Individual skill
lora-trainer
Prepare and launch LoRA, LoKr, or T-LoRA training through lora-scripts-next (SD-Trainer), Anima-first. Use when the user asks to train a character, style, or concept LoRA, choose parameters or repeats and epochs, start a run, or monitor training on Anima, SD1.5, SDXL, or Flux. Organize and caption the dataset, run dataset-doctor, choose a documented starting preset from image count and VRAM, show one confirmation card, then call the mikazuki API and monitor its log.
lora-trainer/SKILL.md
Source commit c2dbaa0bf8ae4f19aaa3f9d56714ce450793c63c
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- Yes
- Skill scan complete
- Yes
- Observed behavior
- Not checked yet
- Last checked
- Nov 4, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 13
- Repository last updated
- Oct 26, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- anima Repository topic
- civitai Repository topic
- claude-code Repository topic
- comfyui Repository topic
- dataset-tools Repository topic
- kohya Repository topic
- lora Repository topic
- lora-training Repository topic
- skill-md Repository topic
- productivity Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 21,556 bytesagents/openai.yamlasset · 215 bytesscripts/failure_catalogue.pyruns · 22,230 bytesscripts/lora_base_info.pyruns · 9,947 bytesscripts/task_insights.pyruns · 13,970 bytesscripts/trainer_state.pyruns · 15,458 bytesscripts/wddm_sysmem.pyruns · 15,480 bytestests/test_failure_catalogue.pyruns · 18,033 bytestests/test_lora_base_info.pyruns · 7,132 bytestests/test_task_insights.pyruns · 8,731 bytestests/test_trainer_state.pyruns · 15,940 bytestests/test_wddm_sysmem.pyruns · 10,640 bytes
Read excerpt
# lora-trainer — LoRA 训练编排入口
把「训练一个 LoRA」的意图，变成一次受控的训练：准备数据 → 体检 → 组装配置 → **用户确认** → 通过 trainer API 开训 → 监看 log。本 skill 默认 **Anima 优先**，也支持 SD1.5 / SDXL / Flux。
> 训练耗时、占显存、难回退。**在 `POST /api/run` 之前必须把组装好的配置摊给用户、明确确认**；未确认不开训。
底层 = `lora-scripts-next`（SD-Trainer）的 `mikazuki` FastAPI（`http://127.0.0.1:28000`，路由前缀 `/api`）。完整契约见 `../references/trainer-api.md`。
## 适用范围（用户用的不是 SD-Trainer 时怎么办）
本 skill 的**开训与打标只针对 SD-Trainer** 的 mikazuki API——`trainer-api.md` 的契约只对它成立。**绝不要**把这套 `/api/run` body 发给别的训练器（kohya_ss GUI、OneTrainer、ai-toolkit…），它们的 API 完全不同。用户在用别的训练器时，按可移植性分层处理：
1. **体检照做**：`dataset-doctor` 与 `fix_dataset.py` 是训练器无关的（标准 kohya `<repeats>_<concept>` + sidecar caption 约定），完整可用，全程离线。
2. **参数知识可借用**：`anima-params.md` / `presets.md` 的键就是 kohya sd-scripts 词汇（`network_dim`、`unet_lr`、repeats/epochs 步数预算）。可以据此给参数建议，或替用户生成一份 kohya 风格 TOML / 命令行，让他们在自己的训练器里手动跑。