HN Showcase
Back to browse
Nano Banana 2 Playground – text-to-image and image-to-image demo

Nano Banana 2 Playground – text-to-image and image-to-image demo

by iamouyang·Mar 1, 2026·1 point·1 comment
Visit ProjectView on HN

AI Analysis

●MidEye Candy

Polished image generator UI, but Midjourney, DALL-E, and Stable Diffusion already dominate.

Strengths
  • •Clean, responsive interface with fast iteration loop and multiple aspect ratio presets
  • •Comparison table clearly communicates model tradeoffs (speed vs. quality vs. fidelity)
  • •Credit-based pricing tiers let users pick cost vs. output quality
Weaknesses
  • •No differentiation from established competitors—another text-to-image wrapper on commodity model
  • •No evidence of superior quality, speed, or unique features vs. market leaders
Category
AI/ML
Target Audience

Designers, content creators experimenting with image generation

Similar To

Midjourney · DALL-E 3 · Stable Diffusion WebUI

Post Description

Hi HN — I’m an indie developer. I built Nano Banana 2 Playground, a simple web demo for generating images from text and transforming existing images (image-to-image).

My goal was a fast, minimal UI that lets you iterate on prompts quickly and compare results without extra friction.

I’d love feedback on:

Prompt UX (what feels missing/confusing)

Which controls/presets are actually useful

How to communicate limitations and expected results clearly

Thanks for taking a look — happy to answer questions and improve it based on your suggestions.

Similar Projects