muapi-blog-header

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Blog Header

博客标题图片

Create a professional, eye-catching blog post header image sized for web (1200×628) with optional title composition guidance.
Estimated credits: ~12 per run.
创建适用于网页的专业吸睛博客文章标题图片(尺寸1200×628),并提供可选的标题排版指导。
预估消耗积分: 每次运行约12积分。

Inputs

输入参数

NameTypeRequiredDefaultDescription
topic
textyesThe blog post topic or title (e.g. "10 productivity hacks for remote developers").
publication_style
textnoclean, editorial, modern, professionalVisual style matching the blog's brand (e.g. "dark tech blog", "warm lifestyle", "minimalist corporate").
dominant_color
textnoOptional primary color direction (e.g. "deep blue", "warm amber", "monochrome").
名称类型必填默认值描述
topic
文本博客文章的主题或标题(例如:“远程开发者的10条生产力技巧”)。
publication_style
文本clean, editorial, modern, professional匹配博客品牌的视觉风格(例如:“深色科技博客”、“温暖生活方式”、“极简企业风”)。
dominant_color
文本可选的主色调方向(例如:“深蓝色”、“暖琥珀色”、“单色”)。

Steps

步骤

Generate a single, publication-quality blog header in one shot — no plan needed unless the user requests variants.
  1. Derive a strong visual metaphor for
    {{topic}}
    :
    • Avoid cliché stock photo compositions (handshake, lightbulb alone).
    • Prefer: dynamic flat lay, abstract concept visualization, illustrated scene, or dramatic lifestyle moment.
  2. Build the image prompt:
    • Subject derived from the metaphor above.
    • Style:
      {{publication_style}}, editorial photography, 16:9 wide, professional blog header, 
      ample negative space on the left side for title text overlay, {{dominant_color}} color palette
      .
    • Tier: quality.
    • Aspect ratio: 1.91:1 (standard Open Graph / blog hero).
  3. Call
    muapi image generate
    (model=gpt-image-2-text-to-image, aspect_ratio=21:9).
一键生成符合出版品质的博客标题图片——除非用户要求变体,否则无需额外规划。
  1. {{topic}}
    提炼一个鲜明的视觉隐喻:
    • 避免老套的库存照片构图(如握手、单独的灯泡)。
    • 优先选择:动态平铺构图、抽象概念可视化、插画场景或富有冲击力的生活瞬间。
  2. 构建图片生成提示词:
    • 主体内容源自上述隐喻。
    • 风格:
      {{publication_style}}, editorial photography, 16:9 wide, professional blog header, 
      左侧预留充足留白以叠加标题文本, {{dominant_color}} color palette
    • 层级:quality。
    • 宽高比:1.91:1(标准Open Graph / 博客首图比例)。
  3. 调用
    muapi image generate
    (model=gpt-image-2-text-to-image, aspect_ratio=21:9)。

Deliverables

交付成果

Return:
  • The header image asset.
  • Title placement guidance: where to overlay the blog title for best readability.
  • Quick alt-text: SEO-friendly image alt text (1 sentence).
返回:
  • 标题图片资源。
  • 标题放置指导:最佳标题叠加位置,确保可读性。
  • 快速替代文本:符合SEO要求的图片替代文本(一句话)。

Notes

注意事项

  • Leave empty space (negative space) intentionally so titles can be overlaid without clashing.
  • If the user uploads an existing brand photo, use
    muapi image edit
    to adapt it instead of generating from scratch.
  • For dark-mode blogs, suggest a dark background; for light, keep backgrounds bright.
  • 刻意预留空白区域(留白),以便叠加标题时不会产生视觉冲突。
  • 如果用户上传了现有品牌照片,使用
    muapi image edit
    进行调整,而非从头生成。
  • 针对深色模式博客,建议使用深色背景;浅色模式则保持背景明亮。

Trigger Keywords

触发关键词

blog header
,
blog image
,
article image
,
featured image
,
og image
,
open graph image
,
hero image

blog header
,
blog image
,
article image
,
featured image
,
og image
,
open graph image
,
hero image

Notes for the Executing Agent

执行Agent注意事项

  • This recipe is LLM-orchestrated: read each phase, gather any missing inputs from the user, then call
    muapi
    CLI commands. Use
    muapi auth configure
    first if
    MUAPI_API_KEY
    is unset.
  • For model IDs without a CLI alias yet, fall back to the raw endpoint via
    curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'
    and poll with
    muapi predict wait <request_id>
    .
  • Substitute
    {{input_name}}
    placeholders with the user's actual inputs before issuing each call.
  • 本流程由LLM编排:阅读每个阶段,向用户收集缺失的输入参数,然后调用
    muapi
    CLI命令。如果
    MUAPI_API_KEY
    未设置,先执行
    muapi auth configure
  • 对于尚未有CLI别名的模型ID,通过
    curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'
    调用原始端点,并使用
    muapi predict wait <request_id>
    进行轮询。
  • 在发出每个调用前,将
    {{input_name}}
    占位符替换为用户的实际输入。