Back to Details

muapi-ad-creative

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Ad Creative Set

广告创意素材套装

Generate a high-converting ad creative set — hero image, ad copy variations, and platform-optimized crops for Meta, Google Display, and LinkedIn.
Estimated credits: ~60 per run.
生成一套高转化的广告创意素材——包括主视觉图、多种广告文案变体，以及针对Meta、Google Display和LinkedIn平台优化的裁剪图。
预估消耗点数： 每次运行约60点。

Inputs

输入参数

NameTypeRequiredDefaultDescription
product_or_service
textyes—What is being advertised (e.g. "SaaS project management tool for remote teams").
target_audience
textyes—Who the ad is for (e.g. "startup founders aged 25–40, tech-savvy").
campaign_goal
textnoawarenessCampaign objective — "awareness", "consideration", or "conversion".
tone
textnoprofessional, clean, modernCreative tone and visual style (e.g. "bold and disruptive", "luxury minimal", "friendly and approachable").
product_image
image_urlno—Optional product or brand image URL already in the session.
名称类型是否必填默认值描述
product_or_service
文本是—广告推广的产品或服务（例如：“面向远程团队的SaaS项目管理工具”）。
target_audience
文本是—广告目标受众（例如：“25-40岁、精通技术的初创公司创始人”）。
campaign_goal
文本否awareness广告活动目标——可选“awareness（品牌认知）”、“consideration（用户考量）”或“conversion（转化）”。
tone
文本否professional, clean, modern创意风格与视觉调性（例如：“大胆颠覆”、“奢华极简”、“亲切易接近”）。
product_image
图片URL否—会话中已有的可选产品或品牌图片URL。

Steps

执行步骤

This skill has TWO phases. Phase A creates the hero concept for approval; Phase B fans out to platform formats.
本技能分为两个阶段。阶段A生成主视觉创意方案供审核；阶段B扩展生成各平台适配格式。

Phase A — Hero image + Ad copy

阶段A — 主视觉图 + 广告文案

Submit ONE the plan with:
  1. Hero image — 
    muapi image generate
    (model=nano-banana-pro) or 
    muapi image edit
    (model=nano-banana-pro-edit) if 
    {{product_image}}
    is provided:
    • Aspect ratio: 1:1 (universal starting point).
    • Prompt must capture: product/service benefit, target audience lifestyle cue, campaign tone.
    • Style: 
      {{tone}}, advertising photography, clean background, product focus, ultra detailed, commercial quality
      .
    • Tier: quality.
After the plan executes, present the hero asset and 3 ad copy variations:
  • Variation A — Problem-aware hook: "Tired of X? [Product] fixes that."
  • Variation B — Benefit-led: "[Feature] → [Outcome] for [Audience]."
  • Variation C — Social proof / urgency: "X teams already use [Product]." Each variation includes: Headline (6 words max), Body (20–30 words), CTA button text.
Ask which copy variation to use for Phase B. Wait for user confirmation.
提交一份执行计划，包含：
  1. 主视觉图 — 若提供了
    {{product_image}}
    ，使用
    muapi image generate
    （模型=nano-banana-pro）或
    muapi image edit
    （模型=nano-banana-pro-edit）生成：
    • 宽高比：1:1（通用起始比例）。
    • 提示词需涵盖：产品/服务核心价值、目标受众生活场景线索、广告活动调性。
    • 风格：
      {{tone}}, advertising photography, clean background, product focus, ultra detailed, commercial quality
      。
    • 等级：quality（高品质）。
计划执行完成后，展示主视觉素材及3种广告文案变体：
  • 变体A — 问题导向钩子：“受X困扰？[产品]帮你解决。”
  • 变体B — 价值主导：“[功能] → 为[受众]带来[成果]。”
  • 变体C — 社交证明/紧迫感：“已有X个团队在使用[产品]。” 每个变体包含：标题（最多6词）、正文（20-30词）、CTA按钮文本。
询问用户选择哪种文案变体进入阶段B，等待用户确认。

Phase B — Platform crops

阶段B — 平台适配裁剪图

Once the user picks a copy direction, submit a SECOND the plan with parallel crops:
  1. muapi image edit
    → 1:1 (Facebook/Instagram feed, 1080×1080)
  2. muapi image edit
    → 9:16 (Story/Reels, 1080×1920)
  3. muapi image edit
    → 1.91:1 (Facebook feed wide, 1200×628)
  4. muapi image edit
    → 1:1 (LinkedIn feed, same as FB)
For each crop:
  • Prompt: "Reframe for [platform] ad format. Keep product/subject centered and uncropped. Maintain original palette and tone. Leave headroom/footroom for text overlays."
  • All crops run in parallel.
Return one asset per format with the recommended copy overlay placement for each.
用户选定文案方向后，提交第二份并行执行的裁剪计划：
  1. muapi image edit
    → 1:1（Facebook/Instagram动态 feed，1080×1080）
  2. muapi image edit
    → 9:16（快拍/短视频 Story/Reels，1080×1920）
  3. muapi image edit
    → 1.91:1（Facebook宽版动态 feed，1200×628）
  4. muapi image edit
    → 1:1（LinkedIn动态 feed，与Facebook一致）
针对每种裁剪格式：
  • 提示词：“适配[平台]广告格式重新构图。保持产品/主体居中且不被裁切。保留原始配色与调性。预留文本叠加的顶部/底部空间。”
  • 所有裁剪任务并行执行。
返回每种格式对应的素材，并标注推荐的文案叠加位置。

Notes

注意事项

  • If 
    campaign_goal
    is "conversion", emphasize urgency and direct CTA in copy.
  • If 
    campaign_goal
    is "awareness", prioritize visual impact over text density.
  • Reference 
    product_image
    via 
    $nX.url
    syntax in Phase B nodes to ensure consistency.
  • Do NOT auto-confirm Phase B without user picking a copy variation.
  • 若
    campaign_goal
    为“conversion（转化）”，文案需强调紧迫感与直接行动号召（CTA）。
  • 若
    campaign_goal
    为“awareness（品牌认知）”，优先突出视觉冲击力而非文本密度。
  • 在阶段B节点中使用
    $nX.url
    语法引用
    product_image
    ，确保素材一致性。
  • 未获得用户选定的文案变体前，不得自动启动阶段B。

Trigger Keywords

触发关键词

ad creative
, 
advertisement
, 
facebook ad
, 
meta ad
, 
google ad
, 
linkedin ad
, 
paid ad
, 
ad banner
, 
display ad
ad creative
, 
advertisement
, 
facebook ad
, 
meta ad
, 
google ad
, 
linkedin ad
, 
paid ad
, 
ad banner
, 
display ad

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：阅读各阶段要求，向用户收集缺失的输入参数，再调用
    muapi
    CLI命令。若未设置
    MUAPI_API_KEY
    ，需先执行
    muapi auth configure
    。
  • 对于尚未有CLI别名的模型ID，可通过原始端点调用：
    curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'
    ，并使用
    muapi predict wait <request_id>
    轮询结果。
  • 发起调用前，需将
    {{input_name}}
    占位符替换为用户实际输入内容。