3 Commits
Author SHA1 Message Date
doggeddalle 4ef4de0a5d Robust adaln, pdd, keymap, modality fixes
Multiple improvements and hardening across the Power LoRA stack:

- adaln: stronger caching (file-version keys), device-safe grid/basis computation, normalized tensor hashing for basis cache, more robust table-to-table rebasing with residual checks and fallback, better detection of adaLN weight name variants.
- apply: validate numeric strengths, reject unsupported passengers, handle loading errors, detect shape mismatches, track rejected/skipped/quantized merges, improved PDD handoff and reporting.
- pdd: introduce movable PddBank/PddState, register banks as additional models, thread-local PDD context, strength-scheduled blending and safer interval clamping.
- keymap/detect/gain/modality/nodes/branch: add support for varied LoRA key spellings, more validation, skip incomplete adapters, and small bugfixes.
- server: surface partial calibration note.
- pyproject/README/.gitignore: packaging, docs, and ignore cleanup; add Python >=3.10 requirement and publisher repo fix.
- web UI: fix balance button behavior, safer auto-balance error handling and factor sanitization.
- tests: add unit tests for adaln, modality and pdd.

Overall: better robustness to varied LoRA formats, mixed devices, malformed inputs, and improved user-facing error/reporting.
2026-08-28 02:22:53 +10:00
doggeddalle 8c4aad1135 Add audit report and Apache-2.0 license
Add a full technical AUDIT_REPORT.md (2026-08-08) documenting priority findings and recommended fixes. Add Apache-2.0 LICENSE file and update README to reference the license. Update pyproject.toml to declare license as Apache-2.0 (replacing MIT). These changes add project licensing and a comprehensive audit summary for maintainers and users.
2026-08-08 22:29:25 +10:00
doggeddalle 28ac439a26 Add MiniMax H3 Power LoRA Stack
Add a ComfyUI plugin implementing a stacked multi-LoRA loader for MiniMax H3. Introduces H3PowerLoraStack and H3LoraInspector node classes, plus modules: adaln (adaLN dense↔curve basis conversion), branch (runtime low-rank branches for quantized weights), apply (stack orchestration), detect (safetensors header introspection), keymap (key normalization), nodes, and a web UI (h3_power_lora_stack.js). Includes pyproject metadata and README. Preserves quantized kernels via branching, rebases adaLN pairs, handles many naming conventions, and provides a browser picker and per-LoRA reporting.
2026-08-08 19:27:06 +10:00