yanghb22-fdu / Hi3D-Official

[MM24] Official codes and datasets for ACM MM24 paper "Hi3D: Pursuing High-Resolution Image-to-3D Generation with Video Diffusion Models".
MIT License
212 stars 12 forks source link

Questions about self.label_emb #20

Open 2hiTee opened 6 days ago

2hiTee commented 6 days ago

Thanks for your wonderful work! I have a question that you said you based on pre-trained SVD to train the first stage Hi3D model. But the original SVD used FPS and bucket_id as the additional condition together with timestep embedding, and the dimension is 768. Here in the configuration file, I see you changed these two condition with elevation and aesthetic condition but starting with the same label embedding. Do you think this works well? Thanks!