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

..

__init__.py

linting

2026-07-03 22:05:33 +02:00

extra_networks_lora.py

fix(lora): disable diffusers-method loras on removal

2026-07-08 03:06:47 +01:00

lora_apply.py

lora guard against param change on-the-fly

2026-07-01 15:53:38 +02:00

lora_common.py

modernize typing

2026-02-19 09:15:37 +01:00

lora_convert.py

fix(lora): handle flattened clip text model in kohya te keys

2026-07-08 03:05:30 +01:00

lora_diffusers.py

feat(lora): surface method-selection reason in load logs

2026-05-10 00:05:37 +01:00

lora_extract.py

fix(lora): handle flattened clip text model in kohya te keys

2026-07-08 03:05:30 +01:00

lora_load.py

fix(lora): disable diffusers-method loras on removal

2026-07-08 03:06:47 +01:00

lora_nunchaku.py

cleanup logger

2026-02-19 11:09:13 +01:00

lora_overrides.py

feat(krea2): add Krea 2 (K2) image model support

2026-06-23 04:41:54 +01:00

lora_timers.py

modernize typing

2026-02-19 09:15:37 +01:00

lyco_helpers.py

full codespell coverage

2026-06-04 12:36:10 +02:00

native_adapter.py

feat(lora): handle bias companion keys on fused-qkv targets

2026-07-14 08:06:45 +01:00

network_boft.py

feat(flux2): native BOFT (butterfly-OFT) support

2026-05-10 00:05:37 +01:00

network_full.py

Major lora refactor: works on my machine edition

2024-11-23 21:57:03 -06:00

network_glora.py

fix(lora): set GLora dim so alpha scaling is applied

2026-05-09 22:04:42 +01:00

network_hada.py

feat(lora): add NetworkModuleHadaChunk for fused-weight LoHA targets

2026-05-09 23:16:09 +01:00

network_ia3.py

Major lora refactor: works on my machine edition

2024-11-23 21:57:03 -06:00

network_lokr.py

refactor(lora): move NetworkModuleLokrSliceChunk to network_lokr

2026-05-18 23:18:31 +01:00

network_lora.py

fix(lora): support embedding-target LoRA and companion bias deltas

2026-06-23 20:40:42 +01:00

network_norm.py

lint fixes

2024-11-29 08:01:26 -05:00

network_oft.py

fix(lora): guard OFT constraint for LyCORIS oft_diag files

2026-05-09 22:04:17 +01:00

network.py

fix(lora): scale the dora diff before the decompose norm

2026-07-14 08:06:45 +01:00

networks.py

fix lint

2026-07-08 09:50:26 +02:00