10 Commits
Author SHA1 Message Date
Ethanfel 27482bb81a fix: restore inline loader parity and retire legacy nodes (1.8.6)
Track exact stock-loader calls across equal strengths, disjoint targets and MODEL/CLIP-only slots. Preserve captured CLIP biases and emit stock-loadable CLIP export aliases.

Remove the Legacy optimizer registration, both WanVideoWrapper-specific nodes, obsolete bridge UI and bundled legacy example. Document replacements and add stock-loader/file-stack/export parity checks to CI. Existing workflows using removed nodes require migration.

Validate the staged tree: 1064 Python tests and 69 subtests passed; 3 CUDA-only skipped; JS migrations and real ComfyUI round trips passed. Keep the rejected H3 search prototype and unrelated plans out of this release.
2026-09-09 12:45:10 +02:00
Ethanfel a5e80a9601 fix: preserve MiniMax H3 merge fidelity 2026-08-24 14:06:06 +02:00
Ethanfel 72911cb7f7 feat: add MiniMax H3 support 2026-08-16 09:53:55 +02:00
EthanfelandClaude Opus 4.8 487385cf60 docs: sync README + wiki to v1.7 (new nodes, params, architectures)
Bring the documentation up to date with the 1.7.0 / algo 1.10.2 state:
- README: document Conflict Editor, Merge Formula, Metadata Reader, Extract
  from Model, Combination Generator; fill param gaps (clip_strength_multiplier,
  dare_dampening, scoring_svd/device/formula, memory_mode, record_dataset,
  output_strength=-1 auto); clarify HunyuanVideo is dit-preset-only (not auto-detected).
- Wiki: add 7 missing nodes to Nodes.md; fix stale option lists (scoring_svd 4
  modes, memory_mode auto_ignore_strength, community_cache upload_only); add
  acestep_dit + Ideogram 4 to architecture tables; fix Home arch count (8->9);
  replace obsolete quality-level/profile names (enhanced+/maximum -> refine+/full,
  classic/v1.2 -> basic/full strategy sets).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-15 15:19:02 +02:00
EthanfelandClaude Sonnet 4.6 3b4a574355 feat: drop download_only — community cache is upload_and_download only
Removes the passive download_only option to encourage contribution.
Users who want community results need to also contribute back.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-04 15:27:19 +02:00
EthanfelandClaude Sonnet 4.6 620399d3c1 feat: add community_cache — HF-backed shared analysis results
Replaces dead record_dataset param with community_cache dropdown
(disabled / download_only / upload_and_download).

Downloads are anonymous via urllib; uploads require HF_TOKEN and
huggingface_hub. LoRA filenames are never shared — content hashes
(SHA256[:16]) are used as keys. Per-LoRA/pair conflict metrics and
winning merge configs are shared; network errors fall back silently to
the full local sweep.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-04 13:39:56 +02:00
EthanfelandClaude Sonnet 4.6 91f514e291 docs: document memory_mode, selection, output_mode, and caching infrastructure
- Add memory_mode, selection, output_mode to AutoTuner entries in Nodes.md
- Add output_mode, memory_mode, selection sections to Configuration-Guide
- Add AutoTuner Caching Infrastructure section covering all three cache types
  (.memory.json, .analysis.json, .analysis.partial.json) and how to clear them
- Add 3 troubleshooting entries for cache-related issues in Tips-and-Troubleshooting
- Update speed tip to mention memory_mode=auto

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-03 20:20:44 +02:00
EthanfelandClaude Opus 4.6 4ae79d0c9e docs: add v2 workflow, rename Legacy, update wiki for Settings nodes
- Add example_workflows/LoRa Optimizer v2.json for the new node layout
- Rename LoRA Optimizer (Advanced) → (Legacy) across all wiki pages
- Document Settings nodes (Merge, Optimizer, AutoTuner) in Nodes.md
- Add Settings and Compatibility Analyzer workflows to Workflows.md
- Add decision_smoothing, smooth_slerp_gate, scoring_speed/formula,
  and Settings node architecture to Configuration-Guide.md
- Update How-It-Works.md node registry and variant descriptions
- Rename patch_compression non_ties → smart in all references
- Update Home.md feature table (8 architectures, settings nodes)
- Add zit_example_1.png asset
- Update SVG assets (timeline, pipeline, bridge, ties, merge-use-cases)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-09 22:56:19 +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 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