메뉴
使用 Kapibala 的 OpenAI 兼容图片接口生成/编辑位图图片，默认模型 gpt-image-2。当需要生成图片、编辑已有图片、或批量生成候选图供挑选时触发。触发词："生成图片""画一张""image generation""edit this image""gpt-image-2""批量出图"。
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/justcyl/my-skills --skill image-gen-kapibala명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
Add, collect, design, audit, and integrate SVG elements into editable diagrams.net/draw.io scientific figures. Use when the user asks to supplement a draw.io diagram with SVG icons, mechanisms, biological objects, model components, pathway symbols, instruments, graphical abstract elements, or publication-style vector assets. Every execution must first ask the user to choose the SVG source mode: network search or self-designed SVG. For network mode, search for multiple relevant SVG candidates for later user selection, record sources and license notes, and fall back to self-designed SVG for concepts with no suitable result. For self-design mode, create restrained, editable, Nature-style SVGs from simple vector primitives. Use with .drawio, SVG, diagrams.net, 科研流程图, 论文示意图, SVG补图, 图标补充, and draw.io配图.
Two-stage workflow for publication-style scientific schematics: generate or use a raster reference with imagegen/PNG/JPG/WebP, then trace it into an editable diagrams.net/draw.io file using research-drawio-skill. Use for Nature-style scientific illustrations, graphical abstracts, model or mechanism schematics, biomedical workflows, AI architecture figures, and paper-style visual drafts that should become editable .drawio source. For complex recognizable elements, author or select dedicated SVG glyphs and compare rendered SVGs against reference crops before inserting them, instead of assembling those elements from draw.io primitives. Enforces a minimum three-round strict pixel-level export/compare/fix loop for close raster-to-draw.io tracing tasks. Use with imagegen, draw.io, diagrams.net, scientific illustration, graphical abstract, paper schematic, figure tracing, SVG glyph tracing, and drawio redraw requests.
Add, collect, design, audit, and integrate SVG elements into editable diagrams.net/draw.io scientific figures. Use when the user asks to supplement a draw.io diagram with SVG icons, mechanisms, biological objects, model components, pathway symbols, instruments, graphical abstract elements, or publication-style vector assets. Every execution must first ask the user to choose the SVG source mode: network search or self-designed SVG. For network mode, search for multiple relevant SVG candidates for later user selection, record sources and license notes, and fall back to self-designed SVG for concepts with no suitable result. For self-design mode, create restrained, editable, Nature-style SVGs from simple vector primitives. Use with .drawio, SVG, diagrams.net, 科研流程图, 论文示意图, SVG补图, 图标补充, and draw.io配图.
SKILL.md 표시 중
| name | image-gen-kapibala |
| description | 使用 Kapibala 的 OpenAI 兼容图片接口生成/编辑位图图片，默认模型 gpt-image-2。当需要生成图片、编辑已有图片、或批量生成候选图供挑选时触发。触发词："生成图片""画一张""image generation""edit this image""gpt-image-2""批量出图"。 |
通过 Kapibala 提供的 OpenAI 兼容 Images API 生成/编辑位图图片。本 skill 只有 CLI 一条路径（没有内置图片生成工具可用），默认模型 gpt-image-2。
~/.zshrc.local 中需要：
export KAPIBALA_API_KEY="..."
export KAPIBALA_BASE_URL="https://kapibala.asia/v1" # 可省略，脚本内置此默认值
Preflight 检查：
[ -n "$KAPIBALA_API_KEY" ] && echo ok || echo "缺少 KAPIBALA_API_KEY，请检查 ~/.zshrc.local 是否已 source"
若缺失，提示用户在 ~/.zshrc.local 添加上面的 export 行并重开终端 / source ~/.zshrc.local，不要替用户猜测或编造 key。
脚本用 uv run 执行，依赖（openai、pillow）已在脚本头部的 # /// script 内联声明，无需提前安装。
先判断两件独立的事：
generateeditgenerategenerate 调用或 generate-batch 的多个 job，不要用 --n 代替——--n 只用于同一个 prompt 出多个变体生成：
uv run <skill-dir>/scripts/generate_image.py generate \
--prompt "a minimal hero image of a ceramic coffee mug, soft studio lighting" \
--out path/to/output.png \
[--model gpt-image-2] [--size 1536x1024] [--quality high] [--n 1]
编辑（--image 可重复传入多张）：
uv run <skill-dir>/scripts/generate_image.py edit \
--prompt "change only the background to a warm sunset gradient; keep the product unchanged" \
--image path/to/source.png \
--out path/to/edited.png
批量（JSONL，每行一个 job，字符串或 {"prompt": "...", "out": "...", ...} 对象均可）：
uv run <skill-dir>/scripts/generate_image.py generate-batch \
--input jobs.jsonl \
--out-dir output/imagegen/batch/
先用 --dry-run 预览最终请求体和输出路径，确认无误再正式执行。
--out 已存在文件默认不覆盖，需要覆盖用 --force；需要额外一份缩略图用 --downscale-max-dim <px>。
| 参数 | 说明 |
|---|---|
--model | 默认 gpt-image-2 |
--size | auto 或 WIDTHxHEIGHT；gpt-image-2 见下方尺寸规则 |
--quality | low/medium/high/auto；草稿用 low，终稿用 high/auto |
--background | transparent/opaque/auto；gpt-image-2 不支持 transparent |
--n | 同一 prompt 的变体数（1-10） |
--out / --out-dir | 单文件路径 / 批量输出目录 |
--input-fidelity | 仅 edit 支持，gpt-image-2 不支持此参数（固定高保真） |
size 为 auto 或满足以下全部约束的 WIDTHxHEIGHT：
<= 3840px16px 的倍数<= 3:1655,360 到 8,294,400 之间常用尺寸：1024x1024（方形快稿）、1536x1024/1024x1536（横/竖版）、2048x2048（2K 方形）、3840x2160/2160x3840（4K 横/竖）。
Use case: <场景，如 product-mockup / ui-mockup / illustration-story>
Primary request: <用户核心诉求>
Scene/background: <环境/背景>
Subject: <主体>
Style/medium: <照片/插画/3D 等>
Composition/framing: <构图>
Lighting/mood: <光线与氛围>
Color palette: <配色>
Materials/textures: <材质>
Text (verbatim): "<需要出现的精确文字>"
Constraints: <必须保留的内容>
Avoid: <禁止出现的内容>
只保留有帮助的字段，不要为了凑格式硬填。脚本内置 --use-case/--scene/--subject/... 等参数会自动拼成上述结构（默认开启，--no-augment 关闭）。
编辑任务务必显式列出不变量，例如 "change only the background; keep the product and its edges unchanged"，每轮迭代都重复一遍以减少漂移。
KAPIBALA_API_KEY：检查 ~/.zshrc.local 是否配置并已 source，不要代替用户猜测 keygenerate-batch 内置指数退避重试（--max-attempts，默认 3 次）；单张 generate/edit 失败需手动重试--force 覆盖，或换路径