skills.rest
prime-skills
prime-skillsOFFICIAL
Explore all skills by this author →
GitHub

nano-banana-2

Generate polished still images from natural-language prompts via RunComfy.

31|9|Updated Apr 30, 2026
Search Tags:#image generation#text-to-image#nano banana#runcomfy#in-image typography#social thumbnails
One-click install
npx skills add https://github.com/prime-skills/runcomfy-agent-skills --skill nano-banana-2-prime-skills
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-2
Source: https://github.com/prime-skills/runcomfy-agent-skills/tree/main/nano-banana-2
Command: npx skills add https://github.com/prime-skills/runcomfy-agent-skills --skill nano-banana-2-prime-skills

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill turns text prompts into polished images quickly, reducing the iteration time and prompting guesswork involved in creating thumbnails, marketing assets, portraits, and social visuals.

Core Features & Use Cases

  • Rapid image generation: Produce one to four image variations using flexible aspect ratios and resolution tiers from draft quality through 4K.
  • Reliable visual direction: Improve composition, typography, framing, and reproducibility with subject-first prompts, quoted in-image text, and reusable seeds.
  • Web-grounded context: Generate imagery informed by current events or real-world entities when web search is enabled.
  • Model routing guidance: Identify when Nano Banana Pro, Nano Banana Edit, GPT Image 2, Flux 2, or Seedream 5 is a better fit.
  • Use Case: Create four vertical wellness-brand social thumbnails at draft resolution, select the strongest concept, and regenerate it at 2K with a locked seed.

Quick Start

Ask the Nano Banana 2 skill to generate four 9:16 social-media images for a wellness brand featuring a ceramic teacup, soft morning light, and the words “Slow Down” in large serif lettering.

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 social media thumbnails with precise text overlay from a prompt?▼

To generate social thumbnails with precise text, use a text-to-image model that supports quoted in-image typography, allowing you to specify exact lettering and composition directly within your natural-language prompt.

Can I reproduce the same image variation across different resolution tiers?▼

Yes, you can reproduce image variations across resolution tiers by locking the seed value. This allows you to generate a draft composition and regenerate the exact same visual at 2K or 4K resolution.

Does text-to-image generation with in-image typography require a specific CLI or authentication setup?▼

Generating images through RunComfy requires the RunComfy CLI, an authenticated account or a valid RUNCOMFY_TOKEN, valid endpoint inputs, and designated output storage for downloaded image results.

What is the best way to create marketing cards using web-grounded context for current events?▼

The best way to create marketing cards with current events context is using a text-to-image model with web search enabled, which grounds the generated imagery in real-world entities and timely information.

When should I choose a different image generation model instead of Nano Banana 2?▼

You should choose an alternative model like Nano Banana Pro, Nano Banana Edit, GPT Image 2, Flux 2, or Seedream 5 when your specific use case requires advanced editing, specialized rendering, or different model routing capabilities.

How do I generate multiple image concepts in different aspect ratios for rapid ideation?▼

You can generate one to four image variations for rapid ideation by specifying flexible aspect ratios, such as 9:16 for vertical social media, and selecting a draft resolution tier to quickly review visual concepts.

Related Skills

Explore More Design & Creative Skills→
prime-skillsprime-skills
31

image-to-video

Routes still-image animation requests to the appropriate RunComfy video generation model.

Official
Advanced
ReScienceLabReScienceLab
1.3k

nanobanana

Generate and edit images with Google Gemini 3 Pro Image via prompts.

Official
Advanced
nexu-ionexu-io
3.2k

nano-banana

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

Official
Intermediate
arm2armarm2arm
4

stable-diffusion-image-generation

Generate images from text prompts using Stable Diffusion and Diffusers.

Community
Advanced