Skip to content

SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.

active 2025-03-072026-06-06 (UTC)

Partial coverage11,520 / 12,566 hourly files (92%) · 2 absent upstream · 1,042 failed, retryable2025-03-052026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
707
Pushes
6
Pull requests
7
Issues
66
Stars
512
Forks
53

Activity over time

Daily event counts in the loaded window

Line chart, 457 days from 2025-03-07 to 2026-06-06. Pushes: 6 total, peak 1 in a day. Pull requests: 7 total, peak 3 in a day. Issues: 66 total, peak 3 in a day. Comments: 63 total, peak 5 in a day. Stars: 512 total, peak 9 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
Akegarasu14603
ZitengXue6005
1879qwer5003
Tasvthe5002
minecraftHCX4002
alex94414003
Rnglg23021
Omg-ciTy3002
baicai993030
a4425090972001
MagicShiba2002
HuanLinOTO2002
ershi11212001
Jacky-MYQ2001
ColorfulGhost2001
AdamShuo2002
IAMJOYBO2000
imp-oh2002
HmmPFF2002
ZeeLyn2001

Recent activity

Latest issues, pull requests and releases

  • Issue#744Mayu1632026-01-26 11:20
    需要更新 - 目前的 Install 腳本所安裝的 PyTorch 與 RTX 50 系並不相容
  • Issue#742MooeMing2026-01-19 11:37
    [Bug Report] Critical Performance Bottleneck: max_data_loader_n_workers is Hardcoded to 0, Severely Limiting High-End Hardware
  • Issue comment#607dainamiter2026-01-11 08:28
    flux lora 训练报错NotImplementedError: Cannot copy out of meta tensor; no data! Please use torch.nn.Module.to_empty() instead of torch.nn.Module.to() when moving module from meta to a different device.
  • Issue#739dd1782026-01-10 12:04
    支持cl tagger模型
  • Issue comment#707lllznnn2025-12-29 08:06
    是否支持MASK的inpainting微调?
  • Issue comment#741NaughtDZ2025-12-22 14:58
    torch2.7.0+cu128这个组合已经不存在了?
  • Issue#740xihuanbodajingshen2025-12-06 00:16
    请教大家关于prodigy优化器显存占用高的问题
  • Issue#738TkskKurumi2025-12-03 03:47
    支持kohya-ss新项目musubi-tuner
  • Issue comment#734MagicShiba2025-11-23 18:16
    希望打标工具可以接入多模态模型
  • Issue comment#735ursb12025-11-02 14:59
    repeat参数是如何定义的?
  • Issue comment#731TryToYikes2025-10-29 01:40
    flux训练时,启用resume恢复中断的训练会发生报错
  • Issue#737nestflow2025-10-26 19:15
    Compatibility issue between PYTHONUTF8 = "1" and latest bitsandbytes.
  • Issue#724sndnnlfhvk2025-10-20 10:47
    希望WebUI加入控制台输出日志
  • Issue#735DiaQusNet2025-10-18 05:19
    repeat参数是如何定义的?
  • Issue comment#729MagicShiba2025-09-28 04:51
    改善标签编辑器使用体验
  • Issue comment#545CharlinChen2025-09-20 18:41
    执行打标签失败了,onnxruntime报错
  • Issue comment#723ZeeLyn2025-09-20 01:59
    Chroma-HD 训练预览图采样有问题
  • Issue#728joachim5082025-09-19 16:04
    Chroma 模式训练出的lora不起作用
  • Issue comment#715CheNing2332025-09-13 07:29
    继续训练失败,KeyError: 'step'
  • Issue comment#662HuanLinOTO2025-09-06 11:49
    V100显卡fp16下训练显卡占用低
  • Issue comment#716KNaiFen2025-09-04 05:39
    使用WD标签器的时候遇到error,谁能帮我看看怎么解决
  • Issue#722jack-uxc2025-09-04 03:05
    秋叶大佬,啥时候能支持qwen呢??期待!
  • Issue comment#720Rnglg22025-09-01 11:27
    添加v预测与zerosnr的参数支持
  • Pull request#720Rnglg22025-09-01 11:05
  • Issue#714Akegarasu2025-09-01 06:57
    配置LyCORIS 网络算法后报错

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 512 stars here means stars gained during the window, not the repo's star count.