npx claudepluginhub nityeshaga/claude-home-base --plugin more-aiThis skill uses the workspace's default tool permissions.
Generate and edit images using Google's Gemini API.
Generates and edits images using Google's Gemini Nano Banana Pro model (gemini-3-pro-image-preview) via bash API calls. Supports logos, product mockups, photo edits; requires GEMINI_API_KEY.
Generates and edits images via Gemini API Python SDK. For text-to-image, editing, style transfers, logos, stickers, mockups, multi-turn refinement, and image composition.
Generates AI images from text prompts, edits images, and composes from multiple references using Gemini models. Supports t2i, i2i, product mockups, and stickers.
Share bugs, ideas, or general feedback.
Generate and edit images using Google's Gemini API.
Check if GEMINI_API_KEY is set in the environment. If not present, ask the user to configure it:
GEMINI_API_KEY=your_key_here in the Environment variables dialogUse the venv Python for all script invocations. The scripts require Python 3.10+ with google-genai and Pillow:
SCRIPTS_DIR="${CLAUDE_PLUGIN_ROOT}/skills/gemini-imagegen/scripts"
PYTHON="${SCRIPTS_DIR}/.venv/bin/python3"
If the venv doesn't exist yet, create it:
python3.12 -m venv "${SCRIPTS_DIR}/.venv"
"${SCRIPTS_DIR}/.venv/bin/pip" install google-genai Pillow
Use these scripts for all image generation tasks. Always invoke with $PYTHON (the venv python from above):
Use when: User wants to create a new image from a text description
$PYTHON "${SCRIPTS_DIR}/generate_image.py" "prompt" output.png [--model MODEL] [--aspect RATIO] [--size SIZE]
Use when: User wants to edit or transform an existing image
$PYTHON "${SCRIPTS_DIR}/edit_image.py" input.png "instruction" output.png [--model MODEL] [--aspect RATIO] [--size SIZE]
Use when: User wants to merge elements from multiple images (up to 14)
$PYTHON "${SCRIPTS_DIR}/compose_images.py" "instruction" output.png image1.png [image2.png ...] [--model MODEL] [--aspect RATIO] [--size SIZE]
Use when: User wants to refine an image through multiple rounds of feedback
$PYTHON "${SCRIPTS_DIR}/multi_turn_chat.py" [--model MODEL] [--output-dir DIR]
| Option | Values |
|---|---|
--model | gemini-3.1-flash-image-preview (default, fastest, best instruction following), gemini-3-pro-image-preview (fallback / best quality, text rendering, 4K), gemini-2.5-flash-image (stable/GA, legacy) |
Model selection: Try gemini-3.1-flash-image-preview first (fastest, great quality). If it fails or the result is unsatisfactory (e.g., poor text rendering, complex composition), fall back to gemini-3-pro-image-preview which produces studio-quality output at the cost of speed.
| --aspect | 1:1, 1:4, 1:8, 2:3, 3:2, 3:4, 4:1, 4:3, 4:5, 5:4, 8:1, 9:16, 16:9, 21:9 |
| --size | 512 (3.1 flash only), 1K, 2K, 4K (pro only) |
Use when: User wants to remove the background from an image (uses macOS Shortcuts)
$PYTHON "${SCRIPTS_DIR}/remove_bg.py" input.jpg [output.png]
If no output path is given, saves to input_nobg.png in the same folder. Requires a one-time setup of a macOS Shortcut named "Remove Background" — the script will print setup instructions if the shortcut is missing.
Write prompts like Midjourney experts - be detailed and specific:
"A photorealistic close-up portrait, 85mm lens, soft golden hour light, shallow depth of field"
"A kawaii-style sticker of a happy red panda, bold outlines, cel-shading, white background"
"Logo with text 'Daily Grind' in clean sans-serif, black and white, coffee bean motif"
"Studio-lit product photo on polished concrete, three-point softbox setup, 45-degree angle"