nitrosocke

/

spider-verse-diffusion

like 343

Hi @nitrosocke :)

I want to ask why is common to provide the .ckpt file?

I was thinking that the .ckpt file was like a compressed version that could be loaded for faster inferences.
But every time I search how to do that, the .ckpt file is uncompressed and then are obtained folders like 'unet', 'vae', 'scheduler', etc.
And those folders are used to initiate the pipeline.

Is it only for have a compressed version and allow faster transfers?

Thanks in advance.