Midjourney basic commands

Midjourney basic commands

March 9th, 2023

▣ Upload your own image, AI training ①Click on the + sign in the input box, there will be an upload file, double click on it and you can select the image to upload, enter. ②Right click on the image and choose copy link. ③Paste it directly into the input box after imagine prompt. ④After pasting, leave a space empty (*important*), then enter the text (can be comma-segmented) and parameters. ⑤Padding diagrams are not limited to only 1 diagram, but can also be mixed with more than 2 diagrams (remember to space in diagrams and diagrams) ⑥Keyword tips, what, who, when, where, how, 5 W's. NSFW (Not Safe For Work) , this part of mentioning words, will be rejected by AI. ▣ Basic commands /imagine The most basic drawing command. Input the keyword after the imagine to draw by AI. /help The robot will push some guide and basic help information. /subscribe to access the subscription channel. Basic membership ($10/month): 200 minutes of GPU usage per month (fast mode). Standard membership ($30/month): 15 hours of GPU usage per month (fast mode) and unlimited access to relax mode. /fast Fast mode generates images. New users can generate 25 images; basic members can generate approximately 200 images/month; standard members can generate approximately 900 images/month. GPU time must be purchased separately after this. /relax Relax mode generates images and is only available to Standard members and above. Unlimited usage time, but GPU queue time must be shared with other members and a maximum of 3 tasks can be performed. Upscale to Max function is not available. /private Private creations, which will not be placed in the public space. Only available to Private Creations members for an additional $20! Don't click on it after you enter it, you'll pay if you do. /public This is a pre-defined value. When you accept the terms of use, you will be informed that all work is public. You can also refer to other people's creations. /show This is followed by the Job_ID to reproduce the painting. You can only enter your own creations, not the Job_IDs of others. The ✉️:envelope:envelope symbol will send you the seed and Job_ ID information of the image. You will find the information sent to you by the bot in your personal private message. ⭐️:star:The star symbol will mark the image as a "favourite". Send the image to the public #favorites channel and add it to your bookmarks on the official website. The ❌:x:fork symbol will cancel or delete this image message and will also remove the image from the official website gallery. /settings sets the first row of current preferences: MJ version, select the version currently in use. Currently v4 is a beta version and can only produce 1:1 images Second row. Test/Test Photo: adds more detail than the default with a generic testability algorithm, or photo reality enhancement algorithm. Quality level: select the preset quality level of the image, in order of 0.5/1(preset)/2. Third row: Style level: select the preset style intensity of the image, in order of 1250/2500(preset)/5000/20000, the higher the number the more you can let yourself go. Fourth row: Upscale level: selects the level of detail of the preset image: regular (preset) / light high / beta test in that order. Fifth row. Public mode/Private mode: public mode and private mode. Remix mode: remix mode. When this mode is enabled, the keyword modification function will be activated while pressing V. Fast mode/Relax mode: Fast mode and infinite mode.  Common parameters of ▣ --beta. Use the beta test algorithm. --hd: use higher resolution algorithm. --aspect / --ar: set the aspect ratio of the image. Example: --ar 16:9. --w --h: Set the width and height of the image. Example: --w 1024 --h 768. --seed: Sets the seed. ---sameseed: output the picture in a seed-like composition. --no: exclude an object. Example: --no people. --iw: set the weight of the reference image, the higher the value the closer it is to the reference image. (default 0.25, maximum 5). --stylize / --s: set the style intensity, the higher the value the more pervasive it is, can be set to any integer between 625 and 60000. --quality / --q: sets the quality of the image, the higher the value the slower the image time, the lower the value the faster the image will come out and the more money it will save. There are five settings available (0.25, 0.5, 1, 2, 5). --chaos / --c: sets the randomness of the image, the higher the value the higher the randomness (0-100). --fast. Fast image output, save GPU usage time. --stop. What percentage (10-100) the image will stop at when it is calculated. Example: --stop 80. --video: Save a video of the algorithm. Add the reaction envelope symbol and the video will be sent to you privately. --v: Which version of the algorithm to use. Example: --v 4. --uplight: equals using Light upscale, light plus one stop of detail. At the end of the keyword enter 'space + horizontal bar + horizontal bar + parameter + space + value'.


no dataCoffee time! Feel free to comment