Comment on BitsFusion: 1.99 bits Weight Quantization of Diffusion Model

<- View Parent
Even_Adder@lemmy.dbzer0.com ⁨3⁩ ⁨weeks⁩ ago

Unfortunately, this won’t work with SD3 since it doesn’t use a U-Net. I wonder how many people are still training 1.5 models?

source
Sort:hotnewtop