marketing

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Marketing production with genmedia

借助genmedia开展营销资产制作

Use this skill when the user wants a campaign system, not one isolated asset. Load references as needed:

```
references/campaign-patterns.md
```
```
references/workflows.md
```
```
references/examples.md
```

Load

model-routing

alongside this skill for default endpoint choices.

Marketing output should be executable: a brief, asset matrix, genmedia command plan, downloaded files, and clear defects. Do not add fake claims, fake social proof, fake partner logos, fake award badges, or invented legal copy.

当用户需要一套完整的活动体系而非单一孤立资产时，可使用本Skill。按需加载参考资料：

```
references/campaign-patterns.md
```
```
references/workflows.md
```
```
references/examples.md
```

加载

model-routing

与本Skill配合使用，以获取默认端点选项。

营销产出需具备可执行性：包含活动简报、资产矩阵、genmedia命令计划、已下载文件及明确的缺陷说明。不得添加虚假宣传、虚假社交证明、虚假合作伙伴标志、虚假奖项徽章或虚构的法律文案。

Inputs to collect

需要收集的输入信息

Only ask when missing details would change the asset plan.

Objective: launch, acquisition, retargeting, activation, education, event.
Audience: persona, market, use case, awareness level, objections.
Offer: product, feature, bundle, trial, waitlist, event, promotion.
Channels: paid social, organic social, landing page, email, display, app.
Required assets: stills, video, thumbnails, hero image, carousel, banner.
Brand rules: colors, logo use, typography, tone, taboo visuals, competitors.
Source media: product images, screenshots, app UI, people, logo, prior ads.
Claims: exact approved copy, proof points, disclaimers, compliance limits.
Budget preference: final-quality, draft exploration, or mixed pipeline.

仅当缺失信息会改变资产规划时才询问用户。

目标：新品发布、用户获取、重定向营销、用户激活、教育推广、活动营销。
受众：用户画像、目标市场、使用场景、认知程度、异议点。
推广内容：产品、功能、捆绑套餐、试用、等待名单、活动、促销。
渠道：付费社交平台、自然社交平台、落地页、电子邮件、展示广告、应用内广告。
所需资产：静态图片、视频、缩略图、主视觉图、轮播素材、横幅广告。
品牌规则：配色、标志使用规范、字体、语气、禁忌视觉元素、竞品相关限制。
源媒体：产品图片、截图、应用UI、人物素材、品牌标志、过往广告素材。
宣传声明：已获批的准确文案、证明点、免责声明、合规限制。
预算偏好：最终品质级、草稿探索级或混合流程。

Genmedia workflow

Genmedia工作流程

Start from routed endpoint IDs.

bash

genmedia models --endpoint_id openai/gpt-image-2 --json
genmedia models --endpoint_id fal-ai/nano-banana-pro/edit --json
genmedia models --endpoint_id fal-ai/nano-banana-2 --json
genmedia models --endpoint_id bytedance/seedance-2.0/image-to-video --json
genmedia models --endpoint_id bytedance/seedance-2.0/text-to-video --json
genmedia models --endpoint_id veed/fabric-1.0 --json

Use text search only as fallback discovery for a missing channel role:

bash

genmedia models "marketing banner image typography" --json
genmedia models "social ad video product campaign" --json
genmedia docs "image generation text rendering" --json

Inspect the selected endpoint before planning exact payloads.

bash

genmedia schema <endpoint_id> --json
genmedia pricing <endpoint_id> --json

Upload all source media.

bash

genmedia upload ./product.png --json
genmedia upload ./logo.svg --json
genmedia upload ./screenshot.png --json
genmedia upload ./creator.jpg --json

Build the campaign matrix before generating.

Minimum matrix:
- Hook asset: earns attention in the first frame.
- Proof asset: shows product, result, process, feature, or evidence.
- Context asset: places product in audience use case.
- Conversion asset: clean end frame with safe space for external copy.

