AI Comparison: DALL-E 2, Midjourney, and Stable Diffusion

Three of the current newest text to image AI programs are DALL-E 2 by OpenAI, Midjourney, and Stable Diffusion. Since these AI programs are all similarly new, the generate images of comparable quality, but in this post, I will try to determine whether any one of them is better than the others. Not only do quality of images matter, but the way you use them also matters, DALL-E 2 is in a website only, Midjourney is a Discord bot and you can see your results on their website, Stable Diffusion is only a discord bot, until it becomes open source. Although these AIs can be used in similar ways, currently, for DALL-E 2, you must request access and wait a few days before being able to use it, and after getting access, you need to pay to make images. Midjourney also requires you to pay, but you don’t need to wait, you just join their discord server and make an image using the bot. Stable Diffusion is entirely free, but if you aren’t already in the Discord server, you can’t join. Stable Diffusion will soon be open source, and you will be able to run it on your own computer if you have a GPU.

All three AIs can create very good images, but they have different advantages and disadvantages, depending on your goal, one may be better than another just because of its style.

PromptStable DiffusionDALL-E 2MidjourneyNotes and Results
A beautiful, very highly detailed oil painting of a huge field with tall, green grass and lots of huge trees with very light blue leaves, in a valley surrounded by small hills, green and light blue color scheme, by Greg Rutkowski.None of the AIs actually made the tree leaves blue.
Stable diffusion did the best job for making a realistic image, even though oil painting is specified.
Midjourney did the best job of making an oil painting.
DALL-E 2 made the correct color scheme, but the wrong colors on individual parts.
A large, very old, wooden ship sailing across the ocean in the middle of a huge rain storm, with lots of dark clouds and lightning, very realistic.Stable Diffusion did much better than either of the other two at the clouds, but the boat isn’t quite right.
DALL-E 2 made the best boat, but that image isn’t very realistic.
Midjourney made the most realistic water, but didn’t do well for any other parts.
A very long river flowing into a lake of pure gold, hidden in the middle of a dense forest of tall trees, with lots of light clouds in the bright blue sky, in the late afternoon.Midjourney got the color scheme right, the other two didn’t.
Stable diffusion is the most realistic.
DALL-E 2 is kind of in the middle of the other two for being good and bad at stuff.
A highly detailed oil painting by Greg Rutkowski and Thomas Kinkade of a secret cave with lots of dark grey rocks, and a river flowing through the middle of it, with a single tree growing in the river with lots of bright red and orange leaves.The color scheme in the DALL-E 2 image is slightly grey.
Both DALL-E 2 and Midjourney did a good job making a cave.
Stable Diffusion did a better job on the tree and the river.
A watercolor painting of a huge, ancient yellow dragon with lots of very vibrant, bright yellow scales flying through the clouds during a thunderstorm, lots of lightning, bright yellow, blue, and grey color scheme.DALL-E 2 made the most coherent dragon, but used a very strange style.
Stable Diffusion and Midjourney did a better job on the style, but didn’t make a very good dragon.
A beautifully highly detailed oil painting of an ancient gold dragon, with lots of very reflective, bright scales flying through the sky on a bright, sunny day over a huge medieval stone castle, by Afremov and Thomas Kinkade.DALL-E 2 made the best dragon, but the style isn’t detailed enough.
The other two failed to make a good dragon, but have a significantly better style.
A black and white pencil sketch of a huge waterfall flowing into a very large lake, surrounded by lots of trees and very rocky cliffs.None of the waterfalls are actually flowing down, and only Stable Diffusion shows a lake.
Midjourney made the most rocks on the cliff, but the fewest trees.
A huge cave full of rainbow color crystals and gems on the ground, and stuck to the walls made of huge grey boulders, very dark, midnight, oil painting by Afremov and Greg Rutkowski.Stable Diffusion and Midjourney made similar images.
DALL-E 2 made a very diffferent, worse image that doesn’t look right or match the prompt.
A highly detailed matte acrylic painting of a heavily armored paladin wielding a very bright glowing gold sword, fighting in a huge battle at dusk.DALL-E 2 did the best job by far, it was the only script to come anywhere near matching the prompt accurately.
Highly detailed oil painting, concept art, of a wizard casting a fireball spell, fighting against a huge ice giant, red and blue color scheme, concept art, highly detailed.All three AIs entirely skipped the “fighting against…” part.
A highly detailed oil painting of a duck walking towards a lake filled with pure gold instead of water.Each AI has a slightly different style, but only DALL-E 2 successfully matched the prompt.
A highly detailed 4K fantasy matte painting of city in cave. ArtStation, CGSociety, Unreal Engine.Midjourney didn’t make anything even slightly resemble a cave, both other AIs made similar images.
A beautiful, highly detailed, very realistic oil painting of a single tree with rainbow leaves, next to a small river, glowing bright blue in the middle of a huge, very dark cave, with lots of dark grey rocks, oil painting by Afremov and Greg Rutkowski.All three AIs successfully made only one tree, but only Stable Diffusion and DALL-E 2 made the tree look realistic.
A very realistic photograph of a dog wearing a golden crown with gems.Midjourney made a much more symmetrical crown, but the dog isn’t as realistic as Stable Diffusion or DALL-E 2.
A watercolor painting by Afremov of a psychedelic orange and blue mushroom growing on the ground in the middle of a forest.Stable Diffusion and Midjourney did a similarly good job for the prompt, but DALL-E 2 only half matched the prompt.
Chart shows images created using a prompt on all three different programs.

All three AIs are different, and can’t really be directly compared by results alone. DALL-E 2 makes the most coherent image, and often follows the prompt best. Stable Diffusion does better for some prompt, and worse for others, but most prompts can be changed to work well with it. Midjourney has a very unique style, but sometimes fails to match the prompt. If you just want to use any of these AIs, your best option is midjourney, you only need to pay, and you get access instantly. If you can’t afford to pay to use them, your best option is Stable Diffusion, it’s entirely free, but you need to apply to get access.

Leave a Comment

Your email address will not be published.