npx claudepluginhub agentic-dev3o/devx-plugins --plugin nano-banana-ultimateThis skill is limited to using the following tools:
**Input:** `$ARGUMENTS` (optional — subject description and scene)
Generates or edits images via Google Gemini from text prompts or up to 14 reference images for text-to-image and multi-image editing.
Generates optimized prompts for Gemini 2.5 Flash Image (Nano Banana) using best practices for photorealistic shots, art styles, and multi-turn editing workflows.
Generates humanized, realistic images via Google AI Studio (Gemini) in influencer or educational styles with natural lighting and subtle imperfections. Activates on image generation requests.
Share bugs, ideas, or general feedback.
Input: $ARGUMENTS (optional — subject description and scene)
If $ARGUMENTS is provided, use it as the portrait brief and skip to prompt building. If empty, ask about the subject and setting.
uv installedGEMINI_API_KEY environment variable set (get one at https://aistudio.google.com/apikey)Build every people/portrait prompt using this structure:
[Person: age/build/expression/clothing] + [Natural Action/Pose] + [Real-World Environment] + [Portrait Framing + Rule of Thirds] + [Natural Light Photography, specific lens]
| Domain | Aspect Ratio | Lens | Notes |
|---|---|---|---|
| Headshot | 3:4 | 85mm f/1.4 | Tight crop, shallow depth of field, subject fills frame |
| Editorial / Lifestyle | 3:2 | 35mm f/2.0 | Environmental context, wider framing |
| Group scene / Team | 16:9 | 24mm f/4.0 | Deep focus, everyone sharp |
| Resolution | 2K | All people domains default to 2K | |
| Lighting | Natural window light or golden hour | Soft, flattering, directional |
uv run "${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> \
--model gemini-3-pro-image-preview
When the user provides an existing photo to modify (e.g., change background, adjust lighting, swap clothing):
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:
"Change the background to a warm golden-hour park scene. Keep the subject's face, expression, clothing, and pose 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 headshots, lifestyle, editorial, group, and environmental portrait scenarios.