Ein Baum und seine Abenteuer



GenAI

Generative AI (GenAI) can create or generate content from input. Input can range from text and images to audio and video. Generated output ranges from text over images and audio to video and an increasing list of content types. Dall-E and Stable diffusion started the age of Text-To-Image and ChatGPT made the value and benefit of Text-To-Text GenAI accessible to the masses.

A Robot painting
A Robot painting for my blog (Dalle-E 3)

Today I am a passionate user of GenAI and love to endulge in Prompt Engineering. On this page you find my Posts and Resources about the topic. Start by reading:

Related Posts

Holiday greetings with GenAI

Festive Greetings - ChatGPT and Midjourney
Festive Greetings - ChatGPT and Midjourney

Happy Holidays and festive greetings, powered by ChatGPT, Midjourney and a little bit of Photoshop.

Utilizing my Custom GPT for Midjourney prompts (open source on GitHub), I generated the image and some subtle variations in three rounds. Finally touching it up with a tagline in Photopea.

Address Custom GPTs as "you"

Custom GPTs
Custom GPTs

You should address your Custom GPT as "you" while giving it instructions.

DO: you are an expert in XYZ that helps users by…

DO NOT: I am an expert in XYZ and help my users by…

DO NOT: Act as an expert in XYZ and help users by…

The why

The initial instruction set to Custom GPTs starts with (Dec 2023):

Give your Custom GPT a goal

Custom GPTs
Custom GPTs

GPTs expect to be given a goal. You will get the most out of a Custom GPT by providing it with one.

Do this

An easy way to leverage this is to include a section in your prompt that looks a bit like this:

## Goals

- Goal 1 explained
- Goal 2 explained

The why

The initial instruction set to Custom GPTs starts with (Dec 2023):

Generative AI is here to stay!

"A path into the AI future" - generated using Midjourney
"A path into the AI future" - generated using Midjourney

Some reflections on what 2022 showed us about the future.

Generative AI describes AI that takes a prompt and generates something from it. Prime examples include Copilot which takes code or comments as a prompt to complete the code I want to write, ChatGPT which takes a chat message and replies with a human-like answer and Stable-Diffusion (or Dall-E, or Midjourney) which takes a prompt and returns a fitting image. All of these AIs made massive progress in 2022!

The Gods of Diffusion

The Pantheon of Diffusion
The Pantheon of Diffusion

I have rencently been spending quite some time with text2image generation. And while looking around for great styles for a project I generated a "Chromatic Goddess of Colors" that I really liked. This sparked the idea within me to generate a whole pantheon of gods and see how far I could push this!