Run still assets synchronously when quick.

bash

genmedia run <endpoint_id> \
  --prompt "<marketing asset prompt>" \
  --download "./outputs/marketing/{request_id}_{index}.{ext}" \
  --json

Run video assets async and download from status.

bash

genmedia run <endpoint_id> \
  --prompt "<campaign video prompt>" \
  --async \
  --json

genmedia status <endpoint_id> <request_id> \
  --download "./outputs/marketing/{request_id}_{index}.{ext}" \
  --json

Use schema fields exactly. Do not pass guessed flags. Mirror names such as

image_urls

image_url

reference_image_url

aspect_ratio

duration

quality

seed

prompt

, or

negative_prompt

从路由端点ID开始。

bash

genmedia models --endpoint_id openai/gpt-image-2 --json
genmedia models --endpoint_id fal-ai/nano-banana-pro/edit --json
genmedia models --endpoint_id fal-ai/nano-banana-2 --json
genmedia models --endpoint_id bytedance/seedance-2.0/image-to-video --json
genmedia models --endpoint_id bytedance/seedance-2.0/text-to-video --json
genmedia models --endpoint_id veed/fabric-1.0 --json

仅当缺少对应渠道的角色时，才将文本搜索作为备用发现方式：

bash

genmedia models "marketing banner image typography" --json
genmedia models "social ad video product campaign" --json
genmedia docs "image generation text rendering" --json

在规划具体负载前，先检查所选端点。

bash

genmedia schema <endpoint_id> --json
genmedia pricing <endpoint_id> --json

上传所有源媒体。

bash

genmedia upload ./product.png --json
genmedia upload ./logo.svg --json
genmedia upload ./screenshot.png --json
genmedia upload ./creator.jpg --json

在生成资产前构建活动矩阵。

基础矩阵包含：
- 引流资产：在第一帧吸引受众注意力。
- 证明资产：展示产品、效果、流程、功能或相关证据。
- 场景资产：将产品置于受众的使用场景中。
- 转化资产：简洁的结尾帧，预留外部文案的安全区域。

若静态资产生成速度快，则同步运行。

bash

genmedia run <endpoint_id> \
  --prompt "<marketing asset prompt>" \
  --download "./outputs/marketing/{request_id}_{index}.{ext}" \
  --json

异步运行视频资产，并通过状态查询结果下载。

bash

genmedia run <endpoint_id> \
  --prompt "<campaign video prompt>" \
  --async \
  --json

genmedia status <endpoint_id> <request_id> \
  --download "./outputs/marketing/{request_id}_{index}.{ext}" \
  --json

严格使用Schema字段。不得传递猜测的参数。需完全匹配字段名称，如
```
image_urls
```
、
```
image_url
```
、
```
reference_image_url
```
、
```
aspect_ratio
```
、
```
duration
```
、
```
quality
```
、
```
seed
```
、
```
prompt
```
或
```
negative_prompt
```
。

Brief build order

活动简报构建顺序

Build the campaign brief before prompts:

Product truth: what the product is and what must stay accurate.
Audience tension: problem, desire, objection, or trigger moment.
Campaign promise: user-approved benefit or visible outcome.
Asset roles: hook, proof, context, conversion, retention, reminder.
Channel specs: crop, runtime, safe zones, text needs, file count.
Variation axis: audience, setting, proof point, visual metaphor, offer.
Guardrails: claims, logo, legal, copy, product fidelity, banned imagery.

在编写提示词前先构建活动简报：

产品事实：产品本质及必须保持准确的信息。
受众痛点：问题、需求、异议或触发时刻。
活动承诺：用户认可的收益或可见成果。
资产角色：引流、证明、场景、转化、留存、提醒。
渠道规格：裁剪要求、时长、安全区域、文案需求、文件数量。
变体维度：受众、场景、证明点、视觉隐喻、推广内容。
约束规则：宣传声明、标志使用、合规要求、文案、产品保真度、禁用视觉元素。

Prompt build order

提示词构建顺序

Write every asset prompt in this order:

Asset role and channel: launch hero, Meta ad, TikTok hook, email header.
Product or subject invariant: exact product, UI, feature, person, logo rule.
Audience context: where, who, problem state, usage moment.
Visual system: camera, lighting, color, composition, texture, motion.
Copy handling: no generated text, safe space, or exact provided wording.
Variant axis: what differs from the other assets.
Guardrails: no fake claims, no extra logos, no distorted product or UI.

