Support for diffusers model loading and fp16 variant loading

#1
by handsomesteve - opened

Hello, will it be possible to upload the unet, vae, text_encoder, text_encoder_2, tokenizer, tokenizer2 files into this repo? Particularly the fp16 variant as well. It will definitely help speed up loading and inference time.
Thank you!

Hello, I have uploaded the diffusers version for v3, and all of my models are already in fp16.

handsomesteve changed discussion status to closed
Your need to confirm your account before you can post a new comment.

Sign up or log in to comment