cicalooo-ComfyUI-H3-PowerLoraStack

22 Commits 1 Branch 0 Tags

3 Commits

Include renames

Author	SHA1	Message	Date
cicalooo	17f019c061	Blend PDD heads as row 0 plus offsets Core treats later bank rows as offsets from the first head. set_weight files already use that layout; proj_out banks are converted before the same blend.	2026-10-11 15:31:21 +11:00
cicalooo	023f1451ad	Match current H3 PDD ABI and slice large LoRA residuals Current ComfyUI passes sigma, sample_sigmas, and shifts into FinalLayer. Accept those directly and keep the thread-local schedule as a fallback. Apply large LoRA residuals in token slices so fc1/qkv does not allocate a second full activation, and broadcast the bias instead of slicing it when sequence length equals the output width.	2026-10-11 13:24:28 +11:00
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

Author

SHA1

Message

Date

cicalooo

17f019c061

Blend PDD heads as row 0 plus offsets

Core treats later bank rows as offsets from the first head. set_weight files already use that layout; proj_out banks are converted before the same blend.

2026-10-11 15:31:21 +11:00

cicalooo

023f1451ad

Match current H3 PDD ABI and slice large LoRA residuals

Current ComfyUI passes sigma, sample_sigmas, and shifts into FinalLayer. Accept those directly and keep the thread-local schedule as a fallback. Apply large LoRA residuals in token slices so fc1/qkv does not allocate a second full activation, and broadcast the bias instead of slicing it when sequence length equals the output width.

2026-10-11 13:24:28 +11:00

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