1.58-Bit Flux
by reynaldi on 1/1/2025, 3:47:45 PM
Some impressive results
> 1.58-bit FLUX achieves a 7.7× reduction in model storage and more than a 5.1× reduction in inference memory usage
Some impressive results
> 1.58-bit FLUX achieves a 7.7× reduction in model storage and more than a 5.1× reduction in inference memory usage