gemini-image-generator

# Gemini Image Generator Generate images from text prompts via CLI using Google Gemini APIs. Supports model selection between fast (`gemini-2.5-flash-image`) and quality (`gemini-3-pro-image-preview`) models, batch generation, watermark removal, and background transparency. ## Reference Loading Table | Signal | Load These Files | Why | |---|---|---| | tasks related to this reference | `prompts.md` | Loads detailed guidance from `prompts.md`. | ## Instructions ### Step 1: Validate Environment Verify the API key exists before any generation attempt -- a missing key produces confusing errors that waste time debugging. ```bash echo "GEMINI_API_KEY is ${GEMINI_API_KEY:+set}" ``` Expect: `GEMINI_API_KEY is set`. If not set, instruct user to configure it and stop. Verify Python dependencies are available: ```bash python3 -c "from google import genai; from PIL import Image; print('OK')" ``` If missing, install: ```bash pip install google-genai Pillow ``` Determine the output path. Always use absolute paths for output files -- relative paths break when scripts run in different working directories. Verify the parent directory exists or will be created. **Proceed only when**: API key is set, dependencies installed, output path is valid. ### Step 2: Select Model and Compose Prompt Choose the model based on the use case: | Scenario | Model | Why | |----------|-------|-----| | Iterating on prompt, drafts | `gemini-2.5-flash-image` | Fast feedback (2-5s) | | Final quality as...