Notices by Steve Troughton-Smith (stroughtonsmith@mastodon.social), page 2

It's kinda fun to give Midjourney completely abstract or nonsense prompts just to see where the fever dream takes you

Blimey. These ain’t movie stills, this is Midjourney’s attempt at ‘live action Luca’

I scrolled back through my Midjourney history to remind myself what its generated images used to look like, about 18 months ago. The difference to today (second pic) is *astonishing*

Re-running last year's prompts (Midjourney v2) in Midjourney v6:

"a vector illustration of david bowie performing on stage, bright colors”

How do you quantify this kind of progress?

"The weeknd in the style of sin city, painterly”

Again, huge leap forward in v6

As a topic, I think this stuff is fascinating. If you're not keeping up with the bleeding edge on Midjourney, you would totally miss the huge improvements that have come to image generation since you last ran something like DiffusionBee on a Mac. It has gone from 'silly little images' to what I would say are stunning works of art and demonstrations of capability. I have no idea what this tech looks like one year from now, never mind ten

“50s album art depicting a 50s motorcar”

v2, v6

To get a feel for what kind of keywords will make for great Midjourney output, I like to pick an artist name and ask for a 'landscape by <name>’. A really basic prompt — effectively ‘when I say this person's name, what comes to mind?’; makes for an easy comparison point. Oftentimes generated art looks nothing like what that artist would actually create, but still conjures distinctive reusable style elements

Names used here:

1) David Hockney
2) Takashi Murakami
3) Yayoi Kusama
4) Kara Walker

Midjourney still lets you generate with each of its model versions, which is kinda neat! So I ran off the same prompt — "a boxer dog” — in the six major versions. V1 was released February 2022, V6 is the new alpha hotness

(Bonus points for the tiny doggy boxing glove)

‘Kehinde Wiley’ makes for an amazing seed for a prompt, though the generator seems to struggle with body parts (I've had to reject more images than usual to get to these few) — perhaps because the artist's own backgrounds are so busy it might be difficult for the network to separate elements?

Now that I have uncovered this hypothetical Kobold movie, I kinda want it to exist 😅 Studio pitch?

These kind of live-action stills are gonna do a number on the Mandela Effect hawkers 😅

A tip that's new to me; Midjourney's /describe function can take an uploaded image and spit out prompts that could guide it back to making more. And you can use this to reverse-engineer images it has generated in the past, of styles or elements you don't recognize, to figure out how to make follow-ups.

There are so many features buried in slash commands that I might never come across

Take your pick!

Just a happy little guy

Lesser-remembered thread in Love Actually

2024 gonna be like

We're a long way from anything like this happening, but, man, seeing Threads profiles light up here conjures a potential future where you might follow Instagram, TikTok, maybe even YouTube accounts and more right from Ivory. How much better could it be to be able to repost or quote-post the /original source item/ instead of a link to some external site every time. ActivityPub all the things!