Fix Gradio permission error by setting GRADIO_TEMP_DIR to /tmp

Add fallback logic to handle PyTorch models and find actual model files - Add manual download fallback when from_pretrained_fastai fails - List repository files to find .pkl or .pt files - Provide clear error message for PyTorch models

Fix python-multipart version conflict with Gradio - Update python-multipart from 0.0.6 to >=0.0.18 to match Gradio requirements

Fix Gradio/FastAPI compatibility - Upgrade FastAPI to >=0.115.0 - Upgrade Gradio to >=4.44.0 to fix AttributeError

Integrate FastAI colorization with Firebase auth and Gradio UI - Replace main.py with FastAI implementation - Add Gradio interface for Space UI - Add Firebase authentication to /colorize endpoint - Add curl examples documentation - Update test.py with User-Agent headers

Detect PyTorch models and provide clear error message - Repository contains generator.pt (PyTorch) not FastAI model

List repository files to find actual model filename instead of guessing

Add fallback mechanism to manually download and load FastAI model if from_pretrained_fastai fails

Add toml dependency required for FastAI model loading

Fix cache directory permissions and OMP_NUM_THREADS warnings - Set HF cache env vars before imports - Set MPLCONFIGDIR for matplotlib - Fix OMP_NUM_THREADS in Dockerfile

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

Restore local ControlNet colorization pipeline

Point inference requests to new HF router endpoint

Update cache paths to use /tmp

Delete colorize-662df-firebase-adminsdk-fbsvc-bfd21c77c6.json

Switch colorization to HF Inference API

Improve SDXL auth error logging

Align pipeline with text-guided colorization Space

Increase img2img strength to improve colorization

Fix colorize pipeline call and fallback storage directories

Improve HF cache directory fallback to use /tmp when /data not writable

Make Firebase credentials writing non-fatal in entrypoint

Remove hf_cache creation from entrypoint - let Python handle it

Remove chmod commands - /data is already writable in HF Spaces

Fix model loading: use /data for HF cache directory instead of /app/data

fix(runtime): ensure /data is writable for non-root (chmod -R 777 /data)

fix(runtime): chown /data to uid 1000 and write firebase creds safely; ensure /data dirs

fix(runtime): use /data for uploads/results and write Firebase creds to /data; set DATA_DIR and OMP_NUM_THREADS

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

update Postman collection

Deploy: HF cache dir, img2img fallback, auth bypass, root route

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

Optimize CPU performance: reduce inference steps and guidance scale for faster processing

Remove unused cv2 import and pin numpy version for compatibility

Update .dockerignore to exclude unnecessary files

Improve entrypoint script creation in Dockerfile

Fix Dockerfile: Replace libgl1-mesa-glx with libgl1 for newer Debian

Initial commit: Colorize API with Firebase App Check integration