{"skill":{"slug":"higgsfield-product-photoshoot","displayName":"Higgsfield Product Photoshoot","summary":"Generate brand-quality product images via mode-specific prompt enhancement on Higgsfield's gpt_image_2 model. The single entry point for any professional bra...","description":"---\nversion: 0.3.0\nname: higgsfield-product-photoshoot\ndescription: |\n  Generate brand-quality product images via mode-specific prompt\n  enhancement on Higgsfield's gpt_image_2 model. The single entry\n  point for any professional brand visual involving a product.\n  Use when: \"make a product photo\", \"studio shot\", \"lifestyle photo\",\n  \"in use\", \"Pinterest pin\", \"hero banner\", \"website header\",\n  \"carousel\", \"Meta ads\", \"ad creatives\", \"model wearing\",\n  \"virtual try-on\", \"person holding product\", \"closeup with hands\",\n  \"levitating product\", \"floating\", \"splash shot\", \"CGI style\",\n  \"surreal product\", \"restyle\", \"Christmas version\",\n  \"in [aesthetic] style\", or any request involving a product, brand,\n  or paid social creative.\n  Modes: product_shot, lifestyle_scene, closeup_product_with_person,\n  pinterest_pin, hero_banner, social_carousel, ad_creative_pack,\n  virtual_model_tryout, conceptual_product, restyle.\n  Backend assembles the final prompt — never write gpt_image_2\n  prompts freehand. Always go through this skill.\n  NOT for: raw text-to-image with no brand/product (use\n  higgsfield-generate), branded marketing video with avatars (use\n  higgsfield-generate's Marketing Studio), Soul Character training\n  (use higgsfield-soul-id).\nargument-hint: \"[--mode <mode>] [--count N] [prompt]\"\nallowed-tools: Bash\n---\n\n# Product Photoshoot\n\nBrand-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.\n\n## Step 0 — Bootstrap\n\nBefore any other command:\n\n1. If `higgsfield` is not on `$PATH`, install it:\n   ```bash\n   curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh\n   ```\n2. If `higgsfield account status` fails with `Session expired` / `Not authenticated`, ask the user to run `higgsfield auth login` (interactive) and wait for confirmation.\n\n## UX Rules\n\n1. Be concise. Print only image URLs in the final reply.\n2. Detect language, respond in it. Mode names and CLI flags stay English.\n3. Ask at most 4 short questions before submitting. Use labeled options, never open-ended.\n4. Skip questions whose answer is obvious from context (uploaded image, prior turn, brand memory).\n5. Never write the gpt_image_2 prompt yourself — backend assembles it.\n6. Polling is silent. Wait until URLs are ready, then deliver.\n\n## Modes\n\n| Mode | When user wants… |\n|---|---|\n| `product_shot` | Product on neutral / studio / catalog background |\n| `lifestyle_scene` | Product in real-world environment, hands, action, atmosphere |\n| `closeup_product_with_person` | Tight crop with hands / partial face — beauty application, holding, demonstrating |\n| `pinterest_pin` | Vertical 2:3 Pinterest-native aesthetic, moodboard feel |\n| `hero_banner` | Wide-format website / email / campaign header |\n| `social_carousel` | 3–10 connected slides for IG / LinkedIn / Facebook |\n| `ad_creative_pack` | Coordinated pack of static ad variants for Meta / TikTok / Pinterest / Google Ads |\n| `virtual_model_tryout` | Product worn or used by an AI-rendered model |\n| `conceptual_product` | Surreal / CGI-style / levitating / splash / sculptural product |\n| `restyle` | Transform an existing image's aesthetic, mood, or seasonal context |\n\n## Mode selection\n\nPick by intent, not surface keyword. When two modes could apply, prefer the more specific one.\n\n- product + neutral / clean / white / studio / catalog / Shopify → `product_shot`\n- product + scene / in use / kitchen / outdoor / cafe / gym → `lifestyle_scene`\n- hands holding / face with product / beauty application / demonstrating → `closeup_product_with_person`\n- Pinterest, pin, vertical pin → `pinterest_pin`\n- hero, banner, website header, landing page, email header, wide format → `hero_banner`\n- carousel, slide post, multi-slide, swipeable → `social_carousel`\n- ads, ad pack, paid social, Meta / TikTok / Pinterest ads → `ad_creative_pack`\n- model wearing, virtual try-on, on body, fashion shoot, lookbook → `virtual_model_tryout`\n- levitating, floating, splash, frozen motion, surreal, CGI, sculptural → `conceptual_product`\n- modify EXISTING image's aesthetic, mood, season — without changing subject → `restyle`\n\nTie-breakers:\n- \"Pinterest pin of my product on a kitchen counter\" → `pinterest_pin` (Pinterest is the platform)\n- \"Hero banner showing my product in use\" → `hero_banner` (banner format wins)\n- \"Carousel of my product in different scenes\" → `social_carousel` (multi-slide wins)\n- \"Closeup of person applying my serum\" → `closeup_product_with_person` (specific genre wins)\n\n## Pre-generation interview\n\nAsk 3–4 short questions before submitting. Always labeled options, never open-ended. Skip a question whose answer is obvious from context.