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 guide for finding FastAI-compatible colorization models - Document how to find models with .pkl files - Add instructions for setting MODEL_ID - Note current model limitation

Switch to FastAI GAN colorization model (Hammad712/GAN-Colorization-Model)

Restore local ControlNet colorization pipeline

Switch colorization to HF Inference API

Align pipeline with text-guided colorization Space

fix: write data under /data and move Firebase creds path to /data; mount static from resolved dirs

feat(auth): accept Firebase Auth id_token (Authorization Bearer) in addition to App Check; add Postman collection and test script; default MODEL_ID to ControlNet color

Initial commit: Colorize API with Firebase App Check integration