The Research Nest
Published in

The Research Nest

I generated all images in this article using a text-to-image AI model (and the results are incredible)

How can we use Stable Diffusion?

Generated by Stable Diffusion

The Basics

Most prompts have the following features.

  • Background 🖼️🏖️
  • Colors 🌈🎨
  • Style 🖌️👨‍🎨

“A blue teddy bear in outer space, painted in anime”

  • The object is a teddy bear.
  • The background is outer space.
  • The style is anime.
A green teddy bear in front of a lake, painted in disney cartoon style
A blue teddy bear in outer space, pencil sketch

The Enhancers

We can enhance and add some specificity to a prompt using these words.

  • Verbs to describe actions on objects.
  • Figures of speech to add a comparative layer.
A beautiful blue teddy bear in outer space, playing the guitar like a rockstar, painted in anime

Does the model pick context automatically?

Consider this prompt.

Blue teddy bear, outer space, guitar, painting, anime

How specific can we get?

Consider something like this.

A #FFC0CB colored teddy bear painting

Fusion Prompts

Stable diffusion shines with sceneries and fusion of concepts.

a city skyline of a cyberpunk utopia
a sandwich made of green bricks

Practical Applications

  • Generating cover photos of articles on the internet. It can be used by the news media or any normal blogger. Stable diffusion generated the cover photo of this article too!
A robot playing basketball
I got this on my very first try. I am sure you can create much better images with a few tweaks and tries.
a concept art of a cyberpunk monster
Got it on the first try. No cherry-picking
a portrait of a bored cat in a cowboy dress
Viola! You can just frame it and sell it as an NFT
A logo of abstract research information being dumped into a nest
Quite something! This is a great starter design that can be used as an inspiration to create the final logo. Guess what? I will use it to create a new logo for The Research Nest.
painting snowflakes summer ice trees fall colors
The Result. Poetic. Authors can make some general imagery for their books in just a few seconds!

Are these images unique and novel?

I had my doubts. Are they truly creating something new and not giving out training data or something with minimal tweaks or random copy-paste mash?

The Future

  1. Models can be fine-tuned for tasks like generating video game assets, NFTs, comics, or 3D graphics.
  2. Text to video is the next direct evolution. Text to reels, text to animation, text to GIFs, possibilities is endless.
  3. Text to music will also start getting popular. Perhaps, we will be able to create a video along with the BGM with a simple text prompt.
  4. The real deal will be the fine-tuned customization layers built on this tech to bring your imagination to life.

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
XQ

Tech 👨‍💻 | Life 🌱 | Careers 👔 | Poetry 🖊️