https://discord.gg/midjourney
) they can use./imagine
command and other commands listed below. Please note the images will still appear on your gallery unless you use /private./imagine
command and make images. On the Discord server, they are marked as "Image Generation" channels. Most commands below require you to be in a bot channel./show
command. You can now use the /show <jobid>
command to produce the resulting image and upscale+variation buttons, based on a job id.e8913dc8-75fa-4b7e-8b61-028b8f43c792
. It can be found in the first part of all image filenames, in the URLs on the website, and other places. It's a unique identifier, and you can only use /show
on jobs that you are the author of. This will also work on "refreshing" old jobs, so if your button click fails on something you made two months ago, you can use /show
on this job and continue prompting!/info
in a bot channel to check your subscription status and usage./fast
in a bot channel. This will enable fast generation, but you will be incrementally charged for each image if you are out of fast jobs./relax
in a bot channel. This will cost you nothing but images will take longer to generate./private
in a bot channel. This will make your images private and hidden from the website, but costs more. It's a subscription upgrade.https://discord.gg/midjourney
) they can use.--stop 80
and replace 80
with the % you want to stop at. Use --uplight
for the upscale to add less details, or redo it with the button "Light Upscale Redo" afterwards./imagine
prompt as normal, but then in the prompt section, paste in the web address where the image is stored online. After the link you can still add new text prompts to complement it. You can see some examples in the Imagine Parameters visual guide here.Copy Link Address
. This address will usually end in a .png
or .jpg
if it's a usable address. See the gif here for using one on Discord./imagine
and then paste the address in the prompt area./imagine
and then paste the address in the prompt area.::0.5
to give that part a weight of 0.5. If the weight is not specified, it defaults to 1./imagine hot dog::2 food::-1
- This sends a text prompt of hot dog
with the weight 2 and food
of weight -1./imagine hot dog::0.5 animal::-0.25
- Sends hot dog
of weight 0.5 and animal
of negative 0.25./imagine hot dog:: food::-1 animal::
- Sends hot dog
of weight 1, food
of weight -1 and animal
of weight 1 (unspecified weights default to 1)./imagine hot dog animal::-1
, as this will send the prompt of hot dog animal
with weight -1, because of how it parses the text before the colons.[image URL] [text prompt]
with no weights specified results in a 20% image(s) / 80% text generation.[image URL] [text prompt 1] --iw 1
Results in a 50% image(s) / 50% text generation.[image URL] [text prompt 1]::2 [text prompt 2]::3 --iw 1
results in a 1/6=17% image(s) , 2/6= 33% text1 , 3/6 = 50% text2.::
between prompts for a hard separator as describe in the answer above.--w 256 --h 320