skills.rest
doany-ai
doany-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

nano-banana-2

Generate image drafts with Google Nano Banana 2 via the RunComfy CLI.

5|2|Updated May 18, 2026
Search Tags:#image#generate#text-to-image#rapid-ideation#prompt-patterns#marketing-visuals#nano-banana-2
One-click install
npx skills add https://github.com/doany-ai/skills --skill nano-banana-2-doany-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-2
Source: https://github.com/doany-ai/skills/tree/main/nano-banana-2
Command: npx skills add https://github.com/doany-ai/skills --skill nano-banana-2-doany-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill accelerates the generation of rapid, concept-ready image drafts by leveraging Google Nano Banana 2 through the RunComfy CLI, providing consistent results with model-specific prompting patterns and a clear routing path for related siblings.

Core Features & Use Cases

  • Prompt-pattern driven generation: Uses subject-first prompts and exact in-image typography cues to deliver predictable, publish-ready visuals.
  • Fast iteration for marketing visuals: Ideal for social thumbnails, banners, and product mockups with quick turnarounds.
  • Flexible deployment: Supports web grounding when needed and simple CLI-based execution for reproducible results.

Quick Start

Run a sample prompt with the RunComfy CLI to generate a single Nano Banana 2 image draft

Frequently Asked Questions about nano-banana-2

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

FAQPage Schema
How do I generate fast image drafts for marketing visuals?▼

To generate marketing visuals, use subject-first prompting patterns with Google Nano Banana 2 via the RunComfy CLI to produce rapid, concept-ready image drafts for social thumbnails and banners.

Can I use in-image typography cues for text-to-image generation?▼

Yes, text-to-image generation supports exact in-image typography cues to deliver predictable, publish-ready visuals using model-specific prompting patterns for consistent results.

Does the RunComfy CLI support web grounding for image generation?▼

The RunComfy CLI supports optional web grounding when needed for image generation, alongside simple CLI-based execution to ensure reproducible results across marketing and product design workflows.

What is the best way to automate batch thumbnail creation?▼

Batch thumbnail creation is best handled by leveraging Google Nano Banana 2 through the RunComfy CLI, which allows for rapid ideation and flexible deployment of multiple image drafts quickly.

How do I write effective prompt patterns for rapid ideation?▼

Effective prompt patterns for rapid ideation use a subject-first structure combined with exact typography cues, following model-specific routing and safety tolerances to generate predictable visual outputs.

Related Skills

Explore More Design & Creative Skills→
agentspace-soagentspace-so
31

nano-banana-2

Generate images from natural-language prompts via the RunComfy Model API.

Official
Intermediate
sylvandingsylvanding
9

gemini-imagegen

Generate, edit, and compose images via the Gemini API.

Community
Intermediate
afel6afel6

powerpoint

Read, create, edit, and validate .pptx files with XML and thumbnail workflows.

Community
Advanced
framersaiframersai

image-gen

Generate images from text prompts using DALL-E, Stable Diffusion, and Midjourney APIs.

Official
Intermediate