Dayamn! ๐
196
Be sure to follow the rule before you head out.
Rule: You must post before you leave.
Couldn't have said it better!
Last year's version. No changes made to the source material, just Midjourney version. This version eliminated the facial hair. Newer versions of the software have stopped removing it.
i love cyberpunk 2020 and i havent even run a proper game yet because all the players have not made any characters in the like five day time period that i have been talking about starting thasgsglkhdsafgl;/sagbjkfdas,ghv,nf,l.dmasfvjdlfvj
Personally, I like to run a session zero with my players, as a group or independently. If it's a first timer group I recommend the Street Rat (template) method from Red. Every player picks a class then we run the Lifepath for each player in a group Session Zero. That way everyone at the table is familiar with the back story of each other's characters. So, the PCs know each other.
For subsequent games it might be better for the players to dial their characters in a bit better than the template (Edgerunners format), and work with you (the GM) in individual Session Zeros. That way they can each have extensive backstory only they and you know about but could affect the campaign later. Critical Role does this type of stuff every campaign and it can be fun.
If you wait for the players to do all this on their own, you'll wait indefinitely. It's more fun to do it with someone else.
What's the prompt/model?
I can share the text prompt (which is fairly simple) but there are four leading images that also compromise the prompt. One is a crop of my original art, one is a still from an anime I found on duck duck go, one is a photo of myself, and lastly still from Arcane. The Arcane still seems to add the beautiful shadowing and ensures that the results are non-binary since I am combining a photo of myself with a female character from the show. Without it I get similar results but far more anime looking.
EDIT: My style of Midjourney prompts are always image source heavy as it lets me steer the results significantly rather than leave it up to the AI's interpretation of my text prompt. The text portion of this prompt is something short like "cyberpunk rocker boy with cybernetic implants holding a gun". As you can see, the image leads overwrote most of the text prompt.