From nano-banana-ultimate
Generates AI product photography including shots, still lifes, packaging mockups, food images, and object compositions with studio lighting using Gemini. Triggers on product photo requests.
How this skill is triggered — by the user, by Claude, or both
Slash command
/nano-banana-ultimate:banana-objectsThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
**Input:** `$ARGUMENTS` (optional — product description and intended use)
Input: $ARGUMENTS (optional — product description and intended use)
If $ARGUMENTS is provided, use it as the product brief and skip to prompt building. If empty, ask about the product and context.
uv installedGEMINI_API_KEY environment variable set (get one at https://aistudio.google.com/apikey)[Object with Material Description] + [Resting/Floating on Surface] + [Studio or Lifestyle Setting] + [Center-Weighted Hero Composition] + [Studio Photography, Controlled Lighting]
| Domain | Aspect Ratio | Resolution |
|---|---|---|
| E-commerce catalog | 1:1 | 2K |
| Instagram product | 4:5 | 2K |
| Lifestyle context | 4:3 | 2K |
Lighting guidance: Use soft diffused studio lighting as the default. Switch to backlit setups for glass and translucent materials to emphasize clarity and refraction.
uv run "${CLAUDE_PLUGIN_ROOT}/scripts/banana.py" \
--prompt "<detailed prompt following the formula>" \
--output "<YYYY-MM-DD-HH-MM-SS-descriptive-name>.png" \
--resolution 2K \
--aspect-ratio <ratio from Domain Defaults> \
--model gemini-3-pro-image-preview
When the user provides an existing product photo to modify (e.g., change background, adjust lighting, add props):
uv run "${CLAUDE_PLUGIN_ROOT}/scripts/banana.py" \
--prompt "<edit instruction: what to change AND what to keep>" \
--output "<YYYY-MM-DD-HH-MM-SS-descriptive-name>.png" \
--input-image "/path/to/source.png" \
--resolution 2K \
--aspect-ratio <ratio>
For edits, describe both the change and what must stay identical:
"Replace the white background with a lifestyle scene on a rustic wooden table with warm morning light. Keep the product, its label, color, and proportions exactly the same."
Up to 14 input images can be passed (repeat --input-image for each).
See references/prompts.md for ready-to-use example prompts covering common product photography scenarios.
npx claudepluginhub agentic-dev3o/devx-plugins --plugin nano-banana-ultimatePlans and executes product photography for e-commerce, advertising, or catalog use. Follows ASMP commercial standards and Amazon image requirements to improve conversion rates.
Generates brand-quality product images via Higgsfield CLI using GPT Image 2. Supports modes for product shots, lifestyle scenes, ad creatives, and social media visuals.
Generates 5 professional ad photography styles (Studio, Floating, Ingredient, In Use, Lifestyle) from a product image or description using banana-claude image generation. Outputs 1:1 and 9:16 sizes for Meta/LinkedIn and TikTok/Reels/Stories.