nodes/ethanfel-ComfyUI-LoRA-Optimizer
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
333 Commits 9 Branches 0 Tags
284bdbc954450ef14177a4e2cb293d7a86ec6c50
Commit Graph
14 Commits
Author SHA1 Message Date
EthanfelandClaude Opus 4.6 b273cd8cf9 docs: remove all calibration_data references from documentation 
Clean up README, wiki Nodes, How-It-Works, and maintainer sync docs
to reflect removal of calibration_data feature.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-08 19:00:55 +01:00
EthanfelandClaude Opus 4.6 7959ce81fd merge: integrate PR #1 correctness refactor into test branch 
Merges srv1n's correctness refactor (PR #1) with conflict resolution
to preserve our recent setting renames and fixes while incorporating
their core improvements:

- Target-key grouping: analysis/merge operates on resolved model weights
  instead of raw LoRA prefixes, fixing trainer-specific aliasing bugs
- Exact low-rank linear patches: lossless linear merges for weighted_sum
  and weighted_average when no nonlinear ops are needed
- Excess conflict metric: sign disagreement beyond statistical expectation
  (cosine-sim aware), replacing raw conflict ratio in decisions
- Subspace overlap: measures how much LoRA weight perturbations align
- Block smoothing: reduces noisy per-prefix mode flips
- Activation-aware calibration scoring for Phase 2 quality evaluation
- ACE-Step architecture support
- Soft LoKr/LoHa imports for graceful degradation
- RS-LoRA compensation re-enabled with safe heuristic
- 519-line test suite (19 tests, all passing)

Conflict resolution kept our:
- Setting renames (merge_refinement, patch_compression, strategy_set)
- Qwen-Image detection fix
- LoRACompatibilityAnalyzer node
- Conflict-mode masking in _apply_conflict_modes (PR's approach)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-08 14:19:34 +01:00
EthanfelandClaude Opus 4.6 63f54f73a4 docs: add merge strategy guide and update README setting references 
Add educational SVG/PNG diagram explaining orthogonal vs conflicting vs
aligned LoRA relationships and when to change merge settings. Update all
README references to use new setting names (merge_refinement,
patch_compression, strategy_set, additive).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-08 13:19:13 +01:00
srv1n 15eb41a758 Remove local paths from maintainer note 2026-03-08 16:13:13 +05:30
srv1n 561249f096 Tighten reviewer-facing maintainer note 2026-03-08 16:08:59 +05:30
srv1n dad533a4f3 Expand maintainer handoff summary 2026-03-08 16:06:52 +05:30
srv1n be7cb96f1e Sync correctness refactor onto upstream dfd3920 2026-03-08 16:02:45 +05:30
EthanfelandClaude Opus 4.6 38d288659c docs: add AutoTuner diff cache design 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-06 02:38:52 +01:00
EthanfelandClaude Opus 4.6 b47736e1cf docs: add wiki pages and bump version to 1.2.2 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-06 01:39:14 +01:00
EthanfelandClaude Opus 4.6 7d2f1ad623 chore: remove remaining plan docs from tracking (gitignored) 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-04 18:26:21 +01:00
EthanfelandClaude Opus 4.6 b5c43f6621 chore: remove plan doc from tracking (gitignored) 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-04 18:26:08 +01:00
EthanfelandClaude Opus 4.6 043c8200a4 docs: add WanVideoLoRAOptimizer design document 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-04 18:17:16 +01:00
EthanfelandClaude Opus 4.6 c916642263 Add architecture-aware key normalization implementation plan 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-03 14:15:01 +01:00
EthanfelandClaude Opus 4.6 b79d897325 Add architecture-aware key normalization design doc 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-03 13:24:17 +01:00