Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-19 09:14:35 +02:00
Code Issues Packages Projects Releases Wiki Activity

docs: cleanup

Browse Source
This commit is contained in:
CalamitousFelicitousness
2026-05-25 06:09:02 +01:00
parent a68ae8991d
commit 55db15c213
5 changed files with 29 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/test-anima-native-adapters.py
+1 -1
View File
@@ -8,7 +8,7 @@ custom Qwen3-projection MLP), or ``lora_te_*`` (Qwen3 text encoder). Routing
is parameterized in ``modules.lora.native_adapter`` via the ``network_prefix``
callable that ``pipelines.anima.anima_lora`` supplies.
Covers the eight families exposed through native_adapter's generics (LoRA,
Covers the families exposed through native_adapter's generics (LoRA,
LoKR, LoHA, OFT, IA3, GLoRA, Norm, Full), focused on:
- LoRA across all five recognized prefixes (BFL transformer / BFL llm_adapter /
test/test-flux2-native-adapters.py
+2 -2
View File
@@ -2,8 +2,8 @@
"""
Offline unit tests for Flux2/Klein native adapter loaders.
Covers the nine native families (LoRA, LoKR, LoHA, OFT, BOFT, IA3,
GLoRA, Norm, Full) plus DoRA threading via the universal
Covers the native families (LoRA, LoKR, LoHA, OFT, BOFT, IA3, GLoRA,
Norm, Full) plus DoRA threading via the universal
NetworkModule.finalize_updown hook, and ex_bias accumulation across
stacked Norm adapters.