ThematicPlane: Bridging Tacit User Intent and Latent Spaces for Image Generation

2025-08-08

AI Summary

While generative AI has lowered barriers to image creation, non-expert users struggle to precisely translate implicit creative intentions—such as emotion or aesthetic style—into actionable inputs for diffusion models. Method: We propose ThematicPlane, the first interactive framework that constructs manipulable latent-space planes aligned with high-level semantic themes (e.g., “warmth”, “drama”) rather than low-level visual features. It leverages semantic embeddings and interactive visualizations to map intuitive user operations—like sliding along thematic dimensions—onto diffusion model latent variables in real time, supporting both divergent exploration and convergent editing. Contribution/Results: A user study (N=6) demonstrates that ThematicPlane significantly improves creative iteration efficiency and expressive freedom. It further validates that interpretable, semantics-aware control is critical for enhancing usability and user trust in generative tools.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Humans and AI: Intelligent User Interfaces
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Generative AI has made image creation more accessible, yet aligning outputs with nuanced creative intent remains challenging, particularly for non-experts. Existing tools often require users to externalize ideas through prompts or references, limiting fluid exploration. We introduce ThematicPlane, a system that enables users to navigate and manipulate high-level semantic concepts (e.g., mood, style, or narrative tone) within an interactive thematic design plane. This interface bridges the gap between tacit creative intent and system control. In our exploratory study (N=6), participants engaged in divergent and convergent creative modes, often embracing unexpected results as inspiration or iteration cues. While they grounded their exploration in familiar themes, differing expectations of how themes mapped to outputs revealed a need for more explainable controls. Overall, ThematicPlane fosters expressive, iterative workflows and highlights new directions for intuitive, semantics-driven interaction in generative design tools.

Problem

• Aligning image generation with nuanced creative intent
• Bridging tacit user intent and system control
• Enabling fluid exploration of high-level semantic concepts

Innovation

• Interactive thematic design plane for semantic control
• Bridges tacit user intent with latent spaces
• Enables fluid exploration without explicit prompts