I’ve put Stable Diffusion 2.0 to the test against Midjourney version 4 in this side-by-side comparison and review.
See for yourself the results
I have used precisely the same prompts for this side-by-side comparison and put them into each of these to compare the results, which might surprise you. I’ve gone through everything from portrait to landscape to character design to still live to animal photography.
I’ve challenged mid-journey and stable Diffusion with the same prompts and We’re going to look at them side by side We’ll go through a number of rounds Covering everything from portraits to Landscapes so let’s jump in number one Is a dream of a distant Galaxy and we Can see that mid Journey has a greater Narrative to the piece they’ve included A character looking distantly into this Space Odyssey where is stable diffusion has Outputted something that’s a little bit More garish and less coherent next up we Have an elegant fantasy couple kissing And again the consistency in the facial Features And in the bodies the anatomy is much Greater inside of my journey I can even Say that my journey is accurately Inputted five fingers to a hand or maybe This is seven But the hands are still improving he’s a Very coherent and easily identifiable Faces next up we have a tired woman Wearing a Valentino gown sitting and a Roadside Diner and although the hands of Mid-journey are still very tiny and look More like a walnut Than A Pair of Hands The overall composition and feeling of The piece is much more engaging than Stable diffusion which has output it’s Something very much more abstract and This woman looks more like she has a
Trotter than a hand next up we have a Fantasy cyberpunk princess you can see Stable diffusions version is All the more together less detailed less Intricate the composition and it’s Anatomy is failing in comparison to Mid-journey we have this girl with Absolutely remarkable abs and a Wonderful Symmetry to the background that’s Leading our gaze in you can see these Leading lines bringing us into the Center of the piece whereas the lines Inside of stable diffusion that lead us Out of the piece and altogether for me There’s something slightly more immature About the output from stable diffusion So many people have been commenting that The removal of nudity and celebrities From stable diffusion has had an impact On the anatomy inside of that works so Let’s just try a celebrity to illustrate This point this is Young Timothy Chalamet And you can see that the mid-journey Outputting gives a greater likeness to The man himself but what’s interesting Is that mid-journey is using a data set That is a few years old and this is Reflected in the age that we’re seeing Timothy at it’s also interesting that There is still Passing likeness to Timothy chalamet Into stable diffusion despite
Celebrities being removed from the data Set So if there’s still some sort of residue Left in the data set for stable Diffusion to still be able to identify And create a likeness But if we just look at the age of Timothy now looking much more adult than He does here there’s still this Boyishness next up we have an example Stock photo of a lion and stable Diffusion I would say is performing this Is the closest run we’ve had between the Images in terms of realism consistency Detail and general aesthetic mid-journey Version just brushes out the water I Think if you didn’t know that this was a Piece of AI art and you were just Glancing at it there’s no reason to Think that this might not even be a real Photo so going into more detail again The stock photo Area is one where stable diffusion is Catching up to mid-journey but there’s Something for me overall that Stable diffusion seems to have less Underlying taste and although the latest Data set that they’re using is supposed To be honest and aesthetic subset of the Image database the way that it creates Images are Generally for me much more rudimentary Immature and lacking in an aesthetic eye It kind of spits out a lot of the
Generic images you imagine to see on Stock sites Terrible stock photos now when you get Some very cheesy generic style images That are often very Overexposed and Highly saturated with unrealistic posed Frame situations something almost wooden And alien-like to them framing the Texture the approach for mid-journey is All the more Aesthetic and pleasing There’s something I would comment on is That my journey often has a tendency to Create things with a slightly Melancholic feel to them it often irrs On the side of melancholy on the deepest Level I believe we are most attracted to One of the things that bring us the most Joy but the things that allow us to see The darkness in ourselves And the depth of mid-journey is picking Up on this we don’t want all rainbows And butterflies sometimes we want to Explore our shadows And there’s a reflection at the deepest Level with mid-journey identifying this Inside of our culture finally we have a Landscape composition this is an Icelandic Beach and although stable Diffusion performs much better and Landscapes still lives And stock photos it’s not quite at the Same level as mid-journey for me Personally my view is that although
Stable diffusion is taking steps Forwards it’s also taking steps Backwards with anatomy and consistency Stepping down whilst Landscapes and Still life are stepping up I personally Will continue to use mid-journey for my Work let me know what you think in the Comments which is your favorite and what Are you looking forward to most in the Future I’m Samson Bowles this is Delightful design I have a delightful Day