所有资产提示词均按以下顺序编写：

资产角色与渠道：发布主视觉、Meta广告、TikTok引流素材、邮件头部图。
产品或主体固定信息：准确的产品、UI、功能、人物、标志使用规则。
受众场景：地点、人群、问题状态、使用时刻。
视觉体系：镜头、光线、配色、构图、纹理、动态效果。
文案处理：不生成文案、预留安全区域或使用提供的准确文案。
变体维度：与其他资产的差异点。
约束规则：不得添加虚假宣传、不得额外添加标志、不得扭曲产品或UI。

Model routing

模型路由

Text-heavy campaign key art, posters, landing heroes, app/UI visuals, and ads with exact copy:
```
openai/gpt-image-2
```
at
```
quality=high
```
.

Premium product or brand stills:

openai/gpt-image-2

, then

fal-ai/nano-banana-pro

, then

fal-ai/nano-banana-2

Edits from source assets:

fal-ai/nano-banana-pro/edit

, then

openai/gpt-image-2/edit

, then

fal-ai/bytedance/seedream/v5/lite/edit

Fast visual exploration:
```
fal-ai/flux-2/klein/9b
```
.
Product reveal or social video:
```
bytedance/seedance-2.0/image-to-video
```
.
Text-to-video concept or brand film:
```
bytedance/seedance-2.0/text-to-video
```
.

Creator or spokesperson ad: load

ugc

and use

veed/fabric-1.0

veed/fabric-1.0/text

, or

fal-ai/creatify/aurora

Multi-shot narrative: load
```
storytelling
```
.
Single polished product asset: load
```
commercial
```
.

含大量文案的活动主视觉、海报、落地页主图、应用/UI视觉素材及需精准文案的广告：使用
```
openai/gpt-image-2
```
，设置
```
quality=high
```
。

高端产品或品牌静态图：优先

openai/gpt-image-2

，其次

fal-ai/nano-banana-pro

，最后

fal-ai/nano-banana-2

。

基于源资产的编辑：优先

fal-ai/nano-banana-pro/edit

，其次

openai/gpt-image-2/edit

，最后

fal-ai/bytedance/seedream/v5/lite/edit

。

快速视觉探索：使用
```
fal-ai/flux-2/klein/9b
```
。
产品揭秘或社交视频：使用
```
bytedance/seedance-2.0/image-to-video
```
。
文本转视频概念或品牌影片：使用
```
bytedance/seedance-2.0/text-to-video
```
。

创作者或代言人广告：加载

ugc

并使用

veed/fabric-1.0

、

veed/fabric-1.0/text

或

fal-ai/creatify/aurora

。

多镜头叙事：加载
```
storytelling
```
。
单一精修产品资产：加载
```
commercial
```
。

Quality bar

质量标准

Before returning:

Every asset maps to a campaign role and channel.
Product, UI, logo, and packaging are stable.
Claims are user-supplied, observable, or removed.
Text is either exact and schema-supported or reserved for external editing.
Variants differ by one clear axis, not random style drift.
Safe zones support overlays, cropping, and platform UI.
Output paths come from
```
downloaded_files[]
```
.
The final answer includes a campaign manifest: asset role, endpoint, request id, local path, prompt summary, and defects.

If the campaign feels generic, reduce the asset count and make each role more specific before generating more variants.

返回结果前需确认：

每一项资产都对应活动角色与渠道。
产品、UI、标志及包装保持一致。
宣传声明均为用户提供、可验证或已移除。
文案要么准确且符合Schema支持，要么预留供外部编辑。
变体仅在一个明确维度上存在差异，而非随机风格偏移。
安全区域支持叠加内容、裁剪及平台UI展示。
输出路径来自
```
downloaded_files[]
```
。
最终答案包含活动清单：资产角色、端点、请求ID、本地路径、提示词摘要及缺陷说明。

若活动内容过于通用，应先减少资产数量并明确每个角色的定位，再生成更多变体。