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 79 stars 14 forks Updated 3 days ago MIT

Install

View on GitHub

Quality Score: 91/100

Stars 20%
63
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
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。��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/...

Details

Author
KerberosClaw
Repository
KerberosClaw/kc_ai_skills
Created
6 months ago
Last Updated
3 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 OR edit an image via GPT/Codex (e.g. 「叫 gpt 生圖」「幫我用 gpt 生圖」「gpt 畫一個 X」「幫我去背」「把這張圖的背景去掉」). The skill drafts a Chinese + English prompt pair and waits for explicit approval. After approval it uses the host-native executor: Codex calls its built-in image_gen tool directly, while Claude Code keeps the Codex CLI background workflow. Supports text-to-image, img2img, and precise EDIT mode with preservation constraints and verification where local artifacts are available.

79 Updated 3 days ago
KerberosClaw
AI & Automation Listed

manga-stage-2-panels

AI 漫剧 Stage 2 — 分镜面板自动生成。锁定 AnimaStandardV7 工作流,仅修改 prompt + LoRA 配置,自动生成 PNG 面板。可选 IP-Adapter / ControlNet 增强(v2.0)。Also load chenxin-core first for VRAM/recipe context.

0 Updated 1 months ago
cxin21
AI & Automation Featured

imagegen

生成网站与内容所需的一切视觉素材——用户说 生成图片、配图、插图、画一张、出一套图、logo、吉祥物、封面、海报、og 图、分享图、favicon 源图、用户场景图、真人图("一个人坐在电脑前")、手绘/蜡笔/水彩风插画、产品宣传图、电影感画面、"网站需要配图"、image gen、imagegen 时必用。也覆盖 rankup 建站流程里的"页面缺图、还是占位图、og:image 没图、每页要独立分享图、favicon 还没做"——这些场景不许用占位图,必须真实生成,一律加载本 Skill。底层走 Codex 内置的 OpenAI 图像生成工具;本 Skill 负责把需求翻成好提示词、跑通、验收、压缩、落盘。

203 Updated today
yan-labs