 months ago

Hello,I am trying to implement your code for Panoramic generation recently, starting by running demo.py. However, I find the generated images are all solid color images. I wonder if I put the pretrained model in the wrong path, especially the files in stable-diffusoin-2-base. Could you please show the path for the files if possible? Thank you.

Tangshitao commented 11 months ago

Hi, You need to download the pretrain model here. (https://www.dropbox.com/scl/fi/yx9e0lj4fwtm9xh2wlhhg/pano.ckpt?rlkey=kowqygw7vt64r3maijk8klfl0&dl=0), and put it under weights/model.ckpt