Image Generation

If you want to skip straight to scripts, click here! Stable Diffusion Release! We knew the world would not be the same – A few people laughed, a few people cried, most people were silent. And just like that, the whole world changes. Stable Diffusion and its openness is a massive improvement to the tools we’ve been using in this space and our ability to modify/understand them. It was bound to happen, but I am very impressed with both how quickly it rolled out and how powerful the tool is....

DALL-E Homebrew In this post, we’ll look at getting setup with running your own A.I. image generator. You need a Linux system with a CUDA enabled card to get this working through to the end. I did get the basic txt-2img script working in Windows. Unfortunately, for the July released retrieval-augmented diffusion models, you need scann in order to index the openimages dataset, which is only available on Linux. WSL worked fine for me....

Reproducing Vinyl Stickers In today’s post, we’ll look at creating and recreating vinyl stickers. This is one of the things Midjourney is particularly good at that could fairly easily translate into real or existing use cases. Services Used Today, and probably in the future, we’re just going to look at results with Craiyon and MidJourney. When I get access to DALL-E 2, I will start including that. Starry AI may make a reappearance when we look at art reproduction or creating new artworks in an artist’s style....

Comparing Apples to Apples To kick off the Daily A.I. section of this site, I wanted to start with something simple like how well the different services can render an apple. In the future, we’ll be doing other simple tests like this one, exploring different use cases for GPT-3 and/or AI Image generation, and work through prompt-crafting. DALL-E 2 recently went into beta and I’m keen to get an invite and begin including that tool in these tests....