Skip to content

Flux lora training: Flux 1 & Flux Klein(4B & 9B) - #69

Merged
imprsnst merged 4 commits into
mainfrom
flux-lora
Sep 10, 2026
Merged

Flux lora training: Flux 1 & Flux Klein(4B & 9B)#69
imprsnst merged 4 commits into
mainfrom
flux-lora

Conversation

@imprsnst

Copy link
Copy Markdown
Collaborator

Summary

  • FLUX.1 dev: new model family, with a generation node and a LoRA training arch. Checkpoints are
    identified by their contents; schnell, Fill/Canny/Depth and Kontext are refused as training bases.
  • FLUX.2 klein Base 9B: new training base. The Base setting now picks 4B or 9B instead of
    whichever file sorts first.
  • App renaming

@imprsnst
imprsnst merged commit 594787a into main Sep 10, 2026
6 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant