ourt AI - Art & Community

Here's an English translation optimized for Google Play:

About This App

OurtAI is a creative AI studio where you can generate images, text, and audio while getting AI assistance - all in one place. Create what you envision with "I want this kind of image," get help writing descriptions, and collaborate with AI to bring ideas to life. Features the latest Gemini 2.5 Flash Image (Nano Banana) model for composition control and high-speed generation.

What You Can Do

Image Generation: Works with simple prompts. Create realistic, anime, illustration, or design sketches

Gemini 2.5 Flash Image (Nano Banana):

Turn illustrations into figurines

Generate photos of yourself in different eras

Create cross-view images

Color line art with specific palettes

Colorize old photographs

Change outfits and styling

Modify character poses

Generate poses from line drawings

Transform maps into 3D building illustrations

Analyze makeup styles

Generate multiple character poses

Control lighting effects

Extract subjects to transparent layers

Place giant anime figures in Tokyo streets

Convert to manga style

Create ID photos

Text Support: Descriptions, captions, promotional content

AI Chat: Improvement suggestions, rephrasing, additional ideas

Share & Publish: Turn generated content into organized artwork posts

Gallery: Manage favorites and history

Voice Synthesis: Convert text to speech

AI Chat Examples

"Make it brighter" → Prompt rephrasing suggestions

"Shorten for social media" → Caption alternatives

"Different variations" → Continuous variation proposals

Sharing & Publishing

Organize generated results into artwork pages

Discover inspiration from public works

Public/private options (gradual expansion planned)

Content guidelines enforce appropriate use

Usage Flow

Enter keywords (brief is fine)

Generate → Save/post if satisfied

Use chat for fine-tuning when unsure

Reuse and share via gallery

Use Gemini 2.5 Flash Image for composition control and variations

Tips

Add details like "time of day," "mood," "texture" for better results

Ask chat: "Suggest different patterns"

Start simple, then gradually add details

Safety Features

Multi-stage filtering for inappropriate/harmful content

User-controlled deletion and management

Rules and privacy policy accessible in-app

Use Cases

Social media avatars and headers

Visual prototypes for projects

Draft descriptions and introductions

Creative writing atmosphere building

Quick caption comparisons

Current Limitations

Video generation currently web-only

Possible delays during high usage

Results may vary from intention (retry/adjust recommended)

Safe Usage

Avoid copyright infringement and inappropriate content

Review content before external sharing

FAQ

Q: What should I write? → Start brief, then add details

Q: Can I use Japanese? → Yes, direct input works

Q: Want different mood? → Tell chat "make it more ○○"

Q: Same composition with variations? → Use Gemini 2.5 Flash Image

Development Policy

To maximize user creativity speed and iteration count, we continuously enhance our design that combines lightweight high-speed models with high-precision models, enabling rapid improvement cycles (try → adjust → finalize).