Welcome to the exciting world of video creation with Midjourney! You can now turn a single image into a dynamic 5-second video.
It's as simple as feeding Midjourney an image to serve as the first frame, adding a text prompt (optional), and then watch as it brings your vision to life with a moving sequence.
• All plan tiers can generate videos in Fast Mode, but only Pro and Mega plans can generate videos in Relax Mode (SD resolution only).
• Standard, Pro, and Mega plans can generate HD resolution videos, but only in Fast Mode.
• Videos cost more GPU time compared to regular images. For a detailed breakdown of costs, see the Batch Size section below.
• Video generations are only compatible with video-specific parameters: --motion low, --motion high, --raw, --loop, --end, and --bs #.
Video tutorial: Watch this quick tutorial on video creation below.
Head to midjourney.com to start creating videos! If you need help accessing our website, check out our Logging In & Connecting Accounts article.
\nIf you use Midjourney via Discord, please make sure you log in using the \"Continue with Discord\" option.
\nAll images in your gallery (regardless of what version they were made in) now have Animate Image buttons below the Creation Actions section when you open them. You'll also see a shortcut button when you hover your mouse over them from the Create page.
\nThe Animate Manually link will give you an opportunity to adjust the text prompt in the Imagine bar before generating the video.
\nThe Auto buttons will automatically start generating a video using your image.
\nThe Loop buttons will automatically start generating a looping video using your image (meaning the starting frame and ending frame are the same image).
\nFor information on \"Low Motion\" and \"High Motion\" check out the Video Motion section below.
\nNote: Any image parameters used to generate your original image will be automatically removed when generating videos.
\nTo select an image to animate, start by clicking on the image icon in the Imagine bar. This opens the images panel, allowing you to upload new images or pick from those you've already uploaded.
Click your image in the uploads library to automatically add it as a Starting Frame, or drag and drop it into the Starting Frame section. To remove your image from the Imagine bar, hover your mouse over it and click the X icon.
\nIf you want to use your images with multiple prompts, click the lock icon to keep your images pinned to the Imagine bar.
Other Image Reference Types (not compatible with video generations): Image Prompt
Style Reference
Omni Reference (V7)
After your image is generated, use the U1 U2 U3 U4 buttons to separate your favorite image from the initial grid.
Once separated, use the Animate (High motion) or Animate (Low motion) buttons to generate a video. If you have Remix Mode turned on, you can edit the prompt text before submitting the video prompt.
Note: In Midjourney versions 5 and later the U# buttons separate your image from the grid but do not change its size, so they do not consume GPU time. In earlier versions these buttons do increase your image size, and will consume GPU time.
Don't see the Animate buttons? If you have upscales in Discord that were made before the release of video generations, you can use the show command to refresh the buttons.
\nTo generate a video using your own image, paste your image URL at the beginning of your prompt and then add the --video parameter to the end of your prompt. A text prompt is optional.
It's important to ensure that you have a valid image URL, meaning the image should already be online. If your image is stored on your computer or device, you can host it on Discord to generate an image URL.
\nMidjourney provides you with powerful tools for unleashing your imagination. When using our tools to create with external images, we have additional necessary precautions you should be aware of.
\nBy using external images with Midjourney, you agree to the following rules in addition to our Terms of Service.
\nIf you disagree with these rules, do not use Midjourney with external images.
\nYou will likely encounter friction with our moderation — seemingly innocent prompts may be blocked by our filters. Blocked jobs don't cost you any credits. GPU time will only be deducted when you see your results.
\nWe encourage you to use this tool and your imagination with joy, wonder, responsibility, and respect.
\nFor additional information on policies, including privacy, payments, and disputes, refer to our Terms of Service.
\nBy default Midjourney will generate 4 videos from each video prompt. If you want to conserve GPU time, you can choose to generate only 1 or 2 videos from each prompt instead. Batch sizes work in both Fast and Relax Mode.
| \n | Batch 4 GPU Cost | \nBatch 2 GPU Cost | \nBatch 1 GPU Cost | \n
|---|---|---|---|
| SD Resolution | \n8 mins | \n4 mins | \n2 mins | \n
| HD Resolution | \n26 mins | \n13 mins | \n7 mins | \n
Add --bs # to the end of your prompt in the Imagine bar. You can use 1, 2, or 4.
You can choose a default batch size for all your video prompts in the settings panel. To do this, click the settings button in the Imagine bar and set the Video Batch Size under More Options. Once you set it, this will apply to all your future video prompts.
Add --bs # to the end of your prompt in Discord. You can use 1, 2, or 4.
Video generations start at 5 seconds, but it doesn't have to stop there. After your video is created, you’ll see options to extend it further. This will add another 4 seconds to your video.
Feel free to extend your video up to 4 times, until it reaches 21 seconds, which is the maximum length available.
Extending a video costs the same amount of GPU time as an initial video generation.
U1 U2 U3 U4 buttons to separate your favorite video from the initial grid, and then look for the Extend (High motion) and Extend (Low motion) buttons. If you have Remix Mode turned on, you can edit the prompt text before submitting the extension prompt.After selecting an image to use as your starting frame, you also have the option to set an ending frame. You can reuse the starting frame to create a looping video, or add a different image as your ending frame.
Once you add an image to the Starting Frame section of the Imagine bar, some additional video options will appear.
\nIf you want to re-use the starting frame as your end frame (this will create a looping video), use the \"Loop\" checkbox in the Ending Frame section.
\nTo use a different image as your ending frame, add it to the Ending Frame section.
\nIf you want to re-use the starting frame as your end frame (this will create a looping video), add --loop to the end of your video prompt.
To use a different image as your ending frame, add the --end parameter to your video prompt and paste your image URL.
It's important to ensure that you have a valid image URL, meaning the image should already be online. If your image is stored on your computer or device, you can host it on Discord to generate an image URL.
\nWhen generating videos, you have two motion settings options to choose from, \"Low Motion\" and \"High Motion.\" Use the corresponding buttons, or add the --motion low or --motion high parameters to the end of your video prompt.
You can also change your default motion setting by loading an image into the Starting Frame section of the Imagine bar and toggling the settings in Motion Amount.
For more precise motion control of your video creations, using the --raw parameter in your video prompts can be helpful. This feature works similarly to Raw Mode for images.
When you add --raw, it reduces the extra creative flair that Midjourney usually adds, allowing your prompt text to have more influence on the outcome.
Midjourney videos are generated in 480p quality, also called Standard Definition (SD). If you have the Standard, Pro, or Mega plan you can also generate videos in 720p quality, or High Definition (HD), by adjusting your Video Resolution under More Options in the settings panel of the Imagine bar .
The exact shape and size of your video is based on the aspect ratio of your starting image. If you upload your generated video to another video-sharing platform, the quality will