New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Support loading more formats of flux diffusers models #1913

Draft

rockerBOO wants to merge 1 commit into kohya-ss:sd3 from rockerBOO:diffusers-flux-loading-flexibility

Contributor

rockerBOO commented Jan 30, 2025

Allow models to be loaded that are just the transformer https://huggingface.co/rockerBOO/Flux-Dev2Pro-fp8_e4m3fn
Allow reduced models to be loaded (they may not have 1-3 shards). There is a index weight_map file that showcases what modules are mapped. We can use this to get a list of shards.

Proposing this but needs further testing. For me it allows me to load a fp8 version of a model which has less shards but is in diffusers format.


          Support loading diffusers models without transformer and use weight_m…

464a3ea

…ap index file

rockerBOO changed the title ~~Support loading diffusers models~~ Support loading more formats of flux diffusers models

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet