Update app/main.py

Update app/main.py

Update app/main.py

Update app/changes_media_clicks.py

Create changes_media_clicks.py

Update app/database.py

Update app/database.py

Update app/main.py

Update app/database.py

Update app/config.py

Update app/main.py

Fix: Always store appname field in colorizations collection

Add AI-enhancer appname support with separate MongoDB connection

Fix MongoDB conflict error in log_media_click

Add collage-maker MongoDB support for media_clicks

Fix Firebase App Check token validation and add Postman collection

Add appname parameter support with collage-maker MongoDB integration

Update app/main.py

Add compressed image support with 2-3MB target file size - Add Compressed_Image_URL field to colorize endpoint response - Implement compress_image_to_target_size function with iterative quality/dimension adjustment - Original download_url returns uncompressed PNG (model output) - Compressed_Image_URL returns JPEG compressed to 2-3MB file size

Update app/main.py

Set fixed caption text for /colorize responses

Add CORS middleware to main.py for auth endpoints

Fix Firebase import handling in auth endpoints - Ensure firebase_admin is always defined - Fix Firebase initialization checks - Improve error messages

Add auth endpoints to main.py - Add /auth/register, /auth/login, /auth/me, /auth/refresh endpoints - Add Pydantic models for auth requests/responses - Add verify_request function for Firebase auth - Import httpx for Firebase REST API calls

Update health endpoint to match requested format with hf_inference_api and fal-ai

Update response formats for /colorize and /health endpoints - /colorize: Add filename, caption, change to PNG format, api_download_url - /health: Add model_type and provider fields

Make CCO model default for colorization - Change default model from GAN (dummy) to CCO (working) - Add fallback to GAN if CCO not available - Fix image format and saving issues

Make IPython import optional in colorizers to fix CCO model loading

Remove model_used field from response to maintain original response format

Integrate CCO colorization models (eccv16 and siggraph17) - Add CCO colorizers module from kinsung/cco - Update /colorize endpoint to support model selection parameter - Add scikit-image dependency - Maintain backward compatibility with existing GAN model - Update MongoDB logging to track model type used

Update app/database.py

Update app/database.py

Update app/database.py

Add ai_edit_daily_count tracking to media_clicks collection

Change ai_edit_last_date to MongoDB Date object format - Store as Date object instead of string format

Add ai_edit_complete and ai_edit_last_date to media_clicks collection

Add success/failure logging to colorizations collection

Only log to media_clicks when user_id is provided

Update default fallback category ID to 69368fcd2e46bd68ae1889b2

Set admin database name to adminPanel for media_clicks collection

Fix empty string handling and support both subCategories and categories schemas

Add MongoDB media click logging with per-user category counts

Fix MongoDB database boolean check - use 'is None' instead of truthiness

Fix Gradio compatibility: remove show_copy_button parameter

Add MongoDB integration for API call logging with timestamps

Update Firebase initialization to auto-detect credentials file and add setup guide

Add Firebase email/password authentication endpoints - Add /auth/register endpoint for user registration - Add /auth/login endpoint with Firebase REST API integration - Add /auth/me endpoint to get current user info - Add /auth/refresh endpoint for token refresh - Integrate with existing Firebase App Check - Add httpx and email-validator dependencies

Refactor to use Hugging Face Inference API with fal-ai provider - Replace local model loading with InferenceClient API - Remove heavy SDXL/ControlNet/BLIP model dependencies - Use FLUX.1-Kontext-dev model via API - Keep FastAPI and Firebase authentication - Significantly reduce memory usage (no local models)

Add memory optimizations for SDXL pipeline - Enable VAE slicing and tiling - Enable attention slicing for UNet and ControlNet - Use sequential CPU offloading for pipeline - Keep BLIP model on CPU to save GPU memory - Add torch.no_grad() and cache clearing - Reduce guidance scale for lower memory usage

Fix permission errors and environment variables for model loading - Use /tmp directory for writable model storage - Set OMP_NUM_THREADS and cache directories at startup - Add better error handling and permission checks