skills.rest
obulai
obulaiOFFICIAL
Explore all skills by this author →
GitHub

obul-nano-banana-2

Generate images from text prompts using Google Gemini 3.1 Flash Image.

1|2|Updated Mar 2, 2026
Search Tags:#image generation#visuals#Gemini#AI art#creative#text-to-image
One-click install
npx skills add https://github.com/obulai/obul-apis --skill obul-nano-banana-2
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: obul-nano-banana-2
Source: https://github.com/obulai/obul-apis/tree/main/skills/obul-nano-banana-2
Command: npx skills add https://github.com/obulai/obul-apis --skill obul-nano-banana-2

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill allows users to quickly generate high-quality images from text prompts, overcoming the limitations of slow or low-fidelity image generation tools.

Core Features & Use Cases

  • Text-to-Image Generation: Creates images based on descriptive text prompts.
  • High-Quality Output: Leverages Google Gemini 3.1 Flash Image for Pro-level quality.
  • Speed: Achieves Flash speed for rapid iteration and generation.
  • Use Case: A user wants to create a unique illustration for a blog post about a "cyberpunk cat detective in a neon-lit city." This Skill can generate multiple variations quickly.

Quick Start

Generate an image of a cute cat wearing a hat.

Frequently Asked Questions about obul-nano-banana-2

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

FAQPage Schema
How do I generate images from text prompts using Gemini 3.1 Flash?▼

To generate images from text prompts, this Skill uses Google Gemini 3.1 Flash Image through the Obul proxy. You provide a descriptive text prompt, and the tool outputs high-quality visuals at Flash speed for rapid iteration.

Do I need an API key to use text-to-image generation here?▼

Yes, text-to-image generation requires an OBUL_API_KEY for authentication and payment processing. You must configure this key in your environment before generating visuals or using advanced features like subject consistency.

Can I maintain subject consistency across multiple AI art generations?▼

Yes, you can maintain subject consistency across multiple AI art generations. The tool supports this advanced feature alongside precise text rendering, allowing you to create coherent variations of the same subject quickly.

What is the best way to rapidly iterate on text-to-image visuals?▼

The best way to rapidly iterate on text-to-image visuals is using a fast generation model. This Skill leverages Google Gemini 3.1 Flash Image to achieve Flash speed, overcoming limitations of slow image generation tools.

Does this image generation tool support precise text rendering in visuals?▼

Yes, the image generation tool supports precise text rendering in visuals. This allows you to generate images that include accurate textual elements based on your descriptive text prompts without visual artifacts.

Related Skills

Explore More Design & Creative Skills→
obulaiobulai
1

obul-nano-banana

Generate and edit images from text prompts using Google Gemini models via the Obul proxy.

Official
Intermediate
nguyenphpnguyenphp
41

ckm:banner-design

Generate multi-format creative banners for social media, ads, websites, and print.

Community
Advanced
byrencheemabyrencheema

nano-banana-image

Generate and edit images via Google Gemini models with a CLI workflow.

Community
Intermediate
marmikcfcmarmikcfc

nano-banana-image-gen

Generate images from text prompts via the Nano Banana API on Orthogonal.

Community
Intermediate