Prompt Exploration of AI Image Diffusion Models for Students

For the last few years, I have had my students explore AI image generation using text prompts. It’s been fascinating to see how the technology has progressed and what students can create with it. When the technology had not been so prominent, I used to have the students do a small competition using Runway.

At first, it was difficult for students to get good results, but with technological improvements, students were able to create increasingly impressive images. Perhaps more importantly, the “wow” factor had gone. Two or three years ago almost no student had tried an image generator. Now, although they tend to use large-language models like ChatGPT more, they are a lot less amazed by the product.

For those who are unaware, numerous models for image generation give slightly different results based on the same prompt. When working with students, it’s important to discuss the ethical implications of AI-generated images, such as potential biases in the training data. A lot of times, they believe these biases only occur with images of minorities, but the results affect all images. Consequently, I found one of the best ways to get students to understand the limitations is to have them generate images using the same prompt with two different models. We then create a slider showcasing the different prompts.

I realized that I had never really taken time out to really create them myself, so I figured this would be a good time to try out different diffusion models. I have found that StableCog seems to provide a generous free tier with different diffusion models, and the sliders can be created fairly easily in Flourish or Juxtapose. I especially wanted to try vector graphics since those usually require a lot of manual work in programs like Adobe Illustrator.

None of these models advertise themselves as being for vector graphics, but it is worth exploring to see how well they perform, and students seem to enjoy pushing these models to their limits. Anyway, here are some differences between the models using the same prompt. I drew from StableCog’s Gallery for the prompts but added terms related to vector graphs: