muapi-product-ad-cinematic

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Cinematic Product Ad

电影质感产品广告

Cinematic 5–10s product ad from a product photo + brand brief.

Estimated credits: ~130 per run.

基于产品照片和品牌简介生成5-10秒的电影质感产品广告。

预估消耗积分： 每次运行约130积分。

Inputs

输入参数

Name	Type	Required	Default	Description
`product_image`	image_url	yes	—	URL of the product photo (must already be uploaded).
`brand_brief`	text	yes	—	Mood / style direction (e.g. "luxury minimal", "playful").
`duration_sec`	int	no	6	Final video length in seconds (5–10).

名称	类型	是否必填	默认值	描述
`product_image`	image_url	是	—	产品照片的URL（需已完成上传）。
`brand_brief`	text	是	—	氛围/风格方向（例如“奢华极简”、“活泼趣味”）。
`duration_sec`	int	否	6	最终视频时长（5-10秒）。

Steps

执行步骤

This skill has TWO phases separated by a user pick. Submit them as two separate the plan calls — never bundle downstream steps into the first plan.

该技能分为两个阶段，需由用户选择后推进。请将两个阶段作为独立的计划调用提交——切勿将后续步骤捆绑到第一个计划中。

Phase A — variant exploration (cheap)

阶段A——变体探索（低成本）

Submit ONE the plan containing only:

Hero frame variants — 4 separate
```
muapi image generate
```
nodes (model=nano-banana-2, aspect_ratio=16:9 by default).
- Each prompt restyles the product against the brand brief mood. Vary lighting, palette, framing, and lens between variants. Keep product geometry intact.
- Reference the user's
```
product_image
```
  if the model supports image conditioning; otherwise describe the product in detail.

After the plan executes, end your turn with a brief message listing the 4 asset_ids and asking the user which one to take forward (e.g. "Pick a hero (asset_1, asset_2, asset_3, or asset_4)?"). Wait.

提交仅包含以下内容的单个计划：

主画面变体——4个独立的
```
muapi image generate
```
节点（默认模型为nano-banana-2，宽高比16:9）。
- 每个提示词需根据品牌简介的氛围重新调整产品风格。在不同变体中改变光线、色调、构图和镜头效果。保持产品几何形态不变。
- 如果模型支持图像条件输入，请参考用户提供的
```
product_image
```
  ；否则请详细描述产品。

计划执行完成后，以简短消息列出4个asset_ids并询问用户选择哪一个推进（例如“请选择一个主画面（asset_1、asset_2、asset_3或asset_4）？”），等待用户回复。

Phase B — commit on the picked hero (expensive)

阶段B——基于选定主画面生成最终内容（高成本）

Once the user replies with their pick, submit a SECOND the plan:

Upscale the picked frame —
```
enhance_image
```
(operation=upscale).
Animate the upscaled frame —
```
muapi video from-image
```
(model=kling-v3.0-standard-image-to-video, duration={{duration_sec}}, prompt="slow cinematic push-in, soft volumetric light, subtle product micro-rotation"). Reference the upscale's URL with
```
$nX.url
```
.
Background music —
```
muapi audio create
```
(kind=music) — runs in parallel with the upscale/animate. Style derived from
```
brand_brief
```
(luxury → "ambient cinematic, warm strings, slow tempo, instrumental"). Duration ≈ video length.
Return the upscaled hero image and the final video.

用户回复选定的主画面后，提交第二个计划：

放大选定的画面——调用
```
enhance_image
```
（操作类型=upscale）。
动画化放大后的画面——调用
```
muapi video from-image
```
（模型=kling-v3.0-standard-image-to-video，时长={{duration_sec}}，提示词为“缓慢的电影式推镜，柔和的体积光，产品轻微微动”）。使用
```
$nX.url
```
引用放大后的画面URL。
背景音乐——调用
```
muapi audio create
```
（类型=music）——与放大/动画化步骤并行执行。风格需匹配
```
brand_brief
```
（例如奢华风格对应“氛围电影感，温暖弦乐，慢节奏，纯器乐”）。时长与视频时长大致相同。
返回放大后的主画面和最终视频。

Notes

注意事项

If the brief mentions "luxury", bias the palette to gold/black; for "playful", bias to bright/saturated.
If video gen fails after failover, fall back to a still-frame slideshow (just return the upscaled hero + music).
Don't auto-confirm step 4 — its cost (~80 cr) deserves a user nod.

如果品牌简介提到“奢华”，调色偏向金色/黑色；如果是“活泼趣味”，则偏向明亮/高饱和度色调。
如果视频生成失败且重试后仍失败，退而求其次生成静态画面幻灯片（仅返回放大后的主画面+音乐）。
步骤4无需自动确认——其成本（约80积分）需获得用户同意。

Trigger Keywords

触发关键词

product ad

commercial

cinematic ad

product video

product ad

、

commercial

、

cinematic ad

、

product video

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.

该流程由LLM编排：请仔细阅读每个阶段，向用户收集缺失的输入信息，然后调用
```
muapi
```
CLI命令。如果未设置
```
MUAPI_API_KEY
```
，请先执行
```
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。

在发出每个调用前，将
```
{{input_name}}
```
占位符替换为用户的实际输入。