facok 531fb5fd1a Fix sharpness calibration: use same base images for all blur levels ...

- Generate base images once upfront, then apply all blur levels to the
  SAME images (was generating different random images per blur level)
- Add separable convolution for kernel_size > 15 (O(2k) vs O(k²))
- Add kernel caching to avoid recomputation
- Add per-blur-level progress logging

This matches SubspaceLab's methodology and ensures PCA receives
properly paired stimuli (same image × multiple blur levels).

2026-03-20 13:34:45 +08:00

..

__pycache__

Add progress output to calibration

2026-03-20 03:02:04 +08:00

__init__.py

Add docstrings to all public functions, classes, and methods

2026-03-17 02:26:21 +08:00

calibration.py

Add progress output to calibration

2026-03-20 03:02:04 +08:00

color_space.py

Refactor: extract shared _hue_lerp and _wrap_hue_diff helpers

2026-03-19 18:14:13 +08:00

defaults.py

Add docstrings to all public functions, classes, and methods

2026-03-17 02:26:21 +08:00

diagnostics.py

Refactor: extract shared _hue_lerp and _wrap_hue_diff helpers

2026-03-19 18:14:13 +08:00

lcs_data.py

Add docstrings to all public functions, classes, and methods

2026-03-17 02:26:21 +08:00

patchify.py

Implement LCS plugin for training-free color control in FLUX

2026-03-17 01:43:26 +08:00

sampling.py

Fix sharpness calibration and simplify intervention hook

2026-03-20 13:12:46 +08:00

sharpness.py

Fix sharpness calibration: use same base images for all blur levels

2026-03-20 13:34:45 +08:00

timestep.py

Implement LCS plugin for training-free color control in FLUX

2026-03-17 01:43:26 +08:00