mirror of
https://github.com/vladmandic/automatic
synced 2026-08-26 15:16:01 +02:00
387a349dfd
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