What are we supposed to be doing with AI?

LLMs can't do two things at once

Language models struggle to balance multiple, potentially contradictory instructions when it comes to sentence structure and flow.

Comparing StabilityAI's text-to-image models for technical diagrams

Comparison of GenAI diagrams from StabilityAI's models. Analyzes layout, visual distinctions, text quality, and accuracy. Highlights strengths and weaknesses, emphasizing the importance of model selection for technical visualizations.

Comparing text-to-image models from OpenAI and StabilityAI

Case study exploring the two leading text-to-image models from OpenAI and StabilityAI. We generate some images together and compare and contrast the results of the same prompt applied to each model.

What does a healthy collaboration between human and AI look like in creative industries?

We want to get better at the things we do when we use AI, not rely on them so much that our skills atrophy and we end up dependent and worse-off than we were before using AI.

The stone woman case study

Using Stability's Image Control Sketch route to turn a simple pencil sketch into a something nearing real-life.