\n\n### Type A — uploaded a product photo, \"make me images / photoshoots\"\n\n1. How many? `[1 / 3 / 5]`\n2. What style/mood? `[Clean studio / Lifestyle / Conceptual / With a model / Other]`\n3. Where will you use them? `[Shopify / Instagram / Pinterest / Paid ads / Website hero]`\n4. Brand colors to match? (skip if obvious)\n\n### Type B — uploaded a product photo, named a use case\n\nE.g. \"make ads for my product\", \"make a Pinterest pin\", \"make a hero banner\". Mode is obvious. Ask only the gaps:\n\n1. How many? (if multi-output mode)\n2. What's the offer / mood / hook?\n3. Anything in particular to emphasize?\n\n### Type C — text only, no product photo\n\n1. Can you upload a product photo? (preferred — much higher fidelity)\n2. If not, describe the product — category, packaging, color, distinctive features.\n3. What style? (same options as Type A)\n4. Where will you use it?\n\n### Type D — uploaded existing image, \"redo / change vibe / different version\"\n\n→ `restyle`\n\n1. What aesthetic? `[Clean girl / Cottagecore / Quiet luxury / Dark academia / Y2K / Other]`\n2. Seasonal context? `[Christmas / Valentine's / Halloween / Black Friday / None]`\n3. What to preserve, what to change? (only if ambiguous)\n\n### Type E — model wearing a product (fashion, accessories)\n\n→ `virtual_model_tryout`\n\n1. Model archetype? (suggest 2–3 based on brand audience)\n2. Environment? `[Studio clean / Outdoor natural / Street style / Editorial / Home cozy]`\n3. Framing? `[Full body / Three-quarter / Waist up / Closeup on product area]`\n\n### Type F — vague request, unclear subject\n\nE.g. \"make me something cool for my brand\".\n\n1. What product or topic?\n2. Goal? `[Sell on a marketplace / Build awareness / Run paid ads / Update website]`\n3. Upload a reference image?\n\nAfter answers → return to the relevant Type A–E.\n\n## Generation\n\nSingle command. Backend assembles the final prompt and submits to `gpt_image_2`. URLs print on stdout.\n\n```bash\nhiggsfield product-photoshoot create \\\n  --mode <mode> \\\n  --prompt \"<short user-intent description from interview answers>\" \\\n  [--image <path-or-upload-id>]... \\\n  [--count <1-10>] \\\n  [--aspect_ratio <override>]\n```\n\nExamples:\n\n```bash\nhiggsfield product-photoshoot create \\\n  --mode lifestyle_scene \\\n  --prompt \"bottle of cold-brew on a sunlit kitchen counter, IG feed\" \\\n  --image bottle.jpg \\\n  --count 3\n```\n\n```bash\nhiggsfield product-photoshoot create \\\n  --mode pinterest_pin \\\n  --prompt \"vertical pin for my candle brand, cottagecore mood\" \\\n  --image candle.jpg\n```\n\n```bash\nhiggsfield product-photoshoot create \\\n  --mode restyle \\\n  --prompt \"Christmas version, quiet-luxury aesthetic\" \\\n  --image existing-shot.jpg\n```\n\n## Image inputs\n\n`--image` accepts a local file path (auto-uploaded) OR an existing upload UUID. Repeat the flag for multiple references.\n\n## Multi-variant\n\n`--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.\n\nFor `social_carousel` and `ad_creative_pack`, count = number of slides / variants in the pack. Backend locks the visual system across all slides automatically.\n\n## Aspect ratio\n\nBackend 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`.\n\n## Delivering results\n\nPrint 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.\n\n```\n3 lifestyle shots ready:\n- https://cdn.higgsfield.ai/.../job_abc.jpg\n- https://cdn.higgsfield.ai/.../job_def.jpg\n- https://cdn.higgsfield.ai/.../job_ghi.jpg\n```\n\n## What this skill does NOT do\n\n- Does not write gpt_image_2 prompts directly. Backend owns prompt assembly.\n- Does not auto-pick a different image-gen model. Always `gpt_image_2`.\n- Does not replace `higgsfield-generate` Marketing Studio for branded video / avatar workflows.\n- Does not replace `higgsfield-generate` for raw text-to-image without a product or brand context.\n\n## Common mistakes to avoid\n\n- Asking more than 4 interview questions in a single message.\n- Picking the wrong mode (e.g. `product_shot` when the user wants a Pinterest pin).\n- Calling `higgsfield generate create gpt_image_2 --prompt ...` directly instead of `higgsfield product-photoshoot create` — bypasses the prompt enhancer and produces noticeably worse output.\n- Pasting the assembled prompt back to the user — they want the URLs.\n- Using a `--mode` value not in the table above.\n","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":472,"installsAllTime":18,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1777911676028,"updatedAt":1778492846193},"latestVersion":{"version":"1.0.0","createdAt":1777911676028,"changelog":"Initial release of Higgsfield Product Photoshoot skill.\n\n- Provides a CLI tool to generate brand-quality product images using mode-specific prompt enhancements.\n- Supports multiple generation modes, including studio, lifestyle, Pinterest pin, hero banner, carousel, ad packs, virtual try-on, conceptual, and restyle.\n- Includes an interactive pre-generation interview with concise, labeled questions to refine outputs.\n- Delivers only image URLs as output, with silent polling until results are ready.\n- Not intended for unbranded text-to-image, marketing videos, or Soul Character training.","license":"MIT-0"},"metadata":null,"owner":{"handle":"higgsfield","userId":"s17f8fwnpnszqskag8vjqhx1ts862976","displayName":"Yerzat Dulat","image":"https://avatars.githubusercontent.com/u/24421551?v=4"},"moderation":null}