Spaces:

Anish530
/

Spotix-API

Sleeping

App Files Files Community

Spotix-API / backend

Commit History

May 13

15:23
Fixed the geometry perspective to follow the article from Farid.

Anish-530

c475a73
15:03
Fixed visual problem of the vanishing heatmap. Also fixed redundant logs

Anish-530

09cc5a2
14:29
Fixed Mobile support. Added a new AI media detection mechanism by Farid, that creates geometric lines. Fixed logs

Anish-530

817ad83

May 3

14:43
Fix: delete file FK violation (delete feedback first), fix sound autoplay policy

Anish-530

2b7c3ce
14:21
Fix: switch email to Brevo HTTP API (bypasses HF SMTP port blocking)

Anish-530

92695a4
12:45
Switch email to Brevo, fix SMTP config

Anish-530

519ff5c
12:21
Fix: 404 page loader stuck, navbar loading spinners, bulletproof NR import

Anish-530

942a467
10:51
Added email code verif

Anish-530

c041d0d

Apr 30

19:15
Fix login (audit_logs table + fault-tolerant audit), feedback graceful errors, remove raw AI explanation fallback, localStorage feedback persistence, Betterstack cloud logging

Anish-530

fe56754
18:14
Fixed loader stuck, Added a new feedback mechanism, and fixed sound upon analysis

Anish-530

ee2facf
15:49
Fix model auto-generation, sync cinematic loaders, update guest CTA

Anish-530

60d0281
08:46
Fix Google OAuth hardcoded localhost redirect

Anish-530

22023e0

Apr 29

15:10
Fix Celery Upstash Redis SSL compatibility

Anish-530

26793ce
14:43
Fix database URL driver normalization for psycopg2

Anish-530

96c41f2
09:44
Fix Windows-specific dependencies for Linux Docker build

Anish-530

ca21c7f
08:53
Switch to Hugging Face Spaces Docker deployment

Anish-530

b61bb63
08:44
Fix Render pricing: Combine web and worker into single free instance

Anish-530

ef1f114
07:19
[Vercel Deployment]

Anish-530

8a0d65c
06:55
[Deployment Phase 1 & 2] - Neon DB and R2 with working turnstile in login page implemented

Anish-530

0edd56d

Apr 27

18:30
[UI/UX] Final touches before deployment.

Anish

5603f49
17:30
[UI/UX] Added Account deletion, with some new features too.

Anish

a16341c

Apr 26

19:31
[UI/UX] More changes to the Frontend

Anish

ee7c0fb
18:12
[Minor changes to Frontend]

Anish

825fa02
08:46
[UI/UX] Features and good animations added

Anish

67264dd

Apr 21

06:59
[Frontend] - Initial Push

Anish

3bf6386

Mar 19

18:20
Minor changes to message of file_routes, to be more informative.

Anish

25bbf6f

Mar 14

19:07
[Updated Feature] > Updated every file_route, user_route, so that guest users can login and only upload 5 videos, 1 image per IP

Anish

e000e33
06:02
[Feature Updated] > Updated anomaly_gif_maker a lot, to be able to precisely extract frames from the video, where the model and pipeline think that part is AI.

Anish

8bdb51c

Mar 12

17:32
[Feature Added] > anomaly_gif_maker. This feature detects the frame where the pipeline thinks it is AI, converts it to gif and shows a side by side comparision to the Original Video, while also annotating the 'Peak Glitch' on the AI RADIANCE MAP gif

Anish

edd550f

Mar 11

19:08
[Feature Added] > Added gif maker for video anomaly detector, where the AI detects where the anomaly is and generates a small gif with comparision to Original and AI Radiance Map.

Anish

ee84eed

Mar 10

18:04
[Feature Added + Updated] > Addediffusion spectrum analyzer which analyzes the video in a more mathematical manner and detects if it's AI or not. Also updated some files to support diffusion spectrum analyzer

Anish

2add1f3

Mar 9

18:00
[Feature Added] > Model Drift Detection mechanism. This feature checks, if the model is confident in predicting the new uploaded images/videos as AI or not, if not then we need to retrain the model.

Anish

cc16b3b
15:30
[Feature Added] > Added Cloudflare Turnstile captcha for better security and bot disengagement. Also updated features, like file_routes, auth_routes to support Turnstile.

Anish

86c1923

Mar 8

18:13
[Feature Updated] > Tweaked aggregator for video processing a bit to identify videos more effectively

Anish

bf557e8
17:42
[Feature Updated] > Updated response for files such that, the video files only get the confidence and ai_explanation added, while image files do not.

Anish

9b8dcc7

Mar 7

20:05
[Feature Added] > Video Pipeline. Have to update the confidence and ai_analysis param for images, where they won't appear.

Anish

0dab55c
18:27
[Feature Added] > Added the Ensemble Aggregator which acts as the Supreme Court of the Pipeline. Listens to all the four distinct detectors and weighs evidence to a final verdict.

Anish

13b0169
18:06
[Feature Added] > Video metadata analyzer. This extracts the metadata from any video and judges it on those information scrapped.

Anish

88aa48f
15:53
[Updated Features] > Updated explainer and attribution with a new model, and support for better heatmap.

Anish

cd801e4

Mar 4

13:29
[Feature Added] > motion detector. This detects motion using Farneback Flow, which tracks motion using mathematical equations. If motion is violent and closer to 1.0 - It is AI, If motion is smooth and lower - it is Natural.

Anish

f49287c
12:17
[Feature Added] > frame_detector. This detects frames and spits out AI or REAL, based on the provided Video. Tested completely, with EDGE CASES.

