Code repository for the paper: Diffusion Noise Feature: Accurate and Fast Generated Image Detection.
active 2024-11-11 → 2026-01-28 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 444 days from 2024-11-11 to 2026-01-28. Pushes: 2 total, peak 1 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 4 total, peak 2 in a day. Comments: 1 total, peak 1 in a day. Stars: 8 total, peak 1 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| YichiCS | 2 | 2 | 0 | 0 |
| prohommunel | 2 | 0 | 0 | 0 |
| ccandtt | 1 | 0 | 0 | 1 |
| haatohaaton | 1 | 0 | 0 | 0 |
| yinghuozijin | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#11ccandtt2025-05-05 14:48about test results
- Issue#14haatohaaton2025-05-05 14:12Applying This Method to Other Datasets
- Issue#13prohommunel2025-04-10 11:13为什么我训练的时候准确率很高，eval的时候很低？
- Issue#13prohommunel2025-04-10 10:42为什么我训练的时候准确率很高，eval的时候很低？
- Issue#12yinghuozijin2024-11-14 16:28The pretrained ckpt?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 8 stars here means stars gained during the window, not the repo's star count.