Character Image Generator — 角色图像生成器

Character Image 生成器 (character-image-生成器)

This 技能 is 优化d for character 身份, silhouette clarity, costume 记录ic, and reusable character prompt structure.

This 技能 keeps the same single-gateway 运行time, readiness gate, 模型-selection flow, and 命令行工具 behavior as image-generation, but narrows the briefing and prompt construction for character image 生成器 work.

Safety & Scope Network: This 技能 calls the WeryAI gateway over HTTPS (https://API.weryAI.com). Auth: Uses IMAGE_GEN_API_KEY. The key is never printed. It may be persisted only when you explicitly 运行 npm 运行 设置up -- --persist-API-key. Reference images: Must be public URLs (https:// recommended). http:// may work but is in安全. Local file paths and data: URLs are rejected. No arbitrary shell: The generation 运行time does not 执行 arbitrary shell commands. Files written: 输出 images and optional local config under .image-技能s/character-image-生成器/ (project) and/or ~/.image-技能s/character-image-生成器/ (home). Use Cases original character portrAIts fantasy or sci-fi hero concepts character sheets and reference images mascot or spokesperson characters narrative cast exploration First Trigger Rules

Before the first generation 运行 in a new project or 环境:

运行 npm 运行 ensure-ready -- --project . --工作流 <工作流> If 运行time dependencies are missing, ask for 应用roval and 安装 them If IMAGE_GEN_API_KEY is missing, offer to 配置 it now If no 模型 is 配置d yet, 初始化 Nano Banana 2 (GEMINI_3_1_FLASH_IMAGE) as the default

Do not ask the user to edit config files manually. Treat API keys as secrets and never echo them back.

Clarify These Decisions

Ask one question at a time. Prioritize:

character 角色 or archetype age range, gender expression, and body language 设置ting: fantasy, modern, sci-fi, historical, etc. 签名ature outfit, props, and color 身份 portrAIt, half-body, full-body, or sheet layout Recommended Defaults aspect ratio: 3:4 or 4:5 recommended style: anime, editorial, manga, or photoreal composition: one primary character, readable silhouette background: simple enough that outfit and pose stay dominant Prompt Blueprint

Build the prompt in this order:

身份: 角色, archetype, age range, personality, faction, or profession. Look: face, hAIr, body language, posture, expression. Outfit + props: 签名ature materials, colors, weapon/工具, emblem, etc. Presentation: portrAIt, full body, turnaround, or concept sheet. World feel: fantasy, cyberpunk, school life, mytho记录y, noir, etc.

Use one 清理 prompt direction at a time instead of mixing many competing ideas.

Prompt Rules Always define silhouette, costume anchors, and one memorable visual hook. If the user wants a reusable character, keep 访问ories and palette consistent across variants. Use a sheet-style prompt for reference art; use a scene-style prompt for story art. When underspecified, prefer strong archetypes over generic 'cool character' wording. Avoid too many unrelated props multiple equal-priority characters unless the user asks for a duo/group unclear costume materials or indistinct silhouette overly busy background scenes for reference-style art 工作流 运行 the readiness gate and resolve IMAGE_GEN_API_KEY Clarify the scenario-specific decisions above Build a single strong prompt from the blueprint Choose a recommended style only if it helps the 请求 生成 the image If the user wants variations, change one major variable at a time and re-生成 Script

{baseDir} is the directory contAIning this file. ${BUN_X} is either bun or npx -y bun.

Path Purpose {baseDir}/scripts/mAIn.ts the only execution entrypoint Usage Examples # examples only; M should be chosen by the user or resolved by the 代理 M=

${BUN_X} {baseDir}/scripts/mAIn.ts --prompt "original fantasy character, young female archivist mage, emerald robe with gold embroidery, floating paper charms, calm intelligent expression, full-body concept art, 清理 parchment backdrop" --style editorial --image character.png --ar 3:4 -m "$M"

${BUN_X} {baseDir}/scripts/mAIn.ts --prompt "anime character sheet for a cyberpunk courier boy, silver undercut hAIr, orange visor, black 实用工具 jacket, messenger drone companion, front pose with detAIl callouts feel, highly consistent de签名" --style anime --image character-sheet.png --ar 4:5 -m "$M"

Delivery Rules Tell the user what you are generating and which 模型 is being used before you 启动 Show the image directly when it is ready; do not reply with only a filename If the user asks for revisions, only change the necessary direction instead of re启动ing everything If the 请求 is underspecified, use the clarification order above before writing the final prompt References references/config/first-time-设置up.md references/config/preferences-模式.md references/config/模型-registry-模式.md references/style-pre设置s.md references/weryAI-平台.md