Nano Banana 2 Direct

Generate/edit images with Gemini 3.1 Flash Image Preview (Nano Banana 2). Direct API call without inference.sh dependency. Use for image create/modify reques...

Security Scan

The skill's requirements and instructions line up with its stated purpose (direct Gemini image generation); it asks only for a Gemini API key and uses standard Python libraries, with no signs of unrelated access or data exfiltration.

Purpose & Capability

Name/description (Gemini image generation) match the actual footprint: it needs GEMINI_API_KEY, the 'uv' runner, and installs google-genai + pillow to call Google's GenAI image model. These requirements are appropriate and expected.

Instruction Scope

SKILL.md instructs running the included script via 'uv run', provides preflight checks, handles input-image paths, and saves output PNGs to the current working directory. Instructions do not ask the agent to read unrelated files, secrets, or send data to third-party endpoints beyond the Gemini API client.

Install Mechanism

There is no aggressive installer; the metadata recommends running 'uv pip install google-genai pillow'. Installing PyPI packages is normal for a Python script but will execute code from those packages—verify you trust the 'google-genai' package source and consider using a virtual environment.

Credentials

Only GEMINI_API_KEY is required (and optionally provided as a CLI flag). No unrelated credentials, config paths, or broad environment access are requested.

Persistence & Privilege

The skill does not request always:true, does not persist or modify other skills, and is user-invocable. It can be invoked autonomously per platform defaults but has no elevated persistence or cross-skill privileges.

Assessment

This skill appears to do what it says: it sends prompts and optional input images to Google's Gemini image model and saves the returned PNG. Before installing: (1) ensure you want to provide a GEMINI_API_KEY to this code; (2) review/confirm the 'google-genai' package source (pip install will run remote code)—use a virtualenv; (3) don't pass sensitive images or credentials as input-image or in prompts, since data goes to Google's API; and (4) verify you have the 'uv' runner available and are comfortable running the included script from your current working directory.

Nano Banana 2 Direct - Gemini 3.1 Flash Image

Generate new images or edit existing ones using Google's Gemini 3.1 Flash Image Preview API directly (no inference.sh required).

Usage

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

Generate new image:

uv run ~/.openclaw/workspace/skills/nano-banana-2-direct/scripts/generate_image.py --prompt "your image description" --filename "output-name.png" [--resolution 1K|2K|4K] [--api-key KEY]

Edit existing image:

uv run ~/.openclaw/workspace/skills/nano-banana-2-direct/scripts/generate_image.py --prompt "editing instructions" --filename "output-name.png" --input-image "path/to/input.png" [--resolution 1K|2K|4K] [--api-key KEY]

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 ~/.openclaw/workspace/skills/nano-banana-2-direct/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
  • uv run ~/.openclaw/workspace/skills/nano-banana-2-direct/scripts/generate_image.py --prompt "<final prompt>" --filename "yyyy-mm-dd-hh-mm-ss-final.png" --resolution 4K

Resolution Options

The Gemini 3.1 Flash Image API supports three resolutions (uppercase K required):

• 1K (default) - ~1024px resolution
• 2K - ~2048px resolution
• 4K - ~4096px resolution

Map user requests to API parameters:

• No mention of resolution → 1K
• "low resolution", "1080", "1080p", "1K" → 1K
• "2K", "2048", "normal", "medium resolution" → 2K
• "high resolution", "high-res", "hi-res", "4K", "ultra" → 4K

API Key

The script checks for API key in this order:

1. --api-key argument (use if user provided key in chat)
2. GEMINI_API_KEY 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 "$GEMINI_API_KEY" (or pass --api-key)
  • If editing: test -f "path/to/input.png"

• Common failures:

  • Error: No API key provided. → set GEMINI_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

Filename Generation

Generate filenames with the pattern: yyyy-mm-dd-hh-mm-ss-name.png

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" → 2025-11-23-14-23-05-japanese-garden.png
• Prompt "sunset over mountains" → 2025-11-23-15-30-12-sunset-mountains.png
• Prompt "create an image of a robot" → 2025-11-23-16-45-33-robot.png
• Unclear context → 2025-11-23-17-12-48-x9k2.png

Image Editing

When the user wants to modify an existing image:

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: <subject>. Style: <style>. Composition: <camera/shot>. Lighting: <lighting>. Background: <background>. Color palette: <palette>. Avoid: <list>."

• Editing template (preserve everything else):

  • "Change ONLY: <single change>. Keep identical: subject, composition/crop, pose, lighting, color palette, background, text, and overall style. Do not add new objects. If text exists, keep it unchanged."

Output

• Saves PNG to current directory (or specified path if filename includes directory)
• Script outputs the full path to the generated image
• Do not read the image back - just inform the user of the saved path

Examples

Generate new image:

uv run ~/.openclaw/workspace/skills/nano-banana-2-direct/scripts/generate_image.py --prompt "A serene Japanese garden with cherry blossoms" --filename "2025-11-23-14-23-05-japanese-garden.png" --resolution 4K

Edit existing image:

uv run ~/.openclaw/workspace/skills/nano-banana-2-direct/scripts/generate_image.py --prompt "make the sky more dramatic with storm clouds" --filename "2025-11-23-14-25-30-dramatic-sky.png" --input-image "original-photo.jpg" --resolution 2K