▣ Upload your own images, AI training
①Click the + sign in the input box, there will be an upload file, double-click it to select the image to upload, enter.
② Right click on the image and select Copy Link.
③ Paste it directly behind the input box imagine prompt.
④After posting, leave a blank space (*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 between diagrams)
(6) Keyword skills, what, who, when, where, how, the 5 W's.
NSFW (Not Safe For Work), this part of the mention, will be rejected by the AI.
▣ Basic Instructions
/imagine
The most basic drawing commands. AI drawing can be done by entering a keyword after imagine.
/help
The bot pushes out some guides and basic help information. /subscribe to enter 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 use of relax mode.
/fast
FAST mode generates images. New users can generate 25 pictures; basic members can generate about 200 pictures/month; standard members can generate about 900 pictures/month. After that, you need to buy additional GPU time.
/relax
The relax mode generates images and is only available to standard members and above.
Unlimited usage time, but need to share GPU queuing time with other members for up to 3 tasks. Cannot use the Upscale to Max function (Upscale to Max).
/private
Created privately, the work will not be placed in a public space.
Private Creative Membership is only enabled for an additional $20! Don't click around after you enter, click and pay.
/public
Public creations, this is a preset value, when you accept the terms of use it will be stated that all creations are public. The work can be used for reference by others, and you can refer to other people's creations as well.
/show
Enter Job_ID after it to reproduce the drawing. Only enter your own creations, not other people's Job_IDs.
The ✉️:envelope:envelope symbol will send you the image's SEED and Job_ ID information. You will find the information sent to you by the bot in your personal private message.
⭐️:star:The star symbol marks the image as a "favorite". 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 piece of image information and also remove the image from the official website gallery.
/settings
Set current preferences first row: MJ version, select the current version in use. Currently v4 is a beta version and can only produce 1:1 images
Second row:
Test/Test Photo: Add more detail than by default with a generalized testability algorithm, or a photo reality enhancement algorithm.
Quality Level: Select the quality level of the preset output, in the order of 0.5/1(preset)/2.
The third row: Style level: choose to preset the intensity of the style of the picture, in order of 1250/2500 (preset)/5000/20000, the larger the number of the more self-expansion.
Fourth row: Upscale level: Select the detail level of the preset image: regular (preset)/light upscale/beta test file in order.
Row 5: Public mode/Private mode: Public mode and Private mode. When this mode is enabled, keyword modification will be enabled while pressing V. Fast mode/Relax mode: fast mode and infinite mode.
▣ Common Parameters
-beta:
Use beta testing algorithms.
-hd: use higher resolution algorithm. -aspect / -ar: set the image aspect ratio. Example: -ar 16:9. -w -h: Set image width and height. Example: -w 1024 -h 768. -seed: Set the seed. -sameseed: output the image 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, max 5). -stylize / -s: set the stylistic intensity, the larger the value the more sky-high, can be set to any integer between 625-60000. -quality / -q: set the quality of the picture, the higher the value the slower the picture time, the lower the value the faster the picture, more money. There are five settings (0.25, 0.5, 1, 2, 5). -chaos / -c: set the randomness of the picture, the larger the value the higher the randomness (0-100).
-fast:
Fast map output to save GPU usage time.
-stop:
What percentage (10-100) the picture stops at during the calculation. Example: -stop 80. -video: saves a video of the algorithm. Adding the reaction envelope symbol will private message the video to you. -v: Which version of the algorithm to use. Example: -v 4. -uplight: equals to use Light upscale, light plus one stop of detail. At the end of the keyword type 'space + bar + bar + parameter + space + value'.