Use when the user wants professional brand-quality product images via Higgsfield's
mode-specific prompt enhancement pipeline. Entry point for any product visual
with a specific format or platform target.
Use whenever: "product photoshoot", "lifestyle product shots", "Pinterest pin",
"hero banner", "ad pack", "virtual try-on", "studio shot", "carousel images",
"Meta ads creative", "model wearing product", "levitating product", "splash shot",
"CGI style product", "restyle product image", Shopify image, brand campaign visual.
10 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 prompt — never call gpt_image_2 directly for product shots.
NOT for: one-off images without a product (use image-gen), branded video with
avatars (use higgsfield-generate), Soul training (use higgsfield-soul-id).
Requires Higgsfield CLI and authed account.
Instrucciones de origen · Vista previa de solo lectura
name
higgsfield-product-photoshoot
version
0.3.0
description
Use when the user wants professional brand-quality product images via Higgsfield's
mode-specific prompt enhancement pipeline. Entry point for any product visual
with a specific format or platform target.
Use whenever: "product photoshoot", "lifestyle product shots", "Pinterest pin",
"hero banner", "ad pack", "virtual try-on", "studio shot", "carousel images",
"Meta ads creative", "model wearing product", "levitating product", "splash shot",
"CGI style product", "restyle product image", Shopify image, brand campaign visual.
10 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 prompt — never call gpt_image_2 directly for product shots.
NOT for: one-off images without a product (use image-gen), branded video with
avatars (use higgsfield-generate), Soul training (use higgsfield-soul-id).
Requires Higgsfield CLI and authed account.
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.
When to use
Any product visual with a specific output format: studio shot, Pinterest pin, hero banner, ad pack, carousel, model try-on
User has a product photo and wants it adapted to a specific marketing context
"make ads for my product", "make a hero banner", "create carousel images"
"virtual try-on", "model wearing my jacket", "levitating product shot"
Paid social creative packs (Meta, TikTok, Pinterest, Google Ads)
Route elsewhere if:
No product, no brand context, just a generic image prompt → image-gen (Gemini, free, faster)
User needs a branded video ad with an avatar → higgsfield-generate (Marketing Studio)
User wants to train a reusable face identity → higgsfield-soul-id
User needs general-purpose AI image/video generation → higgsfield-generate
On Activation
Read brand/voice-profile.md and brand/creative-kit.md if present. Use brand colors, aesthetic language (creative-kit.md > ## Visual Brand Style, written by /visual-style), and platform preferences to inform mode selection and interview answers.
Check CLI: higgsfield account status. If not on $PATH, surface install command. If session expired, prompt auth.
Run the pre-generation interview (see below) — at most 4 questions before submitting.
Optional dependency — Higgsfield account
This skill requires the @higgsfield/cli binary and a Higgsfield account.
Without the CLI installed, return a clear actionable error:
higgsfield CLI not found. Install with:
curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh
Then authenticate:
higgsfield auth login
Without an authed Higgsfield account, the CLI itself surfaces the auth prompt — no special handling needed in the skill.
Fallback for image generation only: if the user just needs a one-off image and doesn't have a Higgsfield account, route them to (Gemini, model , free tier). The product-photoshoot mode enhancer and all product-specific modes require Higgsfield.
image-gen
gemini-3.1-flash-image-preview
Step 0 — Bootstrap
Before any other command:
If higgsfield is not on $PATH, install it:
curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh
If higgsfield account status fails with Session expired / Not authenticated, ask the user to run higgsfield auth login (interactive) and wait for confirmation.
UX Rules
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.
Modes
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
--image accepts a local file path (auto-uploaded) OR an existing upload UUID. Repeat the flag for multiple references.
Multi-variant
--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.
Aspect ratio
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.
Resolution
Use 2k for every product-photoshoot job.
Delivering results
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.
