Sign In
Evolution of Text-to-Image: 2023

Go to year: 202220232024 (pt 1)2024 (pt 2)


Introduction

There weren't a lot of new models in 2023, but it was a year full of major releases to some of the most popular models.

Prompts and project details can be found at the bottom of the article. High resolution versions of the comparison image grids are in this article's attachment.

The Models

Midjourney 5

March 2023

The first half of 2023 is dominated by four new versions of Midjourney 5. We start with 5.0. This version had increased details and realism over version 4. Their generated output resolution has doubled again to 1024x1024 dimensions.

❌free download

Midjourney Niji 5

April 2023

The next month Midjourney released the first sequel to their Niji model, also with more detailed 1024x1024 output.

❌free download

Midjourney 5.1

May 2023

The next month Midjourney released 5.1.

❌free download

Midjourney 5.2

June 2023

Then one month after that they released 5.2.

❌free download

Stable Diffusion XL

July 2023

Finally we can move on to something that isn't Midjourney. Stable Diffusion took their time and redeemed themselves with their XL version. This model was trained on 1024x1024 images and produced more accurate images than 1.5. This version was free, flexible, and easy to train. It became extremely popular and has many fine-tuned variations.

✅free download (civitai | huggingface)

DALL-E 3

October 2023

DALL-E was a major leap in quality over version 2. For the first time, we start to see legible text and an understanding of positioning instructions (left, middle, right). This model is now integrated with Chat-GPT but is also the model used for Microsoft's free Bing and Copilot generators.

❌free download

Firefly 2

October 2023

Adobe trained their own model on stock and public domain images. It could be accessed through their website with an Adobe account and was the beginning of integrating AI directly into Photoshop and Illustrator.

❌free download

Midjourney 6

December 2023

2023 ends the way it began: a new Midjourney version. Now we're up to version 6. This version is better at realism and following instructions. We can see the beginnings of legible text and it's getting much better at following instructions, though it still has room for improvement.

❌free download

Project Details

Disclaimer

I'm not an insider with special access to anything or a programmer who understands how all this works under the hood. I took some time to research, but this is from information found online and I can't guarantee everything is accurate. This is a work in progress; I'm still working on filling in missing information.

Also note that this is only a comparison of base models. Some models can produce significantly better images by using trained checkpoints, styles, presets, or detail enhancers.

Criteria

  • Must still be publicly accessible in 2024 without a complicated setup.

  • For this series, I've excluded turbo/fast versions of the models.

Process

  • I chose 15 prompts that show a variety of photo realism, art styles, people, animals, objects, specific instructions, open-ended short prompts, text, and abstract concepts.

  • All images come from the first generation set and I never picked from more than 1-4 images.

  • When possible, I used images from the same seed which can show differences between minor versions of the same model.

  • I used the recommended settings for each model or the default offered online.

  • I didn't use additional styles or presets.

Prompts

  • african hydropunk princess

  • artificial intelligence

  • astronaut exploring an alien planet

  • overhead view of a breakfast plate with eggs, toast, strawberries, coffee, and a fork

  • exterior of a cafe watercolor painting

  • person wearing cyberpunk accessories in a high tech neon city

  • druid man character design

  • ethereal fairy in the style of oil painting

  • graphic design logo with fennec fox and succulents and text "Desert Design"

  • man and a woman in love

  • photo of a deer in an enchanted forest with cinematic lighting

  • Photo portrait of a woman with long black curly hair in natural light. She's wearing a fashionable purple blouse, a gold necklace with a locket, and hoop earrings. Bokeh background.

  • pixel art city street scene with shops and pedestrians at night

  • red potion bottle with text "health" on the left, blue potion bottle with text "mana" in the middle, green potion bottle with text "poison" on the right, on a wooden table in a dark alchemist's laboratory, in the style of a detailed digital painting

  • woman lying on the grass

Article Updates

  • Nov 26, 2024: Added navigation links. Added download links.


Go to year: 202220232024 (pt 1)2024 (pt 2)

6