Anish

739e45e
11:35
Feature Added -> frame_extractor (Extracts Frames safely. Tested with EDGE Cases too, where graceful termination is a must.)

Anish

95858c6

Mar 3

19:34
Added Secure Video Upload Validation

Anish530

96d596c
15:51
Added alembic for graceful migration of database, without creating new columns/altering columns physically. Alembic does it now.

Anish530

47f3442

Mar 2

17:33
Added separate storage and fixed worker, tasks, which previously got stuck on PROCESSING (NULL PROCESSOR)

Anish530

0196ddb

Mar 1

18:55
Added HTTP Security Headers, for more security

Anish530

de35def
18:06
Added exception handler for global exceptions

Anish530

8413ad5

Feb 28

19:53
Added audit logs to be logged into database for staff ease

Anish530

15785f4
18:56
Initial commit of full project [remaining backend some parts and frontend to be done yet]

Anish530

aa27d2d

Commit History

May 13

Fixed the geometry perspective to follow the article from Farid.

Fixed visual problem of the vanishing heatmap. Also fixed redundant logs

Fixed Mobile support. Added a new AI media detection mechanism by Farid, that creates geometric lines. Fixed logs

May 3

Fix: delete file FK violation (delete feedback first), fix sound autoplay policy

Fix: switch email to Brevo HTTP API (bypasses HF SMTP port blocking)

Switch email to Brevo, fix SMTP config

Fix: 404 page loader stuck, navbar loading spinners, bulletproof NR import

Added email code verif

Apr 30

Fix login (audit_logs table + fault-tolerant audit), feedback graceful errors, remove raw AI explanation fallback, localStorage feedback persistence, Betterstack cloud logging

Fixed loader stuck, Added a new feedback mechanism, and fixed sound upon analysis

Fix model auto-generation, sync cinematic loaders, update guest CTA

Fix Google OAuth hardcoded localhost redirect

Apr 29

Fix Celery Upstash Redis SSL compatibility

Fix database URL driver normalization for psycopg2

Fix Windows-specific dependencies for Linux Docker build

Switch to Hugging Face Spaces Docker deployment

Fix Render pricing: Combine web and worker into single free instance

[Vercel Deployment]

[Deployment Phase 1 & 2] - Neon DB and R2 with working turnstile in login page implemented

Apr 27

[UI/UX] Final touches before deployment.

[UI/UX] Added Account deletion, with some new features too.

Apr 26

[UI/UX] More changes to the Frontend

[Minor changes to Frontend]

[UI/UX] Features and good animations added

Apr 21

[Frontend] - Initial Push

Mar 19

Minor changes to message of file_routes, to be more informative.

Mar 14

[Updated Feature] > Updated every file_route, user_route, so that guest users can login and only upload 5 videos, 1 image per IP

[Feature Updated] > Updated anomaly_gif_maker a lot, to be able to precisely extract frames from the video, where the model and pipeline think that part is AI.

Mar 12

[Feature Added] > anomaly_gif_maker. This feature detects the frame where the pipeline thinks it is AI, converts it to gif and shows a side by side comparision to the Original Video, while also annotating the 'Peak Glitch' on the AI RADIANCE MAP gif

Mar 11

[Feature Added] > Added gif maker for video anomaly detector, where the AI detects where the anomaly is and generates a small gif with comparision to Original and AI Radiance Map.

Mar 10

[Feature Added + Updated] > Addediffusion spectrum analyzer which analyzes the video in a more mathematical manner and detects if it's AI or not. Also updated some files to support diffusion spectrum analyzer

Mar 9

[Feature Added] > Model Drift Detection mechanism. This feature checks, if the model is confident in predicting the new uploaded images/videos as AI or not, if not then we need to retrain the model.

[Feature Added] > Added Cloudflare Turnstile captcha for better security and bot disengagement. Also updated features, like file_routes, auth_routes to support Turnstile.

Mar 8

[Feature Updated] > Tweaked aggregator for video processing a bit to identify videos more effectively

[Feature Updated] > Updated response for files such that, the video files only get the confidence and ai_explanation added, while image files do not.

Mar 7

[Feature Added] > Video Pipeline. Have to update the confidence and ai_analysis param for images, where they won't appear.

[Feature Added] > Added the Ensemble Aggregator which acts as the Supreme Court of the Pipeline. Listens to all the four distinct detectors and weighs evidence to a final verdict.

[Feature Added] > Video metadata analyzer. This extracts the metadata from any video and judges it on those information scrapped.

[Updated Features] > Updated explainer and attribution with a new model, and support for better heatmap.

Mar 4

[Feature Added] > motion detector. This detects motion using Farneback Flow, which tracks motion using mathematical equations. If motion is violent and closer to 1.0 - It is AI, If motion is smooth and lower - it is Natural.

[Feature Added] > frame_detector. This detects frames and spits out AI or REAL, based on the provided Video. Tested completely, with EDGE CASES.

Feature Added -> frame_extractor (Extracts Frames safely. Tested with EDGE Cases too, where graceful termination is a must.)

Mar 3

Added Secure Video Upload Validation

Added alembic for graceful migration of database, without creating new columns/altering columns physically. Alembic does it now.

Mar 2

Added separate storage and fixed worker, tasks, which previously got stuck on PROCESSING (NULL PROCESSOR)

Mar 1

Added HTTP Security Headers, for more security

Added exception handler for global exceptions

Feb 28

Added audit logs to be logged into database for staff ease

Initial commit of full project [remaining backend some parts and frontend to be done yet]