Tag Archives: GenAI

Newer is not always better…

The post discusses the evolution of Stable Diffusion and UI options for generative AI image creation, particularly with XL models. The author tested different XL models with varied prompts but found that the newer models did not always produce better results than the original 1.5 model. Despite improvements, the author still prefers the 1.5 generation’s speed and appeal.

GAI & the creative process (part 4)

In my last post, I was less than satisfied with the motivations and background generated by the model for the female elf in the story. It felt like it drew on too many cliche’s common to the fantasy genre. The next prompt is a direction to expand on a specific paragraph from the previous output:Continue reading “GAI & the creative process (part 4)”

GAI & the creative process (part 3)

Continuing on from my last post, let’s see what other ideas can be mined from my GAI session. Continuing to the next prompt: Why does Roran seek a financial gain from his efforts? How does it compete with his sense of adventure and curiosity? Once again, since I’m still in the same chat-session, the modelContinue reading “GAI & the creative process (part 3)”

GAI & the creative process (part 2)

Continuing on from my last post, let’s see if we can modify the prompt provided to my model to generate better content or provide additional ideas for exploring in the story. Following the output from my first prompt, I added the following: Expand on Roran’s motivation for entering into the woods. Make him much moreContinue reading “GAI & the creative process (part 2)”

Using GAI to jumpstart your creative process

There are a lot of fear mongering articles about Generative AI subverting the role of creatives such as actors, screenwriters, and other authors. While the fear is real, I’m not convinced the threat is. Rather than taking the articles against GAI at face value, I wanted to explore what the current state of the artContinue reading “Using GAI to jumpstart your creative process”

Creating Character Images with Stable Diffusion

I’ve written about using Stable Diffusion after the fact to create images of characters, and shared samples of my results, but did not detail my specific workflow or process, so I thought I’d share a little about it.  I like to let the computer churn out possible images while I’m working on writing or otherContinue reading “Creating Character Images with Stable Diffusion”