Commit History

  1. Revert this session's changes back to the last known-good version⁠ Running

    f4e824d
  2. Refuse a head swap when the two heads face different ways, and say so⁠

    f008eb7
  3. Stop the seam blend from erasing the head swap⁠

    0ab4ea6
  4. Add a workflow PDF, and stop git rewriting line endings inside binaries⁠

    b1cd367
  5. Make glasses transfer opt-in — it was disfiguring glasses-wearing sources⁠

    f25d3bf
  6. Fix the empty hair matte, and stop pasting hair when HairFastGAN is unavailable⁠

    74dd70d

  1. Run swaps as background jobs, and add a Head Swap toggle to the app page⁠

    b60d8aa
  2. Super-resolve the head only, which makes real SR affordable on CPU⁠

    ddb0022
  3. Keep the original photo's background instead of downscaling and interpolating it⁠

    27e2136
  4. Confine scene grain to the parsed head instead of a box around it⁠

    9e549b6
  5. Fix Control Panel Google sign-in inside the Hugging Face iframe⁠

    bb3e953
  6. Turn Flask debug OFF by default and pre-warm models without blocking startup⁠

    e522792
  7. Fix scene-harmonisation regressions: quality scores, skin-tone reversal, long-hair gap⁠

    27bac33

  1. Add scene-harmonisation final pass: match the photo's grain + colour cast over the swapped head so the GAN-smooth face/hair stop looking synthetic/pasted and read as photographed with the scene

    4b38f72
  2. Hair robustness (100-img batch): lighting match only DARKENS hair (no grey wash on bright bg) + conservative grey-edge trim that won't cut lit/highlighted hair

    1addd52

  1. Fix facial discolour patches: restrict the neck/body skin pass to strictly below the chin (it was recolouring lips + cheek-ring -> patches on the face)

    c5fbe15
  2. Hair edge: soft strand edge for both paths (loosen clamp) + remove portrait grey crown by COLOUR not cropping -> no website grey line AND no hard cut-out, local/HF identical

    5f1915f
  3. Fix website grey hair line: raise scene-fill threshold + clamp matte to confident-hair extent (kills the faint grey crown haze); drop guided filter for local/HF parity (no ximgproc on HF)

    2cf928a
  4. Hair/forehead high-precision edge via guided filter (edge-aware matte) + gentle neck/body skin pass; opencv-contrib-headless on HF for ximgproc

    1544cc7
  5. Hair edge: composite with BiSeNet SOFTMAX hair matte (soft strand alpha) instead of a feathered binary mask -> real wispy hair edges, no cut-paste look, both genders

    6ae45af
  6. Hair edge: smoother feather (0.025) for natural soft edges both genders, no hard cut-off; gentler lighting keeps it grey-free

    324e77e
  7. Hair edge: crisper feather + erode-to-solid + gentler lighting match -> natural hairline, no grey fringe on dark hair

    0d2a722
  8. Hair blend: fill portrait grey padding with the scene before feathering (kills the blurry pasted halo) + tighter edge feather -> natural hair edges

    34e8dd6

  1. Hair swap: run Laplacian blend BEFORE hair (it was overwriting transferred hair with target's); opaque core + soft edge + recolour residual old hair for a seamless blend, both genders

    e8b68af
  2. Skin tone: single uniform LAB offset over whole skin (no gate/per-region) -> no patches; verified clean across 10 tones light-to-dark, strength 0.92

    8478059
  3. Skin tone: recolour face-skin + body to SOURCE complexion (sampled from clean parsed skin, lips/eyes excluded, relative luminance gate) — clean on normal faces

    ddb96a3
  4. Skin tone: leave face untouched (swap already source-toned), only lift neck/arms/hands to match face — fixes blue/blotchy face patch

    e711814
  5. Move skin-tone match to final pipeline step so the Laplacian blend can't undo it (output skin now matches source across whole body); strength 0.9

    5b7670e
  6. Skin tone: drive face+neck+body to SOURCE complexion (per-region delta), with luminance gate so beard/brows don't go blue

    e3164c8
  7. Skin tone: blend across whole body (face+neck+arms+hands) via adaptive chroma mask, clothes/background excluded

    9d2db57
  8. Fix close-up selfie detection: pad margin so face-fills-frame photos are found (0 faces -> crude paste was the no-hair/skin bug)

    f0e4246
  9. Fix hair composite: widen parse crop + region clamp so long hair transfers into scene (re-enable hair by default)

    1940cda
  10. Hair swap back to opt-in: in-scene hair composite loses the hair (verified)

    d189e1b
  11. Enable source hair+neck transfer by default (HairFastGAN on GPU, BiSeNet fallback)

    8bcbc72

  1. Remove percentage from loading bar

    d69a33b
  2. Loading bar: motivational admission-nudging messages instead of process steps

    1d240a0
  3. Tighten skin-tone match 0.75 -> 0.85 (closer to source; glasses transfer already on)

    85ce30c
  4. Redesign loading tab: friendly messages (no internal pipeline jargon) + spinner/percentage

    afbdbab
  5. Default to the clean face swap; make head-swap & hair-swap opt-in⁠

    ca509be
  6. Auto de-roll tilted source faces (eye-line alignment) before swap

    8eed89d
  7. Add batch QA test harness (scripts/batch_test.py)⁠

    8a16253
  8. Wire HairFastGAN (GPU) into the swap pipeline for realistic hair transfer⁠

    75fd366
  9. GPU: 1536px working res on CUDA + GPU deploy files (Dockerfile.gpu, requirements-gpu.txt)⁠

    136db11
  10. Enable GPU for InsightFace: auto-add CUDA12 + cuDNN9 DLL dirs on Windows⁠

    e323c6f
  11. Swap only the main subject + always run face swap (fixes the mess)⁠

    4a2b4cf
  12. Retry HF push on transient failures (Space busy building)⁠

    2499381
  13. Resolve all project errors: clean lint, tests, imports⁠

    29b87a5
  14. Revert swap-quality regressions: skin 0.92->0.75, glasses face-swap-path only⁠

    7d36805
  15. Fix: list_locations resilient when message column missing (was showing 0)⁠

    83651d7

  1. Custom per-location result messages + unique defaults; remove em-dashes & "4K"⁠

    0550cee