image-ecommerce

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

image-ecommerce

Use this skill for all e-commerce product photography requests on Starchild.

Covers: white-background hero shots, lifestyle product scenes, flat lay arrangements, detail/macro close-ups, packaging/unboxing shots, group/collection displays, scale reference images, seasonal themes (spring/summer/autumn/winter), 360-degree views, comparison layouts, infographic-style feature callouts, and platform-optimized images for Amazon, Shopify, Taobao, Instagram, Xiaohongshu, Etsy, eBay.

Core principle: call the provided script. Do not re-implement proxy/billing plumbing.

When to use image-ecommerce vs other image skills:

image-ecommerce → user wants PRODUCT PHOTOS for e-commerce, catalogs, or marketing
image-edit → user wants to EDIT or TRANSFORM an existing image (not product-specific)
image-portrait → user wants a portrait with their face/identity preserved
image-create → user wants to CREATE something from text (not product photography)
image-tryon → user wants to try on clothing/accessories on a person

在Starchild平台上，所有电商产品摄影需求均可使用此skill。

涵盖：白底主图、产品生活场景图、平铺俯拍布局、细节/微距特写图、包装/开箱展示图、产品组/系列展示图、尺寸参考图、季节主题图（春/夏/秋/冬）、360°全景图、对比布局图、信息图表式功能标注图，以及针对Amazon、Shopify、淘宝、Instagram、小红书、Etsy、eBay优化的平台适配图片。

**核心原则：**调用提供的脚本，请勿重新实现代理/计费相关逻辑。

何时选择image-ecommerce而非其他图片类skill：

image-ecommerce → 用户需要用于电商、产品目录或营销活动的产品照片
image-edit → 用户需要编辑或转换现有图片（非产品摄影专属）
image-portrait → 用户需要保留面部/身份特征的肖像照
image-create → 用户需要根据文本生成内容（非产品摄影）
image-tryon → 用户需要将服饰/配饰试穿在人物身上

1. Quick start — single product photo (most common)

1. 快速入门 — 单张产品照片（最常用）

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    product_path="uploads/product.jpg",
    style="hero",
    background="white",
)

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    product_path="uploads/product.jpg",
    style="hero",
    background="white",
)

result -> {"success": True, "images": [{"local_path": "output/images/..."}], ...}


The script reads the local file, base64-encodes it, and sends it to fal.ai as a data URI — no manual URL publishing needed.


该脚本会读取本地文件，将其base64编码后以数据URI形式发送至fal.ai，无需手动发布URL。

2. Quick start — public URL

2. 快速入门 — 公共URL

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    product_url="https://example.com/product.jpg",
    style="lifestyle",
    background="natural",
)

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    product_url="https://example.com/product.jpg",
    style="lifestyle",
    background="natural",
)

3. Quick start — text-to-image (no product photo)

3. 快速入门 — 文本生成图片（无产品照片）

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    prompt="premium wireless bluetooth headphones, matte black finish, over-ear design",
    style="hero",
    background="white",
)

When no

product_path

product_url

is provided, the script uses the text-to-image endpoint (no

/edit

suffix). A

prompt

describing the product is required in this mode.

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    prompt="premium wireless bluetooth headphones, matte black finish, over-ear design",
    style="hero",
    background="white",
)

当未提供

product_path

或

product_url

时，脚本会使用文本生成图片接口（无

/edit

后缀）。此模式下必须提供描述产品的

prompt

。

4. Quick start — platform-optimized

4. 快速入门 — 平台适配优化

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    product_path="uploads/product.jpg",
    platform="amazon",
)

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    product_path="uploads/product.jpg",
    platform="amazon",
)

Automatically applies: style=hero, background=white, aspect_ratio=1:1

自动应用：style=hero, background=white, aspect_ratio=1:1

undefined

undefined

5. Quick start — complete product image set

5. 快速入门 — 完整产品图片套装

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo_set(
    product_path="uploads/product.jpg",
    prompt="premium leather wallet",
    platform="amazon",
)

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo_set(
    product_path="uploads/product.jpg",
    prompt="premium leather wallet",
    platform="amazon",
)

Generates 7 images: hero, lifestyle, detail, scale, alternate angle, packaging, flat lay

生成7张图片：主图、生活场景图、细节图、尺寸参考图、多角度图、包装图、平铺俯拍图

undefined

undefined

Delivering the result to the user — IMPORTANT

向用户交付结果 — 重要提示

Never hand the user the raw fal.media URL. fal serves files with restrictive CSP headers. The only reliable delivery path is the already-downloaded local file:

Use each image's
```
local_path
```
(e.g.
```
output/images/xxx.png
```
) — the script always downloads on success.
Tell the user the files are saved to
```
output/images/
```
and viewable in the workspace file panel.
On Web channel, embed inline so the user can preview in chat:
markdown
```
![product](output/images/<filename>.png)
```

On Telegram / WeChat: send via

send_to_telegram(file_path="output/images/...", message_type="image")

send_to_wechat(file_path="output/images/...", message_type="image")

切勿直接将原始fal.media URL交给用户。fal提供的文件带有严格的CSP头，唯一可靠的交付方式是已下载的本地文件：

使用每张图片的
```
local_path
```
（例如
```
output/images/xxx.png
```
）——脚本在执行成功后总会自动下载文件。
告知用户文件已保存至
```
output/images/
```
，可在工作区文件面板中查看。
在Web渠道中，将图片嵌入聊天内容以便用户预览：
markdown
```
![product](output/images/<filename>.png)
```

在Telegram/微信渠道中，通过

send_to_telegram(file_path="output/images/...", message_type="image")

或

send_to_wechat(file_path="output/images/...", message_type="image")

发送图片。

6. Parameters —

product_photo()

6. 参数说明 —

product_photo()

Parameter	Required	Default	Description
`product_path`	no	—	Local workspace file path to the product image
`product_url`	no	—	Public HTTPS URL of the product image
`prompt`	no	—	Custom prompt describing the product or desired photo
`style`	no	`"hero"`	Photography style preset (see §7)
`background`	no	`"white"`	Background type (see §8)
`model`	no	`"nanopro"`	Model: `"nanopro"` (fast ~25s) or `"gpt"` (best quality ~150s)
`count`	no	`1`	Number of images to generate (1–8)
`aspect_ratio`	no	`"1:1"`	Output ratio: `1:1` , `3:4` , `4:3` , `9:16` , `16:9`
`platform`	no	—	Platform preset: `amazon` , `shopify` , `taobao` , `instagram` , `xiaohongshu` , `etsy` , `ebay`

Image input rules:

Provide
```
product_path
```
OR
```
product_url
```
for edit mode (transform existing product photo).
If both are given,
```
product_path
```
takes priority.
Omit both for pure text-to-image generation (requires
```
prompt
```
).

Prompt priority:

prompt + style/background

(enhanced) >

style + background

templates.

Platform preset: When

platform

is set, it overrides default

style

background

, and

aspect_ratio

with platform-optimized values — unless you explicitly set them.

参数	必填	默认值	描述
`product_path`	否	—	产品图片在本地工作区的文件路径
`product_url`	否	—	产品图片的公开HTTPS URL
`prompt`	否	—	描述产品或期望照片效果的自定义提示词
`style`	否	`"hero"`	摄影风格预设（见第7节）
`background`	否	`"white"`	背景类型（见第8节）
`model`	否	`"nanopro"`	模型选项： `"nanopro"` （快速，约25秒）或 `"gpt"` （最佳画质，约150秒）
`count`	否	`1`	生成图片数量（1–8张）
`aspect_ratio`	否	`"1:1"`	输出比例： `1:1` , `3:4` , `4:3` , `9:16` , `16:9`
`platform`	否	—	平台预设： `amazon` , `shopify` , `taobao` , `instagram` , `xiaohongshu` , `etsy` , `ebay`

图片输入规则：

若要使用编辑模式（转换现有产品照片），需提供
```
product_path
```
或
```
product_url
```
。
若同时提供两者，
```
product_path
```
优先级更高。
若两者都不提供，则启用纯文本生成图片模式（需提供
```
prompt
```
）。

提示词优先级：

prompt + 风格/背景

（增强版） >

风格 + 背景

模板。

平台预设： 设置

platform

后，会使用平台优化值覆盖默认的

style

、

background

和

aspect_ratio

——除非你显式指定这些参数。

7. Photography styles

7. 摄影风格

Core product shots

核心产品照片

Style	Key	Best for
Hero shot	`hero`	Primary listing image, magazine ads, main product display
Lifestyle	`lifestyle`	Product in use, editorial, social media
Flat lay	`flat_lay`	Instagram, top-down arrangement, catalog
Detail close-up	`detail`	Material quality, texture, craftsmanship
Packaging	`packaging`	Unboxing experience, brand packaging
Group/collection	`group`	Multiple products, variants, bundles
Scale reference	`scale`	Size comparison, product in hand

风格	标识	适用场景
主图	`hero`	商品列表首图、杂志广告、产品主展示位
生活场景	`lifestyle`	产品使用场景、社论内容、社交媒体
平铺俯拍	`flat_lay`	Instagram、俯视布局、产品目录
细节特写	`detail`	材质质感、纹理、工艺展示
包装展示	`packaging`	开箱体验、品牌包装展示
产品组/系列	`group`	多产品展示、变体产品、套装产品
尺寸参考	`scale`	大小对比、手持产品展示

Marketing & informational

营销与信息类

Style	Key	Best for
360° view	`360_view`	Multi-angle showcase, turntable display
Comparison	`comparison`	Side-by-side, before/after, feature highlight
Infographic	`infographic`	Feature callouts, specs, dimensions

风格	标识	适用场景
360°全景	`360_view`	多角度展示、转盘式呈现
对比图	`comparison`	并排对比、前后对比、功能亮点展示
信息图表	`infographic`	功能标注、参数说明、尺寸展示

Seasonal campaigns

季节营销活动

Style	Key	Best for
Spring	`seasonal_spring`	Cherry blossoms, fresh green, pastel
Summer	`seasonal_summer`	Beach, sunshine, tropical, vacation
Autumn	`seasonal_autumn`	Fall leaves, golden tones, harvest
Winter	`seasonal_winter`	Snow, holiday, festive, cozy

风格	标识	适用场景
春季	`seasonal_spring`	樱花、清新绿色、马卡龙色调
夏季	`seasonal_summer`	海滩、阳光、热带风情、度假场景
秋季	`seasonal_autumn`	落叶、金色色调、丰收主题
冬季	`seasonal_winter`	雪景、节日氛围、温馨场景

8. Background types

8. 背景类型

Background	Key	Best for
Pure white	`white`	Amazon, e-commerce standard, marketplace listings
Gradient	`gradient`	Hero shots, premium feel, modern
Studio	`studio`	Professional catalog, controlled lighting
Natural	`natural`	Outdoor products, organic brands
Lifestyle	`lifestyle`	Home/office context, in-use scenarios
Colored	`colored`	Brand-matching, vibrant marketing
Textured	`textured`	Luxury products, marble/wood surface
Transparent	`transparent`	Product cutout, PNG for design use

背景	标识	适用场景
纯白背景	`white`	Amazon、电商标准、平台商品列表
渐变背景	`gradient`	主图、高端质感、现代风格
工作室背景	`studio`	专业产品目录、可控光线环境
自然背景	`natural`	户外产品、有机品牌
生活场景背景	`lifestyle`	家居/办公场景、产品使用场景
纯色背景	`colored`	品牌配色、活力营销内容
纹理背景	`textured`	高端产品、大理石/木质表面
透明背景	`transparent`	产品抠图、设计用PNG图

9. Platform presets

9. 平台预设

Platform	Aspect Ratio	Background	Style	Key Requirements
Amazon	1:1	white	hero	Pure white bg (RGB 255,255,255), product fills 85%+, no props/text/watermarks, min 1000px (1600px+ for zoom)
Shopify	1:1	white	hero	Square format, consistent catalog style, 2048x2048 recommended
Taobao	1:1	white	hero	800x800 minimum, white bg for main image
Instagram	1:1	lifestyle	lifestyle	1080x1080 feed, lifestyle context, visually appealing
Xiaohongshu	3:4	lifestyle	flat_lay	1080x1440 vertical, aesthetic flat lay, text overlay space
Etsy	4:3	natural	lifestyle	Handmade/artisan feel, natural backgrounds
eBay	1:1	white	hero	White background, clear product view, 1600px min for zoom

平台	宽高比	背景	风格	核心要求
Amazon	1:1	white	hero	纯白背景（RGB 255,255,255），产品占比85%以上，无道具/文字/水印，最小尺寸1000px（支持缩放需1600px以上）
Shopify	1:1	white	hero	正方形格式，统一目录风格，推荐尺寸2048x2048
淘宝	1:1	white	hero	最小尺寸800x800，主图需使用白底
Instagram	1:1	lifestyle	lifestyle	1080x1080 feed尺寸，生活场景背景，视觉吸引力强
小红书	3:4	lifestyle	flat_lay	1080x1440竖版尺寸，美观的平铺俯拍布局，预留文字叠加空间
Etsy	4:3	natural	lifestyle	手工/匠人风格，自然背景
eBay	1:1	white	hero	白底背景，产品清晰展示，最小尺寸1600px以支持缩放

10. Model selection guide

10. 模型选择指南

Model	Key	Speed	Quality	Best for
NanoPro	`nanopro`	~25s	Good	Default for all requests. Fast iteration.
GPT Image 2	`gpt`	~150s	Best	When user explicitly asks for "highest quality" or "best quality". Complex scenes.

Decision rules:

Default: always use
```
nanopro
```
unless the user explicitly requests higher quality.
Use
gpt
when: user says "highest quality", "best quality", "premium", or the scene is very complex with many specific details.
Use
nanopro
when: user wants fast results, is iterating on styles, or generating multiple images.

python

undefined

模型	标识	速度	画质	适用场景
NanoPro	`nanopro`	~25秒	良好	所有请求的默认选项，快速迭代
GPT Image 2	`gpt`	~150秒	最佳	用户明确要求“最高画质”或“最佳质量”时，以及复杂场景

决策规则：

默认设置： 除非用户明确要求更高画质，否则始终使用
```
nanopro
```
。
使用
gpt
的场景：用户提及“最高画质”、“最佳质量”、“高端”，或场景包含大量特定细节的复杂内容。
使用
nanopro
的场景：用户需要快速结果、迭代风格，或生成多张图片。

python

undefined

Default (fast)

默认（快速）

result = product_photo(product_path="product.jpg", style="hero")

High quality (user requested)

高画质（用户要求）

result = product_photo(product_path="product.jpg", style="hero", model="gpt")

---

result = product_photo(product_path="product.jpg", style="hero", model="gpt")

---

11. Intent recognition guide

11. 意图识别指南

Use this table to map user requests to the correct style + background:

使用下表将用户请求映射到对应的风格+背景：

Product listing images

商品列表图片

User says	Style	Background	Notes
"product photo", "listing image", "主图"	`hero`	`white`	Default e-commerce
"Amazon listing", "亚马逊主图"	`hero`	`white`	Use `platform="amazon"`
"Shopify product", "独立站产品图"	`hero`	`white`	Use `platform="shopify"`
"淘宝主图", "天猫主图"	`hero`	`white`	Use `platform="taobao"`
"white background", "白底图"	`hero`	`white`	Standard packshot
"product on white", "纯白背景"	`hero`	`white`	Amazon-style

用户表述	风格	背景	说明
"产品照片"、"商品列表图片"、"主图"	`hero`	`white`	电商默认选项
"Amazon商品列表"、"亚马逊主图"	`hero`	`white`	使用 `platform="amazon"`
"Shopify产品"、"独立站产品图"	`hero`	`white`	使用 `platform="shopify"`
"淘宝主图"、"天猫主图"	`hero`	`white`	使用 `platform="taobao"`
"白底图"、"white background"	`hero`	`white`	标准产品图
"纯白背景产品"、"product on white"	`hero`	`white`	Amazon风格

Lifestyle & context

生活场景与环境

User says	Style	Background	Notes
"lifestyle photo", "场景图"	`lifestyle`	`lifestyle`	Product in context
"product in use", "使用场景"	`lifestyle`	`lifestyle`	Show product being used
"flat lay", "俯拍", "平铺"	`flat_lay`	`textured`	Top-down arrangement
"Instagram product", "小红书产品"	`flat_lay`	`lifestyle`	Social media optimized

用户表述	风格	背景	说明
"生活场景图"、"lifestyle photo"	`lifestyle`	`lifestyle`	产品使用场景
"产品使用场景"、"product in use"	`lifestyle`	`lifestyle`	展示产品使用状态
"俯拍"、"平铺"、"flat lay"	`flat_lay`	`textured`	俯视布局
"Instagram产品图"、"小红书产品图"	`flat_lay`	`lifestyle`	社交媒体优化

Detail & technical

细节与技术类

User says	Style	Background	Notes
"close-up", "detail shot", "细节图"	`detail`	`studio`	Macro/texture
"packaging", "包装图", "开箱"	`packaging`	`studio`	Box + product
"size comparison", "尺寸对比"	`scale`	`studio`	With reference object
"multiple products", "组合图"	`group`	`white`	Collection display
"360 view", "多角度"	`360_view`	`white`	Turntable style
"comparison", "对比图"	`comparison`	`white`	Side by side
"infographic", "功能标注"	`infographic`	`white`	Feature callouts

用户表述	风格	背景	说明
"特写"、"细节图"、"close-up"	`detail`	`studio`	微距/纹理展示
"包装图"、"开箱"、"packaging"	`packaging`	`studio`	包装盒+产品展示
"尺寸对比"、"size comparison"	`scale`	`studio`	搭配参考物体
"多产品图"、"组合图"、"multiple products"	`group`	`white`	系列产品展示
"多角度图"、"360 view"	`360_view`	`white`	转盘式展示
"对比图"、"comparison"	`comparison`	`white`	并排对比
"功能标注"、"infographic"	`infographic`	`white`	功能亮点标注

Seasonal & campaign

季节与营销活动

User says	Style	Background	Notes
"spring campaign", "春季"	`seasonal_spring`	auto	Cherry blossoms, pastel
"summer sale", "夏季"	`seasonal_summer`	auto	Beach, tropical
"autumn/fall", "秋季"	`seasonal_autumn`	auto	Golden leaves, warm
"winter/holiday", "冬季", "圣诞"	`seasonal_winter`	auto	Snow, festive

用户表述	风格	背景	说明
"春季营销"、"spring campaign"	`seasonal_spring`	自动	樱花、马卡龙色调
"夏季促销"、"summer sale"	`seasonal_summer`	自动	海滩、热带风情
"秋季"、"autumn/fall"	`seasonal_autumn`	自动	金色落叶、温暖色调
"冬季"、"圣诞"、"winter/holiday"	`seasonal_winter`	自动	雪景、节日氛围

Complete product set

完整产品图片套装

User says	Function	Notes
"complete set", "全套产品图", "listing images"	`product_photo_set()`	7 images covering all angles
"Amazon listing set", "亚马逊全套"	`product_photo_set(platform="amazon")`	Platform-optimized set

用户表述	功能	说明
"全套产品图"、"complete set"、"listing images"	`product_photo_set()`	生成7张覆盖全角度的图片
"Amazon全套商品图"、"Amazon listing set"	`product_photo_set(platform="amazon")`	平台优化的图片套装

12. Usage examples by scenario

12. 场景使用示例

Amazon listing — white background hero shot

Amazon商品列表 — 白底主图

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    product_path="uploads/headphones.jpg",
    platform="amazon",
)

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    product_path="uploads/headphones.jpg",
    platform="amazon",
)

Lifestyle product photo

产品生活场景图

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    product_path="uploads/coffee_mug.jpg",
    style="lifestyle",
    background="lifestyle",
    prompt="premium coffee mug on rustic wooden table beside an open book, morning sunlight",
)

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    product_path="uploads/coffee_mug.jpg",
    style="lifestyle",
    background="lifestyle",
    prompt="premium coffee mug on rustic wooden table beside an open book, morning sunlight",
)

Product detail close-up

产品细节特写图

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    product_path="uploads/leather_bag.jpg",
    style="detail",
    background="studio",
    prompt="extreme close-up of leather stitching and grain texture",
)

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    product_path="uploads/leather_bag.jpg",
    style="detail",
    background="studio",
    prompt="extreme close-up of leather stitching and grain texture",
)

Seasonal campaign — winter holiday

季节营销活动 — 冬季节日

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    product_path="uploads/candle.jpg",
    style="seasonal_winter",
    prompt="luxury scented candle in cozy holiday setting with pine branches and warm glow",
)

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    product_path="uploads/candle.jpg",
    style="seasonal_winter",
    prompt="luxury scented candle in cozy holiday setting with pine branches and warm glow",
)

Text-to-image — generate product from description

文本生成图片 — 根据描述生成产品

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    prompt="sleek minimalist smartwatch with black silicone band and OLED display showing time",
    style="hero",
    background="gradient",
    model="gpt",
)

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    prompt="sleek minimalist smartwatch with black silicone band and OLED display showing time",
    style="hero",
    background="gradient",
    model="gpt",
)

Flat lay for Instagram / Xiaohongshu

Instagram/小红书平铺俯拍图

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    product_path="uploads/skincare_set.jpg",
    style="flat_lay",
    background="textured",
    platform="xiaohongshu",
)

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    product_path="uploads/skincare_set.jpg",
    style="flat_lay",
    background="textured",
    platform="xiaohongshu",
)

Multiple images — batch generation

批量生成多张图片

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    product_path="uploads/sneakers.jpg",
    style="hero",
    background="white",
    count=4,
)

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo(
    product_path="uploads/sneakers.jpg",
    style="hero",
    background="white",
    count=4,
)

Generates 4 variations of the hero shot

生成4张主图变体

undefined

undefined

Complete product image set

完整产品图片套装

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo_set(
    product_path="uploads/wallet.jpg",
    prompt="premium leather bifold wallet",
    platform="amazon",
)

python

exec(open('skills/image-ecommerce/product_photo.py').read())
result = product_photo_set(
    product_path="uploads/wallet.jpg",
    prompt="premium leather bifold wallet",
    platform="amazon",
)

result -> {"success": True, "sets": [...], "total_images": 7, ...}

Generates: hero, lifestyle, detail, scale, alternate angle, packaging, flat lay

生成：主图、生活场景图、细节图、尺寸参考图、多角度图、包装图、平铺俯拍图

---

---

13. Prompt engineering best practices

13. 提示词优化最佳实践

The product photography prompt structure

产品摄影提示词结构

Every effective product photo prompt should include these elements:

[product description], [photography style], [lighting], [background/surface], [composition], [quality modifiers]

有效的产品摄影提示词应包含以下元素：

[产品描述], [摄影风格], [光线], [背景/表面], [构图], [画质修饰词]

Key principles (derived from product-photography, eachlabs-product-visuals, image-create skills)

核心原则（源自product-photography、eachlabs-product-visuals、image-create技能）

Product preservation is critical — when editing an existing product image:
- Always emphasize "keep the product exactly as it is"
- Preserve shape, color, branding, and details
- Only change the background/context/lighting
Lighting specificity — always specify lighting type:
- Studio: "soft diffused studio lighting", "even lighting with no shadows"
- Dramatic: "dramatic rim lighting", "edge light for premium feel"
- Natural: "natural window light", "golden hour warm light"
- Flat: "flat even lighting" (for e-commerce white background)
Background precision — vague backgrounds produce poor results:
- ❌ "nice background"
- ✅ "pure white background #FFFFFF, no shadows"
- ✅ "rustic wooden table with morning sunlight"
- ✅ "soft gradient from white to light grey"
Composition rules (from product-photography skill):
- Hero shot: product fills 80% of frame, slight 15-30° angle
- Packshot (Amazon): product dead center, fills 85%+
- Flat lay: bird's eye view, organized arrangement
- Group: odd numbers (3 or 5), triangle composition
Shadow types matter:
- No shadow: Amazon/e-commerce requirements
- Contact shadow: grounded but clean
- Drop shadow: adds depth, professional
- Reflection: tech, luxury, premium feel
Material and texture — for detail shots, specify:
- "visible leather grain and stitching"
- "brushed metal finish with subtle reflections"
- "soft fabric texture, thread detail visible"
Platform compliance — when targeting a specific platform:
- Amazon: pure white (RGB 255,255,255), no props/text/watermarks
- Instagram: lifestyle context, visually appealing
- Xiaohongshu: vertical format, aesthetic, text overlay space

产品还原至关重要 — 编辑现有产品图片时：
- 始终强调“保持产品原样”
- 保留产品形状、颜色、品牌标识和细节
- 仅修改背景/环境/光线
光线明确性 — 始终指定光线类型：
- 工作室光线：“柔和漫射工作室光线”、“均匀无阴影光线”
- 戏剧性光线：“戏剧性轮廓光”、“边缘光营造高端质感”
- 自然光：“自然窗光”、“黄金时段暖光”
- 平光：“均匀平光”（适用于电商白底图）
背景精准性 — 模糊的背景描述会导致效果不佳：
- ❌ “好看的背景”
- ✅ “纯白背景#FFFFFF，无阴影”
- ✅ “质朴木桌搭配清晨阳光”
- ✅ “从白色到浅灰色的柔和渐变”
构图规则（源自product-photography技能）：
- 主图：产品占画面80%，轻微15-30°角度
- 产品图（Amazon风格）：产品居中，占比85%以上
- 平铺俯拍：鸟瞰视角，布局整齐
- 产品组：奇数数量（3或5个），三角形构图
阴影类型影响效果：
- 无阴影：Amazon/电商要求
- 接触阴影：产品落地感强且干净
- 投影：增加层次感，专业风格
- 倒影：科技、高端产品适用
材质与纹理 — 细节图需明确：
- “可见皮革纹理与缝线”
- “拉丝金属质感带轻微反光”
- “柔软织物纹理，可见缝线细节”
平台合规性 — 针对特定平台时：
- Amazon：纯白背景（RGB 255,255,255），无道具/文字/水印
- Instagram：生活场景背景，视觉吸引力强
- 小红书：竖版格式，美观布局，预留文字叠加空间

Example: building a custom prompt

示例：构建自定义提示词

User request: "I need a hero shot of my leather wallet for Amazon"

python

result = product_photo(
    product_path="uploads/wallet.jpg",
    platform="amazon",
    prompt="premium leather bifold wallet, rich brown color, slight angle showing card slots",
)

The script automatically builds:

Transform this product image into a professional e-commerce photo.
Keep the product exactly as it is — preserve its shape, color, details, and branding.
premium leather bifold wallet, rich brown color, slight angle showing card slots.
Photography style: professional product hero shot, clean composition, studio lighting...
Background: pure white background #FFFFFF, clean, e-commerce standard, no shadows.

用户请求：“我需要一张用于Amazon的皮革钱包主图”

python

result = product_photo(
    product_path="uploads/wallet.jpg",
    platform="amazon",
    prompt="premium leather bifold wallet, rich brown color, slight angle showing card slots",
)

脚本会自动生成完整提示词：

将此产品图片转换为专业电商照片。
保持产品原样——保留其形状、颜色、细节和品牌标识。
premium leather bifold wallet, rich brown color, slight angle showing card slots.
摄影风格：专业产品主图，简洁构图，工作室光线...
背景：纯白背景#FFFFFF，干净，电商标准，无阴影。

14. E-commerce image set guide

14. 电商图片套装指南

A complete product listing needs 7-9 images. Use

product_photo_set()

for automatic generation, or create individual shots:


white
lifestyle
studio
studio
white
studio
textured
white
seasonal_*

Position	Image Type	Style	Background	Purpose
1	Hero / packshot	`hero`	`white`	Primary listing image
2	Lifestyle	`lifestyle`	`lifestyle`	Product in use/context
3	Detail close-up	`detail`	`studio`	Material quality, craftsmanship
4	Scale reference	`scale`	`studio`	Size in hand or next to known object
5	Alternate angle	`hero`	`white`	Back or side view
6	Packaging	`packaging`	`studio`	Unboxing experience
7	Flat lay	`flat_lay`	`textured`	Arranged composition
8	Infographic	`infographic`	`white`	Dimensions, specs, features
9	Seasonal	`seasonal_*`	auto	Campaign-specific

完整的商品列表需要7-9张图片。可使用

product_photo_set()

自动生成，或手动创建单张图片：


white
lifestyle
studio
studio
white
studio
textured
white
seasonal_*

位置	图片类型	风格	背景	用途
1	主图/产品图	`hero`	`white`	商品列表首图
2	生活场景图	`lifestyle`	`lifestyle`	产品使用场景展示
3	细节特写图	`detail`	`studio`	材质质感、工艺展示
4	尺寸参考图	`scale`	`studio`	手持或与已知物体对比展示大小
5	多角度图	`hero`	`white`	背面或侧面视图
6	包装图	`packaging`	`studio`	开箱体验展示
7	平铺俯拍图	`flat_lay`	`textured`	布局式展示
8	信息图表	`infographic`	`white`	尺寸、参数、功能展示
9	季节主题图	`seasonal_*`	自动	营销活动专属

15. Error handling

15. 错误处理

The script returns structured results. Always check

success

python

result = product_photo(product_path="uploads/product.jpg")
if result["success"]:
    for img in result["images"]:
        print(f"Saved: {img['local_path']}")
else:
    print(f"Error: {result.get('error')}")

Common errors:

```
"File not found"
```
— check the product_path
```
"Unsupported image format"
```
— use JPG, PNG, or WebP
```
"Image too large"
```
— max 10 MB

"Either a product image or a prompt is required"

— provide product_path/product_url or prompt

```
"Unknown style/background"
```
— check available presets in §7/§8

脚本会返回结构化结果，务必检查

success

字段：

python

result = product_photo(product_path="uploads/product.jpg")
if result["success"]:
    for img in result["images"]:
        print(f"已保存：{img['local_path']}")
else:
    print(f"错误：{result.get('error')}")

常见错误：

```
"File not found"
```
— 检查product_path是否正确
```
"Unsupported image format"
```
— 使用JPG、PNG或WebP格式
```
"Image too large"
```
— 图片最大不超过10 MB

"Either a product image or a prompt is required"

— 需提供product_path/product_url或prompt

```
"Unknown style/background"
```
— 检查第7/8节中的可用预设