search

showlab / Show-1

Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation
https://showlab.github.io/Show-1/
Other
1.09k stars 62 forks source link

Download model #31

Closed shamu899063 closed 8 months ago

shamu899063 commented 10 months ago

I am in an area where the network is not very good, may I ask if the four models on the hugging face, base, interpolation, sr1, sr2, for example, under the text_encoder folder all have a bin with the name, pytorch_model-00001-of-00002.bin which is about 9GB. I would like to ask if these files are all the same and can be reused, because I see that there is nothing about modifying text_encoder in your paper.

junhaozhang98 commented 10 months ago

Thanks for your questions. base, interpolation, sr1 models share the same text encoder, which can be reused. sr2 has a different text encoder.