Files
automatic/test
CalamitousFelicitousness 387a349dfd fix(lora): scale the dora diff before the decompose norm
finalize_updown ran apply_weight_decompose on the unscaled delta and
multiplied the result by alpha/rank afterward. LyCORIS and ComfyUI both
bake alpha/rank into the diff before computing the row norms, so any
DoRA with alpha != rank renormalized against the wrong merged weight
(64% relative delta error for kohya-style alpha=1 rank=8; exact only
when alpha == rank, which full-matrix LoKR forces).

- scale updown by calc_scale() before apply_weight_decompose; apply
  only the multiplier afterward
- multiplier lerps the full merged delta (0 disables, 1 equals the
  trainer output); LyCORIS weight-mode ratio interpolation leaves the
  diff applied at multiplier 0 and is not used
- add a numeric regression test mirroring the LyCORIS forward reference
2026-07-14 08:06:45 +01:00
..
2026-02-10 14:31:53 +01:00
2026-04-21 19:24:24 +02:00
2026-04-01 10:29:08 +02:00
2026-07-04 15:26:36 +02:00