Skip to content

Official implementation of "Unseen Visual Anomaly Generation" (CVPR 2025)

active 2025-05-222026-03-02 (UTC)

Partial coverage11,290 / 12,068 hourly files (94%) · 2 absent upstream · 775 failed, retryable2025-03-252026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
208
Pushes
6
Pull requests
0
Issues
27
Stars
123
Forks
12

Activity over time

Daily event counts in the loaded window

Line chart, 285 days from 2025-05-22 to 2026-03-02. Pushes: 6 total, peak 2 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 27 total, peak 3 in a day. Comments: 40 total, peak 5 in a day. Stars: 123 total, peak 10 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

Recent activity

Latest issues, pull requests and releases

  • Issue comment#327544677372026-02-26 00:41
    关于生成质量评估的疑问
  • Issue comment#32lulukie2026-02-26 00:34
    关于生成质量评估的疑问
  • Issue comment#267544677372026-02-08 14:14
    Detailed Anomaly Descriptions
  • Issue#30hansunhayden2026-01-18 08:12
    Can you also supply the evaluation code for anomaly detection?
  • Issue#29lulukie2025-12-08 01:16
    1-shot experiments code open PLZ
  • Issue comment#15easyhappy6662025-10-23 07:26
    When running this code on a single 3090, an OOM (out of memory) error occurs. My computer has two 3090 GPUs. How should I modify the code to run it using both GPUs?
  • Issue comment#28easyhappy6662025-10-18 08:01
    multi-GPU inference
  • Issue#28christosgd2025-10-16 12:25
    multi-GPU inference
  • Issue#27y-inoue-tdse2025-09-25 02:05
    License clarification for AnomalyAny repository
  • Issue#25LonglongaaaGo2025-09-12 02:32
    How to generate heat map
  • Issue comment#24hansunhayden2025-09-01 05:31
    Does it generate not every 200 diffusion steps?
  • Issue#18hansunhayden2025-08-29 05:58
    Unable to generate image by using CPU
  • Issue#21hansunhayden2025-08-29 05:57
    Output error
  • Issue#23hansunhayden2025-08-29 05:56
    I set NUM_DIFFUSION_STEPS = 200, but it stops at 30%.
  • Issue comment#15johnluban2025-08-23 07:22
    When running this code on a single 3090, an OOM (out of memory) error occurs. My computer has two 3090 GPUs. How should I modify the code to run it using both GPUs?
  • Issue comment#21linkenfaqiu2025-08-08 08:58
    Output error
  • Issue comment#21hansunhayden2025-08-08 06:39
    Output error
  • Issue comment#21linkenfaqiu2025-08-07 11:22
    Output error
  • Issue#8hansunhayden2025-08-07 07:10
    Is it possible to implement custom generation using defects of specific image types as defect types? For example, can we input images of types like cracks, bends, scratches, etc.? What changes need to be made? I would like to ask for your advice
  • Issue comment#18hansunhayden2025-08-07 07:09
    Unable to generate image by using CPU
  • Issue#22hansunhayden2025-08-07 07:04
    Any explain about eval code?
  • Issue comment#22hansunhayden2025-08-07 07:04
    Any explain about eval code?
  • Issue comment#21linkenfaqiu2025-07-26 14:09
    Output error
  • Issue comment#15linkenfaqiu2025-07-26 13:47
    When running this code on a single 3090, an OOM (out of memory) error occurs. My computer has two 3090 GPUs. How should I modify the code to run it using both GPUs?
  • Issue comment#15skydadada2025-07-22 08:34
    When running this code on a single 3090, an OOM (out of memory) error occurs. My computer has two 3090 GPUs. How should I modify the code to run it using both GPUs?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 123 stars here means stars gained during the window, not the repo's star count.