# ai-image-generator

Published articles for ai-image-generator.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Build your own Flutter GenUI solution with Gemini structured outputs

DevFeed: [Build your own Flutter GenUI solution with Gemini structured outputs](<https://devfeed.tech/articles/build-your-own-flutter-genui-solution-with-gemini-structured-outputs-23047.md>)

Original publisher: [Read original article](<https://medium.com/flutter-community/build-your-own-flutter-genui-framework-with-gemini-structured-outputs-a6db3653b9b6?source=rss----86fb29d7cc6a---4>)

Author: Cagatay Ulusoy

Published: 2026-06-09T12:28:28Z

Content type: tutorial

Language: en

Sources: [Flutter Community - Medium](<https://devfeed.tech/sources/flutter-community-medium.md>)

Topics: [Flutter](<https://devfeed.tech/topics/flutter.md>), [Framework](<https://devfeed.tech/topics/framework.md>), [Firebase](<https://devfeed.tech/topics/firebase.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [ai-image-generator](<https://devfeed.tech/tags/ai-image-generator.md>), [building](<https://devfeed.tech/tags/building.md>), [firebase](<https://devfeed.tech/tags/firebase.md>), [firebase-ai-logic](<https://devfeed.tech/tags/firebase-ai-logic.md>), [flutter](<https://devfeed.tech/tags/flutter.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generative-ui](<https://devfeed.tech/tags/generative-ui.md>), [llm](<https://devfeed.tech/tags/llm.md>), [ui](<https://devfeed.tech/tags/ui.md>)

### AI overview

This tutorial explains how to build a Flutter generative UI framework by hand with Gemini structured outputs. It introduces a guided five-step refinement flow in which Gemini generates topic-aware options, Flutter renders them as UI controls, and the selected values become structured data for a more specific image prompt.

### Source excerpt

Part 2 of a series "Building Image Assisted Language Learning Practice with Flutter, Firebase and Gemini." Part 1 built the image generation and annotation pipeline. This part buids a generative UI framework by hand, using Gemini structured outputs. Part 3 is the migration: same feature, official Flutter GenUI SDK. In Part 1, I built the first image description practice pipeline for my Flutter app. A user chooses a topic, Firebase and Gemini generate a practice image for the selected topic, and Gemini 3 adds visual annotations on top of the image. That pipeline worked. But after generating enough practices, a different problem became clear. The system could produce valid images, but the variation was limited. For some topics, Gemini kept returning to the same kind of scene, even when the prompt asked for ramdomness explicitly. This post starts one step before image generation. Instead of making the final prompt longer and hoping for more variety, I changed the input flow: what if the user could shape the scene through a guided UI before the image was generated? That led to a five step refinement flow. For each step, Gemini generates topic aware options, such as season, setting, action, framing, mood, and visual details. Flutter renders those options as normal UI controls. The user chooses what they want, and the app stores those choices as structured data before turning them into a more specific image prompt. I did not begin by trying to build a GenUI framework. I was just trying to stop my image generator from repeating itself. But by the end, the system had schemas, widget catalogs, state transitions, and LLM planned screens. So let's start with the original problem. Selected topic: Shopping and errands in Finnish everyday life1. A quick recap My app helps people practice 🇫🇮 Finnish. One of the core exercises is showing the learners a picture and ask them to describe it out loud, then give feedback. The user experience is simple. The content problem behind it is n