You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@ziyaxuanyi offset noise and multires/pyramid noise are both "bandaid" attempts to address the issues (inability to generate very dark or very bright images) with the noise scheduling under typical noise scheduling used by SD and SDXL. It isn't required and doesn't have benefit to v-pred + ztsnr, or flow matching (which is what Flux and SD3 use). See https://arxiv.org/abs/2305.08891 for details on the issues with typical / epsilon noise scheduling.
Yes, you are right. I have modified the code to make it effective when training flux, and tested the generation effect of the training model. It has indeed deteriorated.
When I check the latest version of the code, I found that args.noise_offset is not working for flux training.
Why?Will it cause bad results?
The text was updated successfully, but these errors were encountered: