Future Tech Pilot
People have been writing elaborate prompts for a long time now, but is it really necessary? Does the order of your words matter? Or is it just your ability to condense your idea into a succinct phrase?
Midjourneys new ‘Shorten’ Command helps us get to the bottom of some of these questions … but the results are less clear than I would have liked.
NEW FREE PDF: Prompt Ad-Libs
https://www.futuretechpilot.com/shop/p/prompt-adlibs-lite
NEW PROMPT PACK:
https://www.futuretechpilot.com/shop/p/prompt-adlibs
๐ณ Different Camera Lenses and Angles to use in your Prompts —
https://cameralens.futuretechpilot.com/
๐ณ 200 Aesthetics to change the look of your Prompt — https://200styles.futuretechpilot.com/
๐ณ A helpful little Cheat Sheet to remind you of the Midjourney Basics — https://cheatsheet.futuretechpilot.com/
Other Links:
Merch – https://FutureTechPilot.threadless.com
Discord – https://discord.gg/hK6AmynjAn
Creative Fabrica – https://www.creativefabrica.com/spark/ref/1323759
๐ yay, loving your channel
This is dope! I love MidJourney!
Why can't I save your videos? ๐ฅฒ
Educational – and will change how I prompt! Thank you for the insight.
more awesome content. Didn't know about the shorten prompt, just tried it. very cool. What would you say is the advantage of using –style raw? I haven't used it.
Nice! You can take –upbeta off your prompts btw, it isn't doing anything any more in the new versions ๐
COmbining describe and shorten has completely changed the way things can work. great piece
Awesome and informative video ๐
I love to deep dive into things as well, just never got around to looking at the shorten yet.
I think I remember David mentioning at one of the Office hours that the shorten is not exactly one to one with the Model, meaning that it tries to guess some things and is quite accurate there, but it can be off sometimes, because it is not actually tied to the image generation model. I have noticed that some words do actually make a difference in the end result even though the shorten detail view shows them at a really low priority or at 0.
Everybody says cutting out useless words makes for a better prompt, but from I've seen with my own experiments the shorter images lose depth/atmosphere/emotion. Compare the first image of Audrey Hepburn to your shortened images. Yours look flat and lifeless. So what is it with "ignored" words that flesh out an image?
Most likely, there is a lot of correlation between different words. For instance, with the artists, the fact that Dan Hillier did not seem to matter that much initially could easily be explained by suggesting that when it comes to the latent space of all dimensions from which an image is constructed, he is not significantly different than the other two artists. Their "essence" is already in the image, and if you change the order to nominally alter the weights, the actual representation of the styles does not change.
With a slightly more elaborate version of the argument above, I think you can explain the effect of the ordering on weights. You are shuffling the weights but not moving far from where you were in the high-dimensional latent space.
It's a hit and a miss sometimes, but the order does matter. Try and see how it weighs 'depth of field'. It's strange. 0.00 in many shorten prompts, but there's always a difference. Like the person's comment below, the language model and MJ's model are different, so that might be why there's sometimes inconsistency.
Thanks for the video. ๐
I'm going out on a limb here but I do think that Shorten is only or mostly useful for people who don't know how to prompt very well.
I've been checking Midjourney's feed and I've noted some prompts using codes like (#18fc49d7#), and in the docs I haven't seen anything about that prompting technique, have you? Do you know when and how to use it? Great channel!
Does anyone know what website lets you upload multiple images and then just click a button to get a blending animation between each image in one video? I saw a youtuber show it a few months ago and can't find it.