higgsfield-product-photoshoot Skill: AI Product Photos in 10 Styles

Makes your agent create brand-quality product images in 10 styles, from studio shots and lifestyle scenes to ad packs, using Higgsfield.

Installs: 204.8K; on skills.sh
Stars: 1.8K; on GitHub
Updated: Oct 2026; last repo commit

You give it a product photo and say what you need. The skill asks up to four short multiple-choice questions, picks one of 10 modes, and runs higgsfield product-photoshoot create. A Higgsfield backend writes the final image prompt, so the agent does not freehand it. Image links come back in a short list.

You can ask for 1 to 10 images per run, and every job uses 2k resolution. A Higgsfield account and the higgsfield CLI are required. If the CLI is missing the skill installs it, and if you are logged out it asks you to sign in.

Good for

Shop owners who need product photos without a shoot
Marketers making Pinterest pins, hero banners and paid social creatives
Fashion brands trying virtual model try-ons

Install higgsfield-product-photoshoot

Claude Code

Copy this prompt.

Install the higgsfield-product-photoshoot skill in Claude Code. Run this command:

npx skills add https://github.com/higgsfield-ai/skills --skill higgsfield-product-photoshoot

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js.

From its listing on skills.sh. Source.

What's in the skill

When it loads

Generate brand-quality product images through Higgsfield product-photoshoot prompt enhancement on GPT Image 2 / gpt_image_2. Entry point for professional brand/product visuals. Use when: "product photo", "studio shot", "lifestyle image", "Pinterest pin", "hero/banner", "carousel", "ad creative", "Meta ads", "virtual try-on", "model wearing", "person holding product", "closeup with hands", "levitating/floating/splash product", "CGI/surreal product", "restyle", "seasonal/aesthetic variation", or any product, brand, or paid-social creative. Modes: product_shot, lifestyle_scene, closeup_product_with_person, moodboard_pin, hero_banner, social_carousel, ad_creative_pack, virtual_model_tryout, conceptual_product, restyle. Backend assembles the final prompt; never freehand it. NOT for: no-product text-to-image (use higgsfield-generate), branded avatar video (use higgsfield-generate Marketing Studio), marketplace listing cards (use higgsfield-marketplace-cards), Soul Character training (use higgsfield-soul-id).

Sections in SKILL.md

Step 0 — Bootstrap
UX Rules
Modes
Mode selection
Pre-generation interview
Type A — uploaded a product photo, "make me images / photoshoots"
Type B — uploaded a product photo, named a use case
Type C — text only, no product photo
Type D — uploaded existing image, "redo / change vibe / different version"
Type E — model wearing a product (fashion, accessories)
Type F — vague request, unclear subject
Generation
Image inputs
Multi-variant
Aspect ratio
Resolution

Key facts

Author: Higgsfield AI
License: MIT, from the crawl of the repo
Installs on skills.sh: 204,761 (Nov 2, 2026)
GitHub stars: 1,843 for the higgsfield-ai/skills repo (Nov 2, 2026)
Last repo commit: Oct 27, 2026
What installs: One SKILL.md; no bundled scripts or reference files
Needs: A Higgsfield account and the higgsfield CLI (the skill installs it if missing)
Works in: Claude Code, Cursor, Codex and other coding agents

What it includes

Installs the higgsfield CLI if missing and asks you to log in if needed
Runs the installer script from the higgsfield-ai/cli repo, then checks account status.
Runs code · Step 0: Bootstrap
Product on a neutral, studio or catalog background
Runs code · product_shot
Product in a real setting with hands, action or atmosphere
Runs code · lifestyle_scene
Tight crop with hands or partial face, such as beauty application
Runs code · closeup_product_with_person
Vertical 2:3 Pinterest-style image
Runs code · moodboard_pin
Wide header image for a website, email or campaign
Runs code · hero_banner
3 to 10 connected slides for Instagram, LinkedIn or Facebook
The backend keeps one visual style across slides.
Runs code · social_carousel
A pack of static ad variants for Meta, TikTok, Pinterest or Google
Runs code · ad_creative_pack
Product worn or used by an AI-rendered model
Runs code · virtual_model_tryout
Surreal, CGI, levitating or splash product shots
Runs code · conceptual_product
Changes the look, mood or season of an existing image
Runs code · restyle
--count 1 to 10, --image reference files, --aspect_ratio override
Local image paths are uploaded automatically. Aspect ratios allowed: 1:1, 4:5, 5:4, 3:4, 4:3, 2:3, 3:2, 9:16, 16:9.
Files · Options

From the official docs

Permissions

Medium risk

The skill runs shell commands, can download an installer, and uploads your photos to Higgsfield. Install the CLI yourself first and use photos you may share.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

It may pipe a downloaded installer into your shell
If the higgsfield command is missing, SKILL.md has the agent run `curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh`, which pipes a script from the main branch of another repository into your shell. Install the CLI yourself first if you prefer to review it. github.com
Your product photos are uploaded to Higgsfield
Local image paths passed with --image are uploaded automatically. Do not point it at private images.
Jobs run on your Higgsfield account
SKILL.md does not state what jobs cost or whether they use credits. Check your Higgsfield plan before asking for up to 10 images per run.

Technical details

Talks to	Higgsfield API. raw.githubusercontent.com (CLI installer)

Questions

What does higgsfield-product-photoshoot do?

It generates product and brand images in one of 10 modes, using a Higgsfield backend that builds the prompt from photography templates. You get back image links.

How do I install it in Claude Code, Cursor or Codex?

Use the install box above. The Higgsfield README also lists a Claude Code plugin, gh skill install and a setup script, all of which handle the CLI and sign-in.

Do I need to upload a product photo?

It is preferred. The skill asks for one first because fidelity is much higher. Without it, you describe the product by category, packaging, colour and features.

Does it need an API key or account?

It needs a Higgsfield account and sign-in through higgsfield auth login. The SKILL.md mentions no separate API key.

Is it safe?

It runs shell commands, can pipe a downloaded installer script into your shell, and uploads your product photos to Higgsfield. Use photos you are allowed to share.

How is it different from higgsfield-generate?

This one is only for brand and product images. The SKILL.md sends text-to-image without a product, and branded avatar video, to higgsfield-generate.

Information

updated Nov 2, 2026

Repository: higgsfield-ai/skills
Folder: higgsfield-product-photoshoot

higgsfield-ai/skills skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 2

higgsfield-ai/skills higgsfield-product-photoshoot SKILL.md · github.com
higgsfield-ai/skills README · github.com