Nano Banana Pro 2 Image Generation & Editing (OpenRouter)

Generate new images or edit existing ones using Gemini 3.1 Flash Image Preview via OpenRouter.

Usage

Run the script using absolute path (do NOT cd to skill directory first):

Generate new image:
CODEBLOCK0

Edit existing image:
CODEBLOCK1

Important: Always run from the user's current working directory so images are saved where the user is working, not in the skill directory.

Default Workflow (draft → iterate → final)

Goal: fast iteration without burning time on 4K until the prompt is correct.

• - Draft (1K): quick feedback loop

- uv run {baseDir}/scripts/generate_image.py --prompt "<draft prompt>" --filename "yyyy-mm-dd-hh-mm-ss-draft.png" --resolution 1K

• - Iterate: adjust prompt in small diffs; keep filename new per run

- If editing: keep the same --input-image for every iteration until you're happy.

• - Final (4K): only when prompt is locked

- INLINECODE2

Resolution Options

Supported resolutions (uppercase K required):

• - 0.5K - ~512px resolution (fast drafts, OpenRouter/Gemini 3.1 Flash exclusive)
• 1K (default) - ~1024px resolution
• 2K - ~2048px resolution
• 4K - ~4096px resolution

Map user requests to API parameters:

• - No mention of resolution → INLINECODE3
• "quick draft", "thumbnail", "0.5K" → INLINECODE4
• "low resolution", "1080", "1080p", "1K" → INLINECODE5
• "2K", "2048", "normal", "medium resolution" → INLINECODE6
• "high resolution", "high-res", "hi-res", "4K", "ultra" → INLINECODE7

API Key

The script checks for API key in this order:

1. 1. --api-key argument (use if user provided key in chat)
2. INLINECODE9 environment variable

If neither is available, the script exits with an error message.

Preflight + Common Failures (fast fixes)

• - Preflight:

- command -v uv (must exist) - test -n "$OPENROUTER_API_KEY" (or pass --api-key) - If editing: INLINECODE13

• - Common failures:

- Error: No API key provided. → set OPENROUTER_API_KEY or pass --api-key - Error loading input image: → wrong path / unreadable file; verify --input-image points to a real image - "quota/permission/403" style API errors → wrong key, no access, or quota exceeded; try a different key/account - Error: API request timed out → simplify the prompt or reduce resolution

Filename Generation

Generate filenames with the pattern: INLINECODE20

Format: {timestamp}-{descriptive-name}.png

• - Timestamp: Current date/time in format yyyy-mm-dd-hh-mm-ss (24-hour format)
• Name: Descriptive lowercase text with hyphens
• Keep the descriptive part concise (1-5 words typically)
• Use context from user's prompt or conversation
• If unclear, use random identifier (e.g., x9k2, a7b3)

Examples:

• - Prompt "A serene Japanese garden" → INLINECODE25
• Prompt "sunset over mountains" → INLINECODE26
• Prompt "create an image of a robot" → INLINECODE27
• Unclear context → INLINECODE28

Image Editing

When the user wants to modify an existing image:

1. 1. Check if they provide an image path or reference an image in the current directory
2. Use --input-image parameter with the path to the image
3. The prompt should contain editing instructions (e.g., "make the sky more dramatic", "remove the person", "change to cartoon style")
4. Common editing tasks: add/remove elements, change style, adjust colors, blur background, etc.

Prompt Handling

For generation: Pass user's image description as-is to --prompt. Only rework if clearly insufficient.

For editing: Pass editing instructions in --prompt (e.g., "add a rainbow in the sky", "make it look like a watercolor painting")

Preserve user's creative intent in both cases.

Prompt Templates (high hit-rate)

Use templates when the user is vague or when edits must be precise.

• - Generation template:

- "Create an image of: . Style: