How to Refine AI-Generated Typefaces with Interface Sliders

Table of Links

1. Introduction

2. Related Work

   2.1 Semantic Typographic Logo Design

   2.2 Generative Model for Computational Design

   2.3 Graphic Design Authoring Tool

3. Formative Study

   3.1 General Workflow and Challenges

   3.2 Concerns in Generative Model Involvement

   3.3 Design Space of Semantic Typography Work

4. Design Consideration

5. Typedance and 5.1 Ideation

   5.2 Selection

   5.3 Generation

   5.4 Evaluation

   5.5 Iteration

6. Interface Walkthrough and 6.1 Pre-generation stage

   6.2 Generation stage

   6.3 Post-generation stage

7. Evaluation and 7.1 Baseline Comparison

   7.2 User Study

   7.3 Results Analysis

   7.4 Limitation

8. Discussion

   8.1 Personalized Design: Intent-aware Collaboration with AI

   8.2 Incorporating Design Knowledge into Creativity Support Tools

   8.3 Mix-User Oriented Design Workflow

9. Conclusion and References

6 INTERFACE WALKTHROUGH

6.1 Pre-generation stage

6.2 Generation stage

6.2.2 Regenerating with appropriate strength. Recognizing the generated result is closer to the typeface, she deletes unwanted results and adjusts the design factor strength to 0.86 using the slider. In the subsequent round, she finds a desirable result and clicks it. The chosen design is then displayed in the central canvas.

6.3 Post-generation stage

6.3.1 Evaluating and Refining the generated result. To assess its legibility, Alice navigates to the right side of the canvas and clicks the [Evaluation] button in the EVALUATION. The current position of the result is situated on the imagery side of the slider with a value of 0.55. However, aiming to explore positions more aligned with the typeface side, she drags the slider to the left. After several trials, Alice obtains a series of results, as shown in Fig. 5.