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

obul-nano-banana

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

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates the creation and editing of images from text prompts, eliminating the need for complex design software or manual image manipulation.

Core Features & Use Cases

  • Text-to-Image Generation: Create unique images from descriptive text prompts.
  • Image Editing: Modify existing images based on textual instructions.
  • Image Composition: Combine multiple images into a single visual.
  • Use Case: A user wants to create a unique banner image for their blog post about a "futuristic cityscape at sunset" and uses this skill to generate it.

Quick Start

Use the obul-nano-banana skill to generate an image of a cat wearing a hat on a beach at sunset.

Frequently Asked Questions about obul-nano-banana

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

FAQPage Schema
How do I generate images from text prompts using AI?▼

You can generate images from text prompts by providing descriptive instructions to AI models like Google Gemini. This Skill processes your text descriptions to automatically create unique images without requiring complex design software.

Can I edit existing images with text instructions?▼

Yes, you can edit existing images by providing textual instructions alongside the source image. The AI processes your text commands to modify the visual content, allowing targeted adjustments without manual image manipulation software.

Do I need an API key to use Google Gemini for image generation?▼

Yes, an OBUL_API_KEY is required for authentication to access Google Gemini image generation models via the Obul proxy. This key handles automatic payment processing for your text-to-image and image editing requests.

What is the difference between fast and high-quality AI image generation?▼

Fast image generation uses the gemini-2.5-flash-image model for rapid processing, while high-quality generation uses gemini-3-pro-image-preview for superior visual fidelity. You select the option based on whether speed or detail matters more for your project.

How do I combine multiple images into one using AI?▼

Multi-image composition combines several source visuals into a single cohesive output image. This Skill uses Google Gemini models to process multiple images and merge them based on your text instructions, creating a unified visual asset.

Related Skills

Explore More Design & Creative Skills→
obulaiobulai
1

obul-nano-banana-2

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

Official
Intermediate
UniquecreteUniquecrete

media-agent

Generate blog featured images, social thumbnails, and snippet graphics from Jira tasks.

Community
Intermediate
pikakitpikakit

ai-artist

Generate deterministic, templated prompts for text and image generation models.

Community
Advanced
obulaiobulai
1

obul-x402engine-image

Generate AI images via FLUX and Ideogram through Obul proxy endpoints.

Official
Intermediate