图片免费 已验证

编辑人物极简排版分享封面

以原创编辑风格人物插画搭配精准标题排版,制作清晰利落的社交分享封面。适用于产品发布、文章预览和系列内容;在保持极简、易读和视觉一致的同时,建立鲜明的人物视觉识别。

sl-editorial-character-minimal-typography-og-image sample output

你会得到

  • 一张至少宽 1200 像素的 16:9 分享封面图
  • 一个根据主题设计的原创线描人物
  • 适合缩略图阅读的克制标题排版
  • 便于系列复用的网格、配色和人物绘制规范

适合

  • 只有一句简短标题的产品发布或功能公告
  • 需要建立插画识别度的文章和出版系列

不适合

  • 包含多条主张、多个标志或多个行动号召的文案密集型活动
  • 需要真实摄影叙事或准确描绘真人的内容

你需要提供

  • 准确的标题文案及可选说明文字
  • 用于构思人物形象的产品或出版内容背景

运行要求

  • Node.js 20+
  • A SkillLoom generation key (prepaid)

运行成本

Each image is generated with your prepaid SkillLoom generation key (about $0.05 per image at 1K). Subscriptions do not include generation credits.

一次典型运行约 $0.05(按 sub2api 价格,从你的预付费 key 扣除)

试试这个提示词

/sl-editorial-character-minimal-typography-og-image 为虚构阅读应用 Pagewell 制作 16:9 产品发布分享封面。准确呈现标题 “Read more, remember better.”,使用大号、高对比度 Didone 展示字体,左对齐,最多分成两行。画面搭配一个手捧打开书本、身旁放着紧凑书摞的机智轻松编辑风格线描人物,置于朱红色背景上。不要添加标志、产品名、网址、标签或其他文字。

后续提示词

  • 保持同一视觉系统,让人物动作显得更好奇。
  • 制作第二张系列封面,将标题分成均衡的两行。

验证情况

已验证

render-checkpass4.0 / 5114s

常见问题

可以加入产品名称吗?

可以。请提供准确名称,并说明是否要将其作为说明文字展示。图片不会自行编造名称、标志或宣传主张。

适合制作统一的系列封面吗?

适合。复用网格、标题限制、线描方式和标志性底色,并根据每期主题调整人物动作。

SKILL.md

SKILL.md

Editorial Character Minimal Typography OG Image

Generate a polished 16:9 sharing image with a distinctive editorial character, precise headline typography, and a repeatable visual system.

Style: Editorial Character. Witty and composed, pairing a small expressive line-art character with confident editorial typography on a vivid, controlled ground. Follow references/style-guide.md exactly.

Use this skill when

  • Product launches and feature announcements with one short headline
  • Articles and publishing series that benefit from a recognizable illustrated voice

Do not use

  • Photorealistic portraits, product mockups, or detailed scenes that need realistic material rendering
  • Text-heavy announcements, data graphics, or layouts requiring several logos and calls to action
  • To reproduce another company's brand, logo, product UI or copyrighted characters.

Inputs

  • Fictional or user-provided product or publication name, if it should appear
  • Exact headline text and optional short descriptor
  • Audience, subject, or launch context to inform the character’s gesture
  • Preferred accent color or permission to use the signature red ground

If something essential is missing, ask one short question before starting. Never invent facts, numbers, quotes or customer names; mark gaps as [needs source].

Workflow

  1. Collect the brief fields listed in references/prompt-framework.md. If any text will appear in the image, confirm it letter by letter and freeze it.
  2. Build the prompt with references/prompt-framework.md, following references/visual-system.md for subject, composition, light, palette and the text policy. Write it to prompt.txt.
  3. Check that the generation key is configured: SKILLLOOM_API_KEY and SKILLLOOM_BASE_URL (run npx skillloom doctor --write-env if not).
  4. Tell the user the image is paid from their prepaid key (see the cost note) and get explicit approval.
  5. Generate one image. The task id is saved first, so re-running the same command resumes instead of paying twice:

``bash node scripts/generate.mjs --prompt-file prompt.txt --output image.png --task-file image-task.json --confirm-paid ``

  1. Run the validator and fix every problem it reports:

``bash node scripts/validate-image.mjs image.png ``

What makes this excellent

  • Treat the supplied headline as locked copy: preserve spelling, punctuation, capitalization, and line meaning exactly; do not add text.
  • Choose one simple character action that makes the subject immediately understandable at thumbnail size, without relying on a real person or recognizable mascot.
  • Build the layout on a quiet modular grid: headline occupies the broad left area and the character anchors the right, with safe margins for social crops.
  • Keep the character drawing expressive but economical: consistent black line weight, a few solid fills, and no detailed setting or props beyond one relevant object.
  • Use the fictional sample’s vivid red ground as the series signature; honor a user-requested color only when it maintains strong text contrast and visual consistency.
  • Before delivery, inspect headline rendering at small preview size and regenerate if any characters are malformed, duplicated, or obscured.

Output contract

  • One PNG at 16:9, at least 1200px wide, following the visual system; any approved text spelled exactly.
  • No logos, watermarks or real people's likenesses unless the user owns them.
  • A hand-off note with the final prompt, the task file path and the validator output.
  • Deliver one 16:9 image at a minimum width of 1200 pixels, composed for Open Graph and social preview crops.
  • Include only user-approved copy; do not invent a brand mark, URL, badge, or supporting claim.

Reference demo and agent run

The preview image was generated from the sample brief in scripts/image-spec.json. In a real run the agent fills the brief from the user's request, generates with the user's key, checks the result against the output contract (required text, ratio, no extra words) and regenerates when it misses.

Failure rules

  • If the API reports a low balance or a limit, stop and tell the user; never switch providers or keys silently.
  • If text is misspelled or the composition misses the visual system, ask before generating again. Never retry automatically; every attempt is paid.
  • Never print or store the API key in files you hand over.

相似技能

编辑人物极简排版分享封面 · SkillLoom