nanobanana2 Image Generation & Editing

Generate new images or edit existing ones using Google's nanobanana2 API (Gemini 3.1 Flash Image preview, model id gemini-3.1-flash-image-preview).

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 "$HOME/.openclaw/skills/nanobanana2/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

- INLINECODE3

Resolution (`image_size`)

nanobanana2 accepts these image_size values (see docs): 512, 1K, 2K, 4K. Use uppercase K for 1K/2K/4K; 512 has no K suffix (smaller output, Flash-only).

- 512 — lowest tier (~512px shortest side per aspect table); good for thumbnails / fastest drafts
1K (default) — ~1024px class
2K — ~2048px class
4K — ~4096px class

Map user requests:

- No mention of resolution → INLINECODE13
"tiny", "thumbnail", "512", "low pixel" → INLINECODE14
"low resolution", "1080", "1080p", "1K" → INLINECODE15
"2K", "2048", "normal", "medium resolution" → INLINECODE16
"high resolution", "high-res", "hi-res", "4K", "ultra" → INLINECODE17

Aspect ratio (`aspect_ratio`)

Optional. If omitted, the API defaults apply (e.g. 1:1 for pure text-to-image, or match input image when editing — per API behavior).

Supported values for Gemini 3.1 Flash Image: 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.

Pass explicitly when the user asks for wallpaper, story, reel, banner, etc., e.g. --aspect-ratio 9:16 or --aspect-ratio 16:9.

API Key

The script checks for API key in this order:

1. --api-key argument (use if user provided key in chat)
INLINECODE36 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: INLINECODE40

- 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: INLINECODE46

Format: INLINECODE47

- 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" → INLINECODE51
Prompt "sunset over mountains" → INLINECODE52
Prompt "create an image of a robot" → INLINECODE53
Unclear context → INLINECODE54

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
Use --input-image parameter with the path to the image
The prompt should contain editing instructions (e.g., "make the sky more dramatic", "remove the person", "change to cartoon style")
Common editing tasks: add/remove elements, change style, adjust colors, blur background, etc.