feat: update OpenRouter model handling and enhance documentation

Author: nblog

skills/nano-banana-pro-openrouter/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: nano-banana-pro-openrouter
-description: 'Generate or edit images via OpenRouter with the Gemini 3 Pro Image model. Use for prompt-only image generation, image edits, and multi-image compositing; supports 1K/2K/4K output.'
+description: 'Generate or edit images via OpenRouter image generation models (default: google/gemini-3-pro-image-preview). Use for prompt-only image generation, image edits, and multi-image compositing; supports 1K/2K/4K output.'
 metadata:
   emoji: 🍌
   requires:
@@ -16,7 +16,7 @@ metadata:
 
 ## Overview
 
-Generate or edit images with OpenRouter using the `google/gemini-3-pro-image-preview` model. Support prompt-only generation, single-image edits, and multi-image composition.
+Generate or edit images with OpenRouter using `google/gemini-3-pro-image-preview` as the default model. It supports prompt-only generation, single-image edits, and multi-image composition.
 
 ### Prompt-only generation
 
@@ -50,6 +50,11 @@ uv run {baseDir}/scripts/generate_image.py \
 - Use `--resolution` with `1K`, `2K`, or `4K`.
 - Default is `1K` if not specified.
 
+## Model selection
+
+- Use `--model <name>` only to override the default.
+- Default model is `google/gemini-3-pro-image-preview`.
+
 ## System prompt customization
 
 The skill reads an optional system prompt from `assets/SYSTEM_TEMPLATE`. This allows you to customize the image generation behavior without modifying code.

skills/nano-banana-pro-openrouter/scripts/generate_image.py

@@ -19,6 +19,7 @@
 
 
 # Configuration
+DEFAULT_MODEL = "google/gemini-3-pro-image-preview"
 MAX_INPUT_IMAGES = 3
 MIME_TO_EXT = {
     "image/png": ".png",
@@ -45,6 +46,11 @@ def parse_args():
       default=[],
       help=f"Optional input image path (repeatable, max {MAX_INPUT_IMAGES}).",
     )
+    parser.add_argument(
+        "--model",
+        default=DEFAULT_MODEL,
+        help=f"OpenRouter model to use. Defaults to {DEFAULT_MODEL}.",
+    )
     return parser.parse_args()
 
 
@@ -150,7 +156,7 @@ def main():
     })
 
     response = client.chat.completions.create(
-        model="google/gemini-3-pro-image-preview",
+        model=args.model,
         messages=messages,
         extra_body={
             "modalities": ["image", "text"],