README.md

---
title: ZEN Omni Image Text Studio
emoji: 🧬
colorFrom: indigo
colorTo: purple
sdk: gradio
sdk_version: 6.0.1
app_file: app.py
pinned: false
short_description: Multi-provider studio for images, text, and infographics.
---

Configuration reference: https://huggingface.co/docs/hub/spaces-config-reference

# ZEN Omni Studio — Text • Images • Infographics

This Space lets you plug in:

- **OpenAI** (DALL·E 3, GPT-Image-1, GPT-4.1-mini for text)
- **Google AI Studio** (Gemini, Nano-Banana / Nano-Banana-Pro image models)

## Features

- Modes: **Image**, **Text**, **Infographic Spec**
- Presets:
  - ZEN Glass Dashboard
  - Palantir / Anduril Infographic
  - Youth AI Literacy Poster
  - ZEN AI Arena Card
  - Blueprint / Systems Diagram
- Image controls:
  - Provider (OpenAI vs Google)
  - Size / aspect ratio
  - Quality
  - Number of images
  - Style accent
  - Optional seed for repeatability

## Usage

1. Create a new Space (Gradio, Python).
2. Upload `app.py`, `requirements.txt`, and this `README.md`.
3. Set your **OpenAI** and **Google** API keys in the UI when the Space loads.
4. Choose your **Task Type** (Image / Text / Infographic Spec).
5. Pick a **Preset** and **Style**, then write your prompt.
6. Click **Generate**.

> **Nano-Banana / Nano-Banana-Pro Note**  
> Default Google image model is `nano-banana-pro`.  
> Replace it with the exact model ID from your Google AI Studio project if required.