CalamitousFelicitousness 65e59e7224 feat(lora): z-image native lokr, loha and oft loaders ...

Add three adapter families to the z-image native loader and chain them
with the existing lora path through load_safetensors. Mixed-family
files (for example gta6_amateur_photography_zimagebase_v2.safetensors,
which carries lora and lokr groups in the same file) now load
completely instead of having one family silently dropped.

Shared helpers in pipelines/z_image/zimage_lora.py parse keys by
suffix list, rename legacy attention.out and attention.wo to
attention.to_out.0, and split fused attention.qkv into to_q/k/v. For
lora the split chunks the up weight along dim 0. For lokr the split
emits three NetworkModuleLokrChunk entries that share the tensors and
slice the kronecker product at apply time.

Fused attention.qkv for loha and oft is skipped with a warning. No
NetworkModuleHadaChunk exists, oft rotations are tied to out_features
and cannot be cleanly split across q/k/v, and no real z-image adapter
in that layout exists today.

load_safetensors for zimage chains try_load_lora, try_load_lokr,
try_load_loha and try_load_oft and merges their module dicts into a
single Network so mixed files load every module.

2026-04-14 21:48:19 +01:00

..

__init__.py

Restructure FP16 clamp patch into pipelines/z_image/patch_fp16.py subpackage

2026-04-13 11:18:56 +02:00

patch_fp16.py

linting

2026-04-13 12:18:05 +02:00

zimage_lora.py

feat(lora): z-image native lokr, loha and oft loaders

2026-04-14 21:48:19 +01:00