Skip to content

Training diffusion models

Python · active 2025-03-302026-06-11 (UTC)

Partial coverage11,254 / 11,982 hourly files (94%) · 2 absent upstream · 726 failed, retryable2025-03-292026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
395
Pushes
0
Pull requests
0
Issues
3
Stars
347
Forks
32

Activity over time

Daily event counts in the loaded window

Line chart, 439 days from 2025-03-30 to 2026-06-11. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 3 total, peak 1 in a day. Comments: 13 total, peak 9 in a day. Stars: 347 total, peak 5 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

ContributorContributionsPushesPRsComments
sunset-clouds7006
lavinal7124004
almutwakel1000
CoinCheung1000
forever2081001
1915780101001
Muhammadjunaidmalik11001

Recent activity

Latest issues, pull requests and releases

  • Issue#167almutwakel2025-12-03 00:11
    Gradient checkpointing + dropout causes loss divergence
  • Issue comment#1021915780102025-08-28 08:30
    有人能你告诉我怎么运行嘛
  • Issue comment#72Muhammadjunaidmalik12025-06-23 05:49
    multi-GPU training issues
  • Issue#162CoinCheung2025-05-17 06:34
    Has any train this model on larger datasets?
  • Issue comment#159lavinal7122025-05-09 05:50
    evaluator.py (any pytorch version?)
  • Issue comment#159lavinal7122025-05-03 10:26
    evaluator.py (any pytorch version?)
  • Issue comment#159forever2082025-05-03 10:04
    evaluator.py (any pytorch version?)
  • Issue comment#159lavinal7122025-05-03 09:55
    evaluator.py (any pytorch version?)
  • Issue comment#14sunset-clouds2025-05-03 06:10
    FID score on Imagenet-256 dataset
  • Issue comment#56sunset-clouds2025-05-03 06:08
    Sampling details for FID evaluation
  • Issue comment#75sunset-clouds2025-05-03 06:07
    Details for training and sampling for FID calculation ...
  • Issue comment#77sunset-clouds2025-05-03 06:06
    Question about FID
  • Issue comment#142sunset-clouds2025-05-03 06:02
    IS more than 300
  • Issue comment#159sunset-clouds2025-05-03 05:59
    evaluator.py (any pytorch version?)
  • Issue#161sunset-clouds2025-05-03 05:56
    rFID of VAR is very large
  • Issue comment#159lavinal7122025-04-12 14:36
    evaluator.py (any pytorch version?)

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 347 stars here means stars gained during the window, not the repo's star count.