ICYMI: Chevy feeds its original photos into an AI to create an NFT series (and documents it all here). Follow on IG And Twitter for first glances.
Today I have a double dose of discovery and learning to fuel your AI/NFT degeneracy:
-
A 300m view of Midjourney
-
A great ancient discovery!
The 1000 ft view of Midjourney (aka how MJ works, so you can easily start tinkering).
The free (but messy) option:
Create a Discord account → Join the Midjourney Discord channel → go to one of the “#newbie” bot channels in the left column → type ‘/imagine’ followed by your text prompt.
The only problem with this option is that there are ~13 million members in the Midjourney Discord, with ~1.5 million people active at any one time.
Which means these channels are a mess of constant prompts and pictures being sent/received that quickly obscure the results of your prompts.
Here’s how to calm down the sound…
The free (and chill) option:
Refer at least 1 person to Web3 Daily (via this link: {{subscriber.rh_reflink}} ) → receive an email from us inviting you to join our Discord → Go to the “Midjourney” channel in the left column → type ‘/imagine ‘ followed by your text prompt.
(It’s much quieter and easier to follow/create this way).
Today’s great discovery!
You can send Midjourney multiple reference images.
Which means if you have a ‘reference image + text prompt’ combination serving up the goods, you can create new yet familiar creations by adding additional reference images.
It seems like a small discovery – but it really doesn’t get you started until you find a ‘reference image + text prompt’ that works.
For example:
This image, along with the prompt “Nasa, Saturn V, Soyuz, nasa uniform, loudspeaker system, satellite, radio tower, photo by Larry Sultan and Petra Collins” produced some absolute stunners…
Like so: