higgsfield-product-photoshoot

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Product Photoshoot

产品拍摄

Brand-image generation via the

higgsfield product-photoshoot create

command. The CLI calls a backend prompt enhancer that holds mode-specific photography vocabulary and structural templates, then submits to

gpt_image_2

and returns image URLs.

通过

higgsfield product-photoshoot create

命令生成品牌级图片。CLI会调用后端的提示词优化器，该优化器包含特定模式的摄影词汇和结构化模板，随后将请求提交至

gpt_image_2

并返回图片URL。

Step 0 — Bootstrap

步骤0 — 初始化

Before any other command:

higgsfield

is not on

$PATH

, install it:

bash

curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh

higgsfield account status

fails with

Session expired

Not authenticated

, ask the user to run

higgsfield auth login

(interactive) and wait for confirmation.

在执行任何其他命令前：

如果

higgsfield

不在

$PATH

中，请安装：

bash

curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh

如果
```
higgsfield account status
```
返回「Session expired」/「Not authenticated」，请让用户执行
```
higgsfield auth login
```
（交互式）并等待确认。

UX Rules

UX规则

Be concise. Print only image URLs in the final reply.
Detect language, respond in it. Mode names and CLI flags stay English.
Ask at most 4 short questions before submitting. Use labeled options, never open-ended.
Skip questions whose answer is obvious from context (uploaded image, prior turn, brand memory).
Never write the gpt_image_2 prompt yourself — backend assembles it.
Polling is silent. Wait until URLs are ready, then deliver.

保持简洁。最终回复仅输出图片URL。
检测语言并使用对应语言回复。模式名称和CLI参数保持英文。
提交前最多询问4个简短问题。使用带标签的选项，切勿采用开放式问题。
若答案可从上下文（上传的图片、之前的对话、品牌记忆）中明确，则跳过对应问题。
请勿自行编写gpt_image_2提示词——由后端负责组装。
轮询过程静默进行。等待URL准备就绪后再交付结果。

Modes

支持模式

Mode	When user wants…
`product_shot`	Product on neutral / studio / catalog background
`lifestyle_scene`	Product in real-world environment, hands, action, atmosphere
`closeup_product_with_person`	Tight crop with hands / partial face — beauty application, holding, demonstrating
`pinterest_pin`	Vertical 2:3 Pinterest-native aesthetic, moodboard feel
`hero_banner`	Wide-format website / email / campaign header
`social_carousel`	3–10 connected slides for IG / LinkedIn / Facebook
`ad_creative_pack`	Coordinated pack of static ad variants for Meta / TikTok / Pinterest / Google Ads
`virtual_model_tryout`	Product worn or used by an AI-rendered model
`conceptual_product`	Surreal / CGI-style / levitating / splash / sculptural product
`restyle`	Transform an existing image's aesthetic, mood, or seasonal context

模式	用户需求场景…
`product_shot`	产品置于中性/棚拍/商品目录背景中
`lifestyle_scene`	产品处于真实环境、有人手互动、动态效果或特定氛围中
`closeup_product_with_person`	特写镜头包含人手/部分面部——如美妆涂抹、手持产品、演示操作
`pinterest_pin`	2:3竖版Pinterest原生美学风格，具有情绪板质感
`hero_banner`	宽幅网站/邮件/活动页眉
`social_carousel`	3–10张连贯幻灯片，适用于IG/LinkedIn/Facebook
`ad_creative_pack`	一套协调的静态广告变体，适用于Meta/TikTok/Pinterest/Google Ads
`virtual_model_tryout`	AI渲染模特穿戴或使用产品的效果
`conceptual_product`	超现实/CGI风格/悬浮/水花/雕塑感产品效果
`restyle`	转换现有图片的美学风格、氛围或季节场景

Mode selection

模式选择

Pick by intent, not surface keyword. When two modes could apply, prefer the more specific one.

product + neutral / clean / white / studio / catalog / Shopify →
```
product_shot
```
product + scene / in use / kitchen / outdoor / cafe / gym →
```
lifestyle_scene
```
hands holding / face with product / beauty application / demonstrating →
```
closeup_product_with_person
```
Pinterest, pin, vertical pin →
```
pinterest_pin
```
hero, banner, website header, landing page, email header, wide format →
```
hero_banner
```
carousel, slide post, multi-slide, swipeable →
```
social_carousel
```
ads, ad pack, paid social, Meta / TikTok / Pinterest ads →
```
ad_creative_pack
```
model wearing, virtual try-on, on body, fashion shoot, lookbook →
```
virtual_model_tryout
```
levitating, floating, splash, frozen motion, surreal, CGI, sculptural →
```
conceptual_product
```
modify EXISTING image's aesthetic, mood, season — without changing subject →
```
restyle
```

Tie-breakers:

"Pinterest pin of my product on a kitchen counter" →
```
pinterest_pin
```
(Pinterest is the platform)
"Hero banner showing my product in use" →
```
hero_banner
```
(banner format wins)
"Carousel of my product in different scenes" →
```
social_carousel
```
(multi-slide wins)
"Closeup of person applying my serum" →
```
closeup_product_with_person
```
(specific genre wins)

根据用户意图而非表面关键词选择模式。当两个模式均可适用时，优先选择更具体的模式。

产品 + 中性/干净/白色/棚拍/商品目录/Shopify →
```
product_shot
```
产品 + 场景/使用中/厨房/户外/咖啡馆/健身房 →
```
lifestyle_scene
```
人手持有/带产品的面部/美妆涂抹/演示操作 →
```
closeup_product_with_person
```
Pinterest、图钉、竖版图钉 →
```
pinterest_pin
```
主视觉、横幅、网站页眉、着陆页、邮件页眉、宽幅 →
```
hero_banner
```
轮播图、幻灯片帖子、多幻灯片、可滑动 →
```
social_carousel
```
广告、广告包、付费社交、Meta/TikTok/Pinterest广告 →
```
ad_creative_pack
```
模特穿戴、虚拟试穿、上身效果、时尚拍摄、Lookbook →
```
virtual_model_tryout
```
悬浮、漂浮、水花、定格动态、超现实、CGI、雕塑感 →
```
conceptual_product
```
修改现有图片的美学风格、氛围、季节——不改变主体 →
```
restyle
```

平局判定规则：

「我的产品在厨房台面上的Pinterest图钉」→
```
pinterest_pin
```
（平台属性优先）
「展示产品使用场景的主视觉横幅」→
```
hero_banner
```
（横幅格式优先）
「产品在不同场景下的轮播图」→
```
social_carousel
```
（多幻灯片属性优先）
「人手涂抹精华液的特写」→
```
closeup_product_with_person
```
（特定类型优先）

Pre-generation interview

生成前问询

Ask 3–4 short questions before submitting. Always labeled options, never open-ended. Skip a question whose answer is obvious from context.

提交前询问3–4个简短问题，始终使用带标签的选项，切勿采用开放式问题。若答案可从上下文明确，则跳过对应问题。

Type A — uploaded a product photo, "make me images / photoshoots"

A类 — 已上传产品照片，需求为「生成图片/拍摄效果」

How many?
```
[1 / 3 / 5]
```

What style/mood?

[Clean studio / Lifestyle / Conceptual / With a model / Other]

Where will you use them?

[Shopify / Instagram / Pinterest / Paid ads / Website hero]

Brand colors to match? (skip if obvious)

需要生成多少张？
```
[1 / 3 / 5]
```

风格/氛围？

[干净棚拍 / 生活场景 / 概念风格 / 带模特 / 其他]

使用场景？

[Shopify / Instagram / Pinterest / 付费广告 / 网站主视觉]

需匹配的品牌颜色？（若明确则跳过）

Type B — uploaded a product photo, named a use case

B类 — 已上传产品照片，指定了使用场景

E.g. "make ads for my product", "make a Pinterest pin", "make a hero banner". Mode is obvious. Ask only the gaps:

How many? (if multi-output mode)
What's the offer / mood / hook?
Anything in particular to emphasize?

例如「为我的产品制作广告」「制作Pinterest图钉」「制作主视觉横幅」。模式已明确，仅询问缺失信息：

需要生成多少张？（若为多输出模式）
卖点/氛围/钩子？
需特别强调的内容？

Type C — text only, no product photo

C类 — 仅文本，无产品照片

Can you upload a product photo? (preferred — much higher fidelity)
If not, describe the product — category, packaging, color, distinctive features.
What style? (same options as Type A)
Where will you use it?

是否可以上传产品照片？（优先推荐——生成效果保真度更高）
若无法上传，请描述产品——品类、包装、颜色、特色功能。
风格？（与A类选项相同）
使用场景？

Type D — uploaded existing image, "redo / change vibe / different version"

D类 — 已上传现有图片，需求为「重做/改变氛围/不同版本」

→

restyle

What aesthetic?

[Clean girl / Cottagecore / Quiet luxury / Dark academia / Y2K / Other]

Seasonal context?

[Christmas / Valentine's / Halloween / Black Friday / None]

What to preserve, what to change? (only if ambiguous)

→ 选择

restyle

模式

目标美学风格？

[Clean girl / Cottagecore / Quiet luxury / Dark academia / Y2K / 其他]

季节场景？

[圣诞 / 情人节 / 万圣节 / 黑五 / 无]

需保留和修改的内容？（仅当需求模糊时询问）

Type E — model wearing a product (fashion, accessories)

E类 — 模特穿戴产品（时尚、配饰类）

→

virtual_model_tryout

Model archetype? (suggest 2–3 based on brand audience)

Environment?

[Studio clean / Outdoor natural / Street style / Editorial / Home cozy]

Framing?

[Full body / Three-quarter / Waist up / Closeup on product area]

→ 选择

virtual_model_tryout

模式

模特类型？（根据品牌受众推荐2–3种）

环境？

[干净棚拍 / 户外自然 / 街头风格 / 时尚大片 / 居家温馨]

取景？

[全身 / 四分之三身 / 腰部以上 / 产品区域特写]

Type F — vague request, unclear subject

F类 — 需求模糊，主题不明确

E.g. "make me something cool for my brand".

What product or topic?

Goal?

[Sell on a marketplace / Build awareness / Run paid ads / Update website]

Upload a reference image?

After answers → return to the relevant Type A–E.

例如「为我的品牌制作一些酷炫内容」。

产品或主题是什么？

目标？

[在电商平台销售 / 提升品牌知名度 / 投放付费广告 / 更新网站]

是否可以上传参考图片？

获取答案后 → 回到对应的A–E类流程。

Generation

生成操作

Single command. Backend assembles the final prompt and submits to

gpt_image_2

. URLs print on stdout.

bash

higgsfield product-photoshoot create \
  --mode <mode> \
  --prompt "<short user-intent description from interview answers>" \
  [--image <path-or-upload-id>]... \
  [--count <1-10>] \
  [--aspect_ratio <override>]

Examples:

bash

higgsfield product-photoshoot create \
  --mode lifestyle_scene \
  --prompt "bottle of cold-brew on a sunlit kitchen counter, IG feed" \
  --image bottle.jpg \
  --count 3

bash

higgsfield product-photoshoot create \
  --mode pinterest_pin \
  --prompt "vertical pin for my candle brand, cottagecore mood" \
  --image candle.jpg

bash

higgsfield product-photoshoot create \
  --mode restyle \
  --prompt "Christmas version, quiet-luxury aesthetic" \
  --image existing-shot.jpg

执行单一命令即可。后端组装最终提示词并提交至

gpt_image_2

，URL会输出至标准输出。

bash

higgsfield product-photoshoot create \
  --mode <mode> \
  --prompt "<从问询答案中提取的简短用户意图描述>" \
  [--image <路径或上传ID>]... \
  [--count <1-10>] \
  [--aspect_ratio <自定义值>]

示例：

bash

higgsfield product-photoshoot create \
  --mode lifestyle_scene \
  --prompt "冷萃咖啡瓶置于阳光照射的厨房台面上，用于IG动态" \
  --image bottle.jpg \
  --count 3

bash

higgsfield product-photoshoot create \
  --mode pinterest_pin \
  --prompt "蜡烛品牌的竖版图钉，Cottagecore氛围" \
  --image candle.jpg

bash

higgsfield product-photoshoot create \
  --mode restyle \
  --prompt "圣诞版本，Quiet luxury美学风格" \
  --image existing-shot.jpg

Image inputs

图片输入

--image

accepts a local file path (auto-uploaded) OR an existing upload UUID. Repeat the flag for multiple references.

--image

参数接受本地文件路径（自动上传）或已有的上传UUID。可重复添加该参数以使用多张参考图片。

Multi-variant

多变体生成

--count 3

returns 3 distinct image URLs. Backend asks the enhancer to vary preset, lighting, angle, and palette across variants — they will not be paraphrased copies of one another.

For

social_carousel

and

ad_creative_pack

, count = number of slides / variants in the pack. Backend locks the visual system across all slides automatically.

--count 3

会返回3个不同的图片URL。后端会让优化器在预设、光线、角度和调色板上生成变体——它们不会是单一图片的重复改写版本。

对于

social_carousel

和

ad_creative_pack

模式，count值等于轮播幻灯片/广告变体的数量。后端会自动锁定所有幻灯片的视觉系统一致性。

Aspect ratio

宽高比

Backend picks a sensible default per mode. Override with

--aspect_ratio

only if the user explicitly asks for a different one. Allowed values:

1:1

4:5

5:4

3:4

4:3

2:3

3:2

9:16

16:9

后端会根据模式选择合理的默认宽高比。仅当用户明确要求时，才通过

--aspect_ratio

参数自定义。允许的值：

1:1

4:5

5:4

3:4

4:3

2:3

3:2

9:16

16:9

。

Delivering results

结果交付

Print the image URLs as a short bulleted list. No JSON, no IDs, no internal model names, no enhanced prompt text. If a job failed, mention it briefly with the failure status.

3 lifestyle shots ready:
- https://cdn.higgsfield.ai/.../job_abc.jpg
- https://cdn.higgsfield.ai/.../job_def.jpg
- https://cdn.higgsfield.ai/.../job_ghi.jpg

将图片URL以简短的项目符号列表形式输出。不要输出JSON、ID、内部模型名称或优化后的提示词文本。若任务失败，请简要提及失败状态。

3张生活场景图已生成：
- https://cdn.higgsfield.ai/.../job_abc.jpg
- https://cdn.higgsfield.ai/.../job_def.jpg
- https://cdn.higgsfield.ai/.../job_ghi.jpg

What this skill does NOT do

该技能不支持的操作

Does not write gpt_image_2 prompts directly. Backend owns prompt assembly.
Does not auto-pick a different image-gen model. Always
```
gpt_image_2
```
.
Does not replace
```
higgsfield-generate
```
Marketing Studio for branded video / avatar workflows.
Does not replace
```
higgsfield-generate
```
for raw text-to-image without a product or brand context.

不直接编写gpt_image_2提示词，提示词组装由后端负责。
不会自动切换其他图像生成模型，始终使用
```
gpt_image_2
```
。
无法替代higgsfield-generate的Marketing Studio处理品牌视频/虚拟形象工作流。
无法替代higgsfield-generate处理无产品或品牌背景的纯文本转图片需求。

Common mistakes to avoid

需避免的常见错误

Asking more than 4 interview questions in a single message.
Picking the wrong mode (e.g.
```
product_shot
```
when the user wants a Pinterest pin).
Calling
```
higgsfield generate create gpt_image_2 --prompt ...
```
directly instead of
```
higgsfield product-photoshoot create
```
— bypasses the prompt enhancer and produces noticeably worse output.
Pasting the assembled prompt back to the user — they want the URLs.
Using a
```
--mode
```
value not in the table above.

单次消息中询问超过4个问题。
选择错误模式（例如用户需要Pinterest图钉时选择
```
product_shot
```
）。
直接调用
```
higgsfield generate create gpt_image_2 --prompt ...
```
而非
```
higgsfield product-photoshoot create
```
——这会绕过提示词优化器，导致输出质量明显下降。
将组装后的提示词返回给用户——用户需要的是图片URL。
使用上述表格之外的
```
--mode
```
值。