About
Instagram
LinkedIn

Master Thesis
Practical Exploration     → 01  Ideation    → 02  Fine-tuning    → 03  Experiments    → 04  Co-creations    → 05  Result

Co-Creating with AI

Exploring and Integrating Stable Diffusion Models in the Creative Process of Poster Design.


This thesis explores the integration of Artificial Intelligence (AI), specifically personalised Stable Diffusion models, as a co-creative tool in poster design. Through practical experiments, the study examines how AI can generate diverse and inspirational outputs that push one’s creative boundaries, while emphasising the necessity of human intervention to refine and balance the design elements. The AI’s role is viewed as a collaborative tool rather than a replacement for designers, preserving the essence of human creativity while also  potentially transforming future design practices.
Master of Arts in Digital Communication Environments
University of Applied Sciences and Arts Northwestern SwitzerlandMentors
Dr. Paloma López Grüninger, Jinsu Ahn, Ludwig Zeller

Practical Exploration

01    Ideation

01 .01    Explorating

There are many AI tools out there to generate graphic images. To understand and see the visual potential of these tools, I started exploring the most well-known ones, such as DALL·E, Midjourney, and Stable Diffusion, to compare and see the visual differences.
Midjourney Explore Archive

Using basic text-to-image prompts, and without having a specific topic in mind, I asked for a graphic poster from different AI tools.
 DALL·E, txt2img
Midjourney, txt2img
Stable Diffusion’s v1.5 was a model released in autumn 2022 by Runway ML, a partner of Stability AI, and is based on the v1.2 model.
Stable Diffusion, v1.5, txt2img

Stable Diffusion’s xl1.0 model (SDXL) is a model that can generate “legible text” and diverse art styles. It is considered a better image model than v1.5, with its larger dataset, allowing for superior compositions.
Stable Diffusion, xl1.0, txt2img
Graphic-art is a model made by user Pmejna on CivitAI for Stable Diffusion based on v1.5, focused mainly on graphic design. It is a good example of how a model can be trained or fine-tuned specifically for creating graphic images.
 Stable Diffusion, graphic-art, txt2img

01 .02   Ideas

This phase was crucial for translating abstract mental ideas into visual representations, laying a foundation for subsequent experimentation. This involved idea generation with mind mapping and sketching to develop initial concepts.
Figural reasoning

© 2024 BASEL

Top