Update api/main.py

Update api/main.py

Update api/main.py

Update api/main.py

Update api/main.py

Add ai_edit_complete and ai_edit_last_date fields to media_clicks collection

Only log to admin media_clicks if user_id is provided; regular MongoDB logging always happens

Improve admin Mongo database detection and error messages

Add logging status endpoint and improved admin Mongo initialization logging

first commit

Update api/main.py

Ensure mask matches resized image size

fix: correct indentation after else in /inpaint-multipart (line ~343)

feat: use fixed pink RGB bounds (lower=[150,0,100], upper=[255,120,255]) for /remove-pink and mask_is_painted in /inpaint-multipart; keep white=remove logic

fix: correct invert_mask logic - RGB masks already have white=remove, only invert if invert_mask=False explicitly requested

fix: preserve image quality by limiting resize to 3000px, add output verification, improve debug logging

fix: handle RGB masks correctly - use RGB channels when alpha is all 255, so white pixels become white in mask

fix: improve pink detection with multiple methods and add debug logging to diagnose removal issues

fix: correct binary mask encoding - pink pixels get alpha=0 so 255-alpha becomes white (255) for removal

refactor: use exact reference model implementation from aryadytm/remove-photo-object - simple 255-alpha inversion

fix: improve image quality with LANCZOS4 interpolation, better mask validation, and high-quality PNG output

fix: match reference model exactly - use simple 255-alpha inversion like aryadytm/remove-photo-object

fix: add debug logs for mask processing; verify output changes to diagnose removal issues

fix: fix indentation line 338 using Python script

fix: correct indentation error on line 338

docs: update /remove-pink endpoint docstring - clarify no black paint needed

fix(api): remove black paint detection - just auto-detect pink segments, everything else kept automatically

docs: add /remove-pink endpoint to API documentation

feat(api): add /remove-pink endpoint - simple one-parameter endpoint that auto-detects pink segments and removes them

feat(api): improve pink/magenta auto-detection with tolerance - automatically segment pink as white (remove), rest as black (keep)

fix: simplify mask processing to match reference model - direct white=remove detection

feat(api): auto-convert painted images to black/white masks (white=remove, black=keep) for better compatibility

fix(mask): improve mask detection - handle RGB paint directly, detect magenta and white areas; match reference model behavior

feat(api): improve painted mask detection - detect magenta (255,0,255) and other paint colors; better logging

fix(mask): ensure proper mask interpretation - selected areas are removed; add detailed logging

fix(mask): improve mask loading to match standard convention (white=remove); add debug logs

feat(api): add passthrough flag to return original image unchanged for /inpaint and /inpaint-multipart

feat(api): robust painted mask detection; fallback to dark-threshold when diff empty; add logs

feat(api): allow painted-on mask via mask_is_painted flag (auto-diff + Otsu threshold)

feat(api): support invert_mask flag for /inpaint and /inpaint-multipart (selected area removed by default)

feat: invert-mask option in UI and core; add docs (no secrets)

Update api/main.py

Update requirements.txt

Update api/main.py

fix: revert to sdk: docker for FastAPI

fix: change SDK from docker to streamlit to match app.py

feat(api): simplify /inpaint response to return only filename; update docs

feat(api): add /inpaint-url endpoint returning public download URL; docs updated

feat(download): make /download public; docs: add HTTP_API_Documentation.txt

Merge feature: inpaint direct image return