nanobananalisted

Generate or edit images using Google's Nano Banana family (Gemini 2.5 Flash Image, Gemini 3.1 Flash Image Preview, and Gemini 3 Pro Image Preview). Use this skill whenever the user asks to "generate an image", "create a visual", "make a hero image", "edit this photo", "blend these references", produce assets for blog posts, social media, marketing/DevRel content, icons, infographics, magazine-style mocks, isometric scenes, or product mockups, OR when the user mentions "nano banana", "Gemini image", "nanobanana", "Imagen alternative", or "Google image gen". Trigger this skill even when the request is casual, such as "make me an image of X" or "I need a visual for the blog post". Always prefer this over describing an image in text when a real image is what the user wants.
Xipher-Labs/walter-os · ★ 5 · AI & Automation · score 67

Install: claude install-skill Xipher-Labs/walter-os

# Nano Banana — Image Generation & Editing Google's Nano Banana family lives in the Gemini API. Three tiers as of May 2026: | Variant | Model ID | Use when | |---|---|---| | Nano Banana | `gemini-2.5-flash-image` | Speed, cost (~$0.039/img), high-volume batches, drafts, DevRel iteration | | Nano Banana 2 | `gemini-3.1-flash-image-preview` | Default for production: better text rendering, hybrid reasoning | | Nano Banana Pro | `gemini-3-pro-image-preview` | 4K output, complex semantic reasoning, hero/marketing assets, multi-language text in image | All outputs include an invisible **SynthID watermark**. Decline requests to remove it. ## Setup (once) ```bash walter ai configure --profile mixed --set image_generation=gemini pip install google-genai pillow export GEMINI_API_KEY="..." # https://aistudio.google.com/apikey ``` The helper script checks `~/.config/walter-os/ai-capabilities.yaml` (or `WALTER_AI_CAPABILITIES_FILE`) before calling Gemini. If `provider_gemini` is disabled or `route_image_generation` does not include `gemini`, it exits before loading SDK dependencies. Store the key in your private overlay or shell secret manager, never in the repository. ## 1. Text → Image (basic generation) ```python from google import genai from PIL import Image from io import BytesIO client = genai.Client() response = client.models.generate_content( model="gemini-2.5-flash-image", contents=[ "Hero illustration for a Solana RPC infrastructure blog post. "