text-guided-image-colorization

Running

App Files Files Community

text-guided-image-colorization / app /colorize_model.py

Commit History

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

0454a91

LogicGoInfotechSpaces commited on Nov 13

List repository files to find actual model filename instead of guessing

a2d6cd7

LogicGoInfotechSpaces commited on Nov 13

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

80080e1

LogicGoInfotechSpaces commited on Nov 13

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

6108abf

LogicGoInfotechSpaces commited on Nov 13

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

5e6062c

LogicGoInfotechSpaces commited on Nov 13

Restore local ControlNet colorization pipeline

8d0a1ae

LogicGoInfotechSpaces commited on Nov 13

Point inference requests to new HF router endpoint

d58eb50

LogicGoInfotechSpaces commited on Nov 13

Update cache paths to use /tmp

bdef219

LogicGoInfotechSpaces commited on Nov 13

Switch colorization to HF Inference API

f79a7fe

LogicGoInfotechSpaces commited on Nov 13

Improve SDXL auth error logging

dfc30a3

LogicGoInfotechSpaces commited on Nov 13

Align pipeline with text-guided colorization Space

8f6f449

LogicGoInfotechSpaces commited on Nov 13

Increase img2img strength to improve colorization

eb42092

LogicGoInfotechSpaces commited on Nov 13

Fix colorize pipeline call and fallback storage directories

bfba916

LogicGoInfotechSpaces commited on Nov 13

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

67d9b2f

LogicGoInfotechSpaces commited on Nov 13

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

2f136a8

LogicGoInfotechSpaces commited on Nov 13

update Postman collection

f1c1f42

LogicGoInfotechSpaces commited on Nov 11

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

7471c96

LogicGoInfotechSpaces commited on Nov 11

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

2ae242d

LogicGoInfotechSpaces commited on Nov 11

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

62db9e6

LogicGoInfotechSpaces commited on Nov 11

Initial commit: Colorize API with Firebase App Check integration

60c56d7

LogicGoInfotechSpaces commited on Nov 11

Commit History

Detect PyTorch models and provide clear error message - Repository contains generator.pt (PyTorch) not FastAI model 0454a91

List repository files to find actual model filename instead of guessing a2d6cd7

Add fallback mechanism to manually download and load FastAI model if from_pretrained_fastai fails 80080e1

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 6108abf

Switch to FastAI GAN colorization model (Hammad712/GAN-Colorization-Model) 5e6062c

Restore local ControlNet colorization pipeline 8d0a1ae

Point inference requests to new HF router endpoint d58eb50

Update cache paths to use /tmp bdef219

Switch colorization to HF Inference API f79a7fe

Improve SDXL auth error logging dfc30a3

Align pipeline with text-guided colorization Space 8f6f449

Increase img2img strength to improve colorization eb42092

Fix colorize pipeline call and fallback storage directories bfba916

Improve HF cache directory fallback to use /tmp when /data not writable 67d9b2f

Fix model loading: use /data for HF cache directory instead of /app/data 2f136a8

update Postman collection f1c1f42

Deploy: HF cache dir, img2img fallback, auth bypass, root route 7471c96

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 2ae242d

Optimize CPU performance: reduce inference steps and guidance scale for faster processing 62db9e6

Initial commit: Colorize API with Firebase App Check integration 60c56d7

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

0454a91

List repository files to find actual model filename instead of guessing

a2d6cd7

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

80080e1

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

6108abf

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

5e6062c

Restore local ControlNet colorization pipeline

8d0a1ae

Point inference requests to new HF router endpoint

d58eb50

Update cache paths to use /tmp

bdef219

Switch colorization to HF Inference API

f79a7fe

Improve SDXL auth error logging

dfc30a3

Align pipeline with text-guided colorization Space

8f6f449

Increase img2img strength to improve colorization

eb42092

Fix colorize pipeline call and fallback storage directories

bfba916

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

67d9b2f

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

2f136a8

update Postman collection

f1c1f42

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

7471c96

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

2ae242d

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

62db9e6

Initial commit: Colorize API with Firebase App Check integration

60c56d7