ads-photoshoot

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Ads Photoshoot — AI Product Photography

Ads Photoshoot — AI产品摄影

Transforms a product image or description into professional ad-ready photography in 5 distinct visual styles. Each style generates at two sizes: 1:1 (Meta/LinkedIn) and 9:16 (TikTok/Reels/Stories).

可将产品图片或描述转换为5种不同视觉风格的专业广告可用摄影作品。每种风格会生成两种尺寸：1:1（适用于Meta/LinkedIn）和9:16（适用于TikTok/Reels/Stories）。

Quick Reference

快速参考

Command	What it does
`/ads photoshoot`	Interactive: ask for product + styles
`/ads photoshoot --styles studio floating`	Generate only selected styles
`/ads photoshoot --product shoe.jpg`	Start with a product image file
`/ads photoshoot --all-platforms`	Generate all 5 sizes per style

命令	功能
`/ads photoshoot`	交互式流程：询问产品信息及风格选择
`/ads photoshoot --styles studio floating`	仅生成指定风格的作品
`/ads photoshoot --product shoe.jpg`	从指定产品图片文件开始生成
`/ads photoshoot --all-platforms`	为每种风格生成全部5种尺寸的作品

Environment Setup

环境配置

bash

export GOOGLE_API_KEY="your-key"

bash

export GOOGLE_API_KEY="your-key"

See /ads generate for alternative providers

查看 /ads generate 了解其他可选服务商

undefined

undefined

Process

生成流程

Step 1: Collect Product Information

步骤1：收集产品信息

Ask (combine into one message):

Product image: Path to product image file (local) OR product URL OR text description

"Provide a product image path (e.g. ./product.jpg), a URL, or describe your product"
Product description: What is it? Key features to highlight? (helps prompt quality)
Styles to generate: Which of the 5 styles? (default: all 5)
- Studio, Floating, Ingredient, In Use, Lifestyle
Target platforms: Which platforms will these run on?
- Determines output sizes (default: Meta + TikTok → 1:1 + 9:16)

一次性询问以下内容：

产品图片：本地产品图片文件路径、产品URL或文字描述

"请提供产品图片路径（例如 ./product.jpg）、URL，或描述你的产品"
产品描述：产品是什么？有哪些需要突出的核心特性？（有助于提升提示词质量）
生成风格：选择5种风格中的哪些？（默认：全部5种）
- Studio（棚拍）、Floating（悬浮）、Ingredient（原料展示）、In Use（使用场景）、Lifestyle（生活方式）
目标平台：这些素材将用于哪些平台？
- 决定输出尺寸（默认：Meta + TikTok → 1:1 + 9:16）

Step 2: Load Brand Profile (Optional)

步骤2：加载品牌档案（可选）

Check for

brand-profile.json

in the current directory.

If found, extract for style injection:

```
colors.primary
```
→ inject into backgrounds and accent elements
```
aesthetic.mood_keywords
```
→ inject as atmosphere descriptors
```
target_audience
```
→ use for Lifestyle and In Use context
```
imagery.forbidden
```
→ exclude from all prompts

If not found, proceed with standard style templates.

检查当前目录下是否存在

brand-profile.json

文件。

如果找到，提取以下信息用于风格注入：

```
colors.primary
```
→ 融入背景和强调元素
```
aesthetic.mood_keywords
```
→ 作为氛围描述词
```
target_audience
```
→ 用于Lifestyle和In Use风格的场景构建
```
imagery.forbidden
```
→ 从所有提示词中排除相关元素

如果未找到，则使用标准风格模板生成。

Step 3: Check API Key

步骤3：检查API密钥

Verify the required environment variable is set before generating:

bash

python3 -c "
import os, sys
provider = os.environ.get('ADS_IMAGE_PROVIDER', 'gemini')
keys = {'gemini': 'GOOGLE_API_KEY', 'openai': 'OPENAI_API_KEY',
        'stability': 'STABILITY_API_KEY', 'replicate': 'REPLICATE_API_TOKEN'}
env_var = keys.get(provider, 'GOOGLE_API_KEY')
if not os.environ.get(env_var):
    print(f'Error: {env_var} not set (provider: {provider})', file=sys.stderr)
    sys.exit(1)
print(f'OK: {env_var} is set')
"

If this exits with code 1, show setup instructions from

~/.claude/skills/ads/references/image-providers.md

and stop.

生成前验证是否已设置所需环境变量：

bash

python3 -c "
import os, sys
provider = os.environ.get('ADS_IMAGE_PROVIDER', 'gemini')
keys = {'gemini': 'GOOGLE_API_KEY', 'openai': 'OPENAI_API_KEY',
        'stability': 'STABILITY_API_KEY', 'replicate': 'REPLICATE_API_TOKEN'}
env_var = keys.get(provider, 'GOOGLE_API_KEY')
if not os.environ.get(env_var):
    print(f'Error: {env_var} not set (provider: {provider})', file=sys.stderr)
    sys.exit(1)
print(f'OK: {env_var} is set')
"

如果该脚本退出码为1，显示

~/.claude/skills/ads/references/image-providers.md

中的配置说明并终止流程。

Step 4: Construct Prompts per Style

步骤4：为每种风格构建提示词

For each selected style, build the prompt using the template + product description + brand DNA.

针对每个选中的风格，使用模板+产品描述+品牌信息构建提示词。

Style 1: Studio

风格1：Studio（棚拍）

Clean, e-commerce style product shot.

Base template:

"[product description], professional product photography, clean white seamless
background, even studio lighting, soft drop shadow, high detail product focus,
ecommerce style, [brand.colors.primary] subtle accent reflections if applicable,
top-down or 3/4 angle, no distractions, catalog quality"

Composition: Centered, slight 3/4 angle or flat lay. Output sizes: 1080×1080, 1080×1920

简洁的电商风格产品照片。

基础模板：

"[产品描述], 专业产品摄影, 干净的白色无缝背景, 均匀的棚拍灯光, 柔和的投影, 高细节产品聚焦, 电商风格, [品牌主色调] 若适用则添加微妙的反光点缀, 俯视或3/4角度, 无干扰元素, 商品目录级质量"

构图： 居中，轻微3/4角度或平铺。 输出尺寸： 1080×1080, 1080×1920

Style 2: Floating

风格2：Floating（悬浮）

Dramatic levitation effect.

Base template:

"[product description] floating in mid-air, dramatic floating product shot,
[brand.colors.primary or brand.aesthetic.mood_keywords[0]] gradient background,
atmospheric shadow below product, levitation effect, product defying gravity,
clean modern aesthetic, high contrast, striking visual"

Composition: Product centered vertically, ample space above and below. Output sizes: 1080×1080, 1080×1920

富有冲击力的悬浮效果。

基础模板：

"[产品描述] 悬浮在空中, 富有冲击力的悬浮产品照片,
[品牌主色调或品牌氛围关键词第一个] 渐变背景,
产品下方的氛围阴影, 悬浮效果, 产品仿佛摆脱重力,
干净现代的美学风格, 高对比度, 极具视觉吸引力"

构图： 产品垂直居中，上下留有充足空间。 输出尺寸： 1080×1080, 1080×1920

Style 3: Ingredient

风格3：Ingredient（原料展示）

Flat lay with components.

Base template:

"[product description] centered flat lay, surrounded by its key ingredients
or materials artfully arranged, top-down overhead view, clean light background,
natural texture surface, product as hero element, ingredients scattered with
intentional negative space, editorial food photography style"

Composition: Top-down, product in center, ingredients fanning out. Output sizes: 1080×1080 (optimal for this style)

包含组件的平铺构图。

基础模板：

"[产品描述] 居中平铺, 周围精心布置其核心原料或材质,
俯视角度, 干净明亮的背景, 自然纹理的表面,
产品为核心元素, 原料分散布置并留有刻意的留白,
编辑级美食摄影风格"

构图： 俯视，产品居中，原料呈扇形散开。 输出尺寸： 1080×1080（该风格最优尺寸）

Style 4: In Use

风格4：In Use（使用场景）

Authentic usage context.

Base template:

"person's hands using [product description] in natural context, lifestyle
photography, focus on product-hand interaction, shallow depth of field,
warm natural window light, authentic not staged, [brand.target_audience.profession]
implied context, [brand.aesthetic.mood_keywords] atmosphere"

Composition: Hands prominent, product clearly identifiable, background soft-focus. Note: Hands only — no full face (avoids model release complications). Output sizes: 1080×1080, 1080×1920

真实的使用场景。

基础模板：

"人手在自然场景中使用[产品描述], 生活方式摄影,
聚焦产品与手的互动, 浅景深,
温暖的自然窗光, 真实而非摆拍,
[目标受众职业] 隐含场景, [品牌氛围关键词] 氛围"

构图： 手部突出，产品清晰可辨，背景虚化。 注意： 仅展示手部，不出现完整面部（避免模特授权问题）。 输出尺寸： 1080×1080, 1080×1920

Style 5: Lifestyle

风格5：Lifestyle（生活方式）

Aspirational full-context shot.

Base template:

"[product description] in aspirational lifestyle scene, [brand.target_audience.age_range]
demographic implied environment, [brand.target_audience.profession] context,
[brand.aesthetic.mood_keywords] atmosphere, golden hour or clean natural lighting,
editorial photography style, [brand.aesthetic.negative_space] composition,
product clearly visible and prominent"

Composition: Environmental context, product as hero element within the scene. Output sizes: 1080×1080, 1080×1920

具有感染力的完整场景照片。

基础模板：

"[产品描述] 置于具有感染力的生活场景中,
[目标受众年龄层] 对应的环境,
[目标受众职业] 场景,
[品牌氛围关键词] 氛围,
黄金时段或干净的自然光,
编辑级摄影风格,
[品牌留白风格] 构图,
产品清晰可见且为核心元素"

构图： 环境为背景，产品是场景中的核心元素。 输出尺寸： 1080×1080, 1080×1920

Step 5: Generate Images

步骤5：生成图像

For each style × size combination:

bash

python ~/.claude/skills/ads/scripts/generate_image.py \
  "[constructed prompt]" \
  --size [WxH] \
  --output ./product-photos/[style]/[product-slug]-[style]-[WxH].png \
  --json

Track results. If a generation fails, retry once with a simplified prompt.

针对每种风格×尺寸组合执行以下命令：

bash

python ~/.claude/skills/ads/scripts/generate_image.py \
  "[构建好的提示词]" \
  --size [宽x高] \
  --output ./product-photos/[风格]/[产品别名]-[风格]-[宽x高].png \
  --json

跟踪生成结果。若生成失败，使用简化提示词重试一次。

Step 6: Organize and Report

步骤6：整理与报告

Output directory structure:

./product-photos/
  studio/
    product-studio-1080x1080.png
    product-studio-1080x1920.png
  floating/
    product-floating-1080x1080.png
    product-floating-1080x1920.png
  ingredient/
    product-ingredient-1080x1080.png
  in-use/
    product-in-use-1080x1080.png
    product-in-use-1080x1920.png
  lifestyle/
    product-lifestyle-1080x1080.png
    product-lifestyle-1080x1920.png

Summary:

✓ Product photos generated: [N] images

  Studio:     ./product-photos/studio/ (2 sizes)
  Floating:   ./product-photos/floating/ (2 sizes)
  Ingredient: ./product-photos/ingredient/ (1 size — square only)
  In Use:     ./product-photos/in-use/ (2 sizes)
  Lifestyle:  ./product-photos/lifestyle/ (2 sizes)

  Estimated cost: [N] images × $0.067 = ~$[total]

  Best for:
  • Meta Feed → Studio (4:5) or Lifestyle (4:5)
  • TikTok/Reels → Floating (9:16) or In Use (9:16)
  • LinkedIn → Studio (1:1) or Lifestyle (1:1)
  • Google PMax → Studio (1:1) — crop to 1.91:1 after

  Run `/ads generate` to use these in a full campaign.

输出目录结构：

./product-photos/
  studio/
    product-studio-1080x1080.png
    product-studio-1080x1920.png
  floating/
    product-floating-1080x1080.png
    product-floating-1080x1920.png
  ingredient/
    product-ingredient-1080x1080.png
  in-use/
    product-in-use-1080x1080.png
    product-in-use-1080x1920.png
  lifestyle/
    product-lifestyle-1080x1080.png
    product-lifestyle-1080x1920.png

生成总结：

✓ 已生成产品照片：[N] 张

  Studio:     ./product-photos/studio/（2种尺寸）
  Floating:   ./product-photos/floating/（2种尺寸）
  Ingredient: ./product-photos/ingredient/（1种尺寸 — 仅正方形）
  In Use:     ./product-photos/in-use/（2种尺寸）
  Lifestyle:  ./product-photos/lifestyle/（2种尺寸）

  预估成本：[N] 张 × $0.067 = ~$[总计]

  平台适配建议：
  • Meta Feed → Studio（4:5）或 Lifestyle（4:5）
  • TikTok/Reels → Floating（9:16）或 In Use（9:16）
  • LinkedIn → Studio（1:1）或 Lifestyle（1:1）
  • Google PMax → Studio（1:1）— 生成后裁剪为1.91:1

  运行 `/ads generate` 可将这些素材用于完整广告活动。

Cost Estimate

成本预估

Before generating, show:

Number of styles selected × 2 sizes = total images
"$[N] images × $0.067 = ~$[total] (Gemini default)"
If >$0.50, ask for confirmation

生成前显示：

选中风格数量 × 2 = 总图像数量
"$[N] 张 × $0.067 = ~$[总计]（默认使用Gemini）"
若预估成本超过$0.50，需确认是否继续

Platform Recommendations

平台推荐

Style	Best Platforms	Rationale
Studio	Meta Feed, LinkedIn, Google PMax	Universal, clean, platform-safe
Floating	Meta Reels, TikTok, Stories	High visual impact on vertical placements
Ingredient	Meta Feed, Pinterest	Works best as square; tells product story
In Use	TikTok, Meta Reels, Stories	Authentic, native-feeling content
Lifestyle	All platforms	Aspirational, broad audience appeal

风格	最佳适配平台	理由
Studio	Meta Feed、LinkedIn、Google PMax	通用、简洁、符合平台规范
Floating	Meta Reels、TikTok、Stories	垂直布局下视觉冲击力强
Ingredient	Meta Feed、Pinterest	正方形效果最佳；传递产品故事
In Use	TikTok、Meta Reels、Stories	真实自然，贴近原生内容
Lifestyle	所有平台	具有感染力，受众广泛

Reference Files

�考文件

~/.claude/skills/ads/references/image-providers.md

— API setup and pricing

~/.claude/skills/ads/references/brand-dna-template.md

— Brand injection schema

~/.claude/skills/ads/references/meta-creative-specs.md

— Safe zone for 9:16

~/.claude/skills/ads/references/tiktok-creative-specs.md

— Safe zone constraints

~/.claude/skills/ads/references/image-providers.md

— API配置及定价

~/.claude/skills/ads/references/brand-dna-template.md

— 品牌风格注入模板

~/.claude/skills/ads/references/meta-creative-specs.md

— 9:16尺寸安全区域规范

~/.claude/skills/ads/references/tiktok-creative-specs.md

— TikTok平台安全区域限制