search

NasirKhalid24 / CLIP-Mesh

Official implementation of CLIP-Mesh: Generating textured meshes from text using pretrained image-text models
MIT License
422 stars 37 forks source link

Training the diffusion prior #5

Closed bluestyle97 closed 1 year ago

bluestyle97 commented 1 year ago

Hi, congratulations on your fantastic work! Could you please share the code for training the diffusion prior? I want to be more clear about some training details. Besides, I'm curious if the CLIP text embeddings and image embeddings are normalized when training the diffusion prior network. Thanks!

NasirKhalid24 commented 1 year ago

Hey - the training script is from the following repo, the embeddings used are LAION precomputed ones