skills.rest
krusemediallc
krusemediallcCOMMUNITY
Explore all skills by this author →
GitHub

nano-banana-image-ad

Generate Meta image-ad creatives via the Arcads API using Nano Banana models.

1.5k|357|Updated Apr 1, 2026
Search Tags:#image generation#Marketing#nano banana#ad creative#Meta ads#gemini image#arcads api
One-click install
npx skills add https://github.com/krusemediallc/arcads-claude-code --skill nano-banana-image-ad
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-image-ad
Source: https://github.com/krusemediallc/arcads-claude-code/tree/main/skills/nano-banana-image-ad
Command: npx skills add https://github.com/krusemediallc/arcads-claude-code --skill nano-banana-image-ad

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Creating standalone Meta image-ad creatives with AI image models requires handling API authentication, presigned reference uploads, prompt safety constraints, and polling for results. This Skill automates that entire pipeline through the Arcads external API with the Nano Banana (Gemini Flash Image) model family.

Core Features & Use Cases

  • Text-to-image and image-edit generation: Produce 1-5 ad variants per run in 1:1, 16:9, or 9:16 ratios, or edit an existing source image with nano-banana-edit.
  • Reference-grounded generation: Upload up to 14 local reference images (product shots, characters, style guides) through Arcads' presigned-upload flow for consistent branding.
  • Built-in ad safety guards: Automatically appends no-platform-chrome, edge-safe layout, and text-fidelity suffixes so outputs are ready for Meta placement.
  • Use Case: A media buyer needs three photoreal lifestyle ad variants featuring a product photo. The Skill rewrites the prompt from a validated template library, confirms credit cost, generates the variants, and hands the image paths to a Meta ad-builder skill.

Quick Start

Ask the agent to generate three 1:1 Nano Banana image-ad variants from your product photo using the nano-banana-image-ad skill with your Arcads credentials in .env.

Frequently Asked Questions about nano-banana-image-ad

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate Meta image ads with Nano Banana via the Arcads API?▼

Run the generate_image.py script with a prompt, aspect ratio (1:1, 16:9, or 9:16), variant count, and optional reference images. It handles presigned uploads, submits to POST /v2/images/generate, polls until generated, and downloads PNGs locally.

What is the difference between nano-banana-2, nano-banana-pro, and nano-banana-edit?▼

nano-banana-2 (Gemini 2.5 Flash Image) is the default for most templates. nano-banana-pro (Gemini 3 Pro Image) costs more but locks character identity for hero shots. nano-banana-edit is inpaint-focused and only used with image_edit mode for masked edits.

How many reference images can Nano Banana ads use?▼

The Arcads API caps Nano Banana generation at 14 reference images, and the script enforces this limit. References are uploaded fresh per variant through the presigned-URL flow and passed as filePaths in the request.

Does this skill support aspect ratios like 4:5 or 2:3?▼

No. The Arcads /v2/images/generate endpoint only accepts 1:1, 16:9, and 9:16. For other Meta ratios, generate at 1:1 and post-crop, or use a backend that supports the full Meta ratio set natively.

Can this skill upload generated ads to Meta or generate videos?▼

No. It only generates static images and outputs local file paths. Meta upload is handled by a separate ad-builder skill, and video, carousel, and DCO ads are explicitly out of scope.

Why do Nano Banana ads sometimes have garbled text or extra fingers?▼

Garbled small text is a known Nano Banana weakness, and limb errors are common in Gemini-family models. The skill mandates visual QA per variant and up to two retries with corrected prompts; passing brand wordmarks as reference images reduces drift.

Related Skills

Explore More Marketing & Sales Skills→
Ouro-labsOuro-labs
14

ce-gemini-imagegen

Generate and edit images from text prompts using the Gemini API.

Official
Intermediate
fdarkaoufdarkaou
39

meta-ads

Manage Meta Ads campaign monitoring, optimization, creative generation, and upload workflows.

Community
Advanced
williamsforealwilliamsforeal
1

static-ad-generator

Generate static ad images via FAL API calls from brand research and template prompts.

Community
Advanced
nexu-ionexu-io
3.2k

nano-banana

Generate or edit images with Nano Banana models from prompts and input images.

Official
Intermediate