flux
flux copied to clipboard
Why FLUX VAE is hard to learn on?
In DC-AE paper, I observed that the performance using FLUX's VAE was notably inferior. When comparing FLUX VAE and Stable Diffusion 1.5 VAE in my experiment, I found consistent results with the paper - FLUX VAE exhibited significantly slower convergence rates and bad performance compared to SD1.5 VAE.
Has anyone encountered similar issues or can explain the underlying reasons for this performance difference?