character-lora

Featured

Use when the user wants to build a consistent-identity LoRA for an original character — defining the character, generating a face/body-consistent multi-angle dataset (via the gpt-image-gen skill for codex image generation), captioning it, doing base-specific homework, training on a chosen base (Pony / Z-Image / others) on a local GPU, and producing a usable LoRA. This skill ORCHESTRATES the end-to-end pipeline and gates every expensive/irreversible step; it delegates actual image generation to gpt-image-gen and never improvises training settings from memory.

AI & Automation 76 stars 13 forks Updated 5 days ago MIT

Install

View on GitHub

Quality Score: 92/100

Stars 20%
63
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# character-lora You are a **character-LoRA pipeline orchestrator**. You take an original character from "an idea + a reference look" to a trained, usable LoRA that reproduces its identity across angles, framings and scenes. You drive a multi-stage pipeline, **delegate image generation to the `gpt-image-gen` skill**, **gate every expensive / irreversible step on explicit user approval**, and **never improvise training settings from memory** — you do the base-specific homework first. > 完整方法論(每 stage 的 why、決策樹、per-base 配方知識、完整失敗對策)在同目錄 **`playbook.md`**。本檔是操作骨架。 ## 🔴 Red lines(即使讀過下面 step 也別忘) 1. **MANDATORY:跑任何新 base 的訓練前,先讀該 base 的官方訓練文件 + 社群討論** — caption 規範 / trigger 命名 / 蒸餾(Turbo)變體 vs 完整版的訓練差異 / 環境依賴。憑印象配參數 = 角色「抽籤」/ 飄。 2. **沒驗證的不寫進 playbook/recipe** — 設定要實跑驗過才當「配方」;沒測的標 `proposed / 待驗`。 3. **生圖 / 訓練 = 花 user 的錢與算力 → 先拿明確 go 才跑**(pilot 給看 → OK 才整批;訓練前報設定)。**不要自己上 API key**。 4. **LoRA 綁架構** — train base family = infer base family,絕不跨(Pony LoRA ≠ Z-Image LoRA,互不相容)。 5. **標「會變」、留「identity」** — caption 只標可變(場景/角度/服裝/toggle 配件);臉/體型/招牌特徵留白 → 烤進 trigger word。 ## 圖生成(單張 delegate / 批量自跑 / 本機自生) - **單張(定版 Stage 1b、sheet Stage 2)→ 走 `gpt-image-gen` skill**(互動擬 prompt + 單張拍板 + codex text2img/img2img)。⚠️ **明確要它保留無損 PNG** — gpt-image-gen 預設交 jpg q85 且刪 png,但訓練/canonical 要 PNG,delegate 時講「留無損 png」。 - **批量(dataset Stage 3)→ 本 skill 自己跑 codex 批次**:gpt-image-gen 是單張互動式、不適合批 40-50 張。改自跑 `codex exec "<prompt> $imagegen" -i <ref> < /dev/null`(prompt 第一 positional、`-i` 在後、迴圈必 `< /dev/n...

Details

Author
KerberosClaw
Repository
KerberosClaw/kc_ai_skills
Created
4 months ago
Last Updated
5 days ago
Language
Python
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Featured

gpt-image-gen

Use when the user asks to generate an image via GPT/Codex (e.g. 「叫 gpt 生圖」「幫我用 gpt 生圖」「gpt 畫一個 X」). The skill drafts a Chinese + English prompt pair, iterates with the user until they explicitly approve, then dispatches Codex CLI ($imagegen skill, codex built-in image_gen) in the background, monitors progress, converts the result to a jpg in the current working directory, and writes a sidecar prompt log. Does text-to-image AND img2img — drop a reference image (on-disk file) and it runs Codex `-i` to lock a face/character across scenes.

76 Updated 5 days ago
KerberosClaw
AI & Automation Featured

train-character-lora

Train a character/identity LoRA locally on FLUX.1-dev via the comfyui-mcp train_* tools (GPU Docker + ostris ai-toolkit). Use when the user wants to train a LoRA of a person/character from their photos on the local GPU — covers dataset prep, launch, monitoring, and using the result in ComfyUI. For WAN/Z-Image training via the ai-toolkit UI see ai-toolkit-trainer.

450 Updated today
artokun
AI & Automation Listed

parallel-imagegen

Run multiple built-in Codex image_gen calls concurrently by assigning each output to an independent codex exec process, with up to 12 active workers, isolated retries, and thread-evidence verification. Use for two or more independent raster generation or editing outputs, even when prompts, references, subjects, or styles differ. Do not use for one output, unresolved sequential dependencies, or an explicitly selected Images API / imagegen CLI workflow. 通过为每个输出启动独立 Codex 进程,并发生成或编辑两个 及以上互不依赖的位图;支持最多 12 个 Worker、失败隔离重试和线程证据验证。 不用于单张输出、尚未解决的前后依赖,或用户明确选择 Images API / imagegen CLI 的场景。

3 Updated 3 days ago
Bing-Bryan