Glowhub
An Interactive Educational Tool for Building Trust in Imagery Generative AI
Alix Zhang
Take a Glance
About the Project
Project Overview
GlowHub is an interactive educational tool that enhances learnability and transparency in text-to-image AI, a field often overlooked in AI literacy. Visual creators struggle with the misalignment outcomes in using text-based AI tools, while AI biases remain abstract and hidden. GlowHub offers real-time, hands-on exploration through a progressive, visual learning approach. It fosters both intuitive understanding and critical reflection, empowering users to grasp AI’s logic while questioning its limitations. By learning through practice, users critically engage with AI and reflect on future human-AI relationships.
Goal
GlowHub aims to demystify generative AI and build a learning experience for visual creators, fostering both confidence and critical awareness in generative AI through transparency and interactive learning.
Target User
The target users of GlowHub are visual creators, including designers, artists and other related professionals. Their creative processes rely heavily on visual thinking, experiential knowledge, and responsive engagement.
As generative AI become more integrated into creative industries, the ability to use AI tools allows visual creators to expand their creative process, improve workflow efficiency, and stay competitive in a rapidly changing field.
Experience
Visual Think
Respond
Outcome
GlowHub offers a new approach to building cognitive trust in generative AI through an interactive web-based tool. It introduces a new interface paradigm for human–AI interaction, one that goes beyond traditional CUI, GUI and passive tutorials.
Take a Glance
Feature
Prototype
Explore Section
Explore focuses on helping users build prompt literacy through hands-on experimentation. Users can adjust each of the five sliders independently in Single Prompt Mode or combine them in Combined Prompt Mode to understand how different elements interact.
Offering interactive tools to bridge visual intuition and AI logic.
Beware Section
While Explore teaches how to use AI effectively, Beware teaches how to use it with the awareness of AI's bias and limitations. In this section, GlowHub presents side-by-side image sliders that reveal how genAI often misinterprets language, culture, gender, and meaning.
Offering interactive tools to bridge visual intuition and AI logic.
What Took Me Here
Process
Background Research
This is a space to share more about the business: who's behind it, what it does and what this site has to offer. It’s an opportunity to tell the story behind the business or describe a special service or product it offers. You can use this section to share the company history or highlight a particular feature that sets it apart from competitors.
How I make it work
GlowHub’s visual content was generated using MidJourney V5, chosen for its quality, speed, and breadth. To reduce randomness, I generated 4–8 images per prompt and carefully selected the most representative result—highlighting, for example, gender bias when the prompt “nurse” consistently produced female figures.
To visualize prompt influence, I created morphing animations in Stable Diffusion’s ComfyUI, using the AnimateDiff plugin. Each animation runs 90 frames at 15 fps, balancing clarity with performance.
The interactive interface was built in Unity, where users explore image changes through sliders mapped to keyframes rather than videos—ensuring smooth, low-latency playback even during quick or reversed navigation. The result is an intuitive, responsive learning experience.
User Test
Goal: Evaluate GlowHub’s impact on AI trust, prompt confidence, and bias awareness.
Participants: 8 creatives—including students, artists, designers, and educators—ranging in age from their early 20s to 60+, with diverse cultural backgrounds (Asian, White, Black) and varying levels of genAI experience.
Method: Pre-test/Post-test survey, Likert Scale
To reach more users and collect broader feedback, the study was shifted from in-person sessions to a more efficient online format. Curious how your own trust in AI might shift?
What's Next
Conclusion
What Users Say
Improved trust and clarity
Users reported higher trust in generative AI and showed a clearer understanding of its limitations and biases.
Playful, open, and inspiring
Users described GlowHub as exploratory and creative. The interface helped them think in new directions and experiment more freely.
Users suggest:
More control & scalability
Interconnected sliders
Clearer guidance
Future
GlowHub is not just a tool—it’s redefining how we interact with AI itself. Moving beyond traditional Graphical User Interfaces (GUI) and text-based Conversational Interfaces (CUI), GlowHub envisions a future where AI becomes an adaptive creative partner, bridging the gap between human intuition and machine logic.
Future iterations will introduce greater interactivity between prompt elements, allowing sliders to work in synergy, creating a more fluid, exploratory interface that reflects the complexity of AI-generated imagery. By integrating real-time feedback, contextual guidance, and interactive tutorials, GlowHub will help users not just understand AI, but intuitively engage with it.
More than a tool, GlowHub envisions a future where AI becomes a co-creative partner—adaptive, transparent, and designed to enhance human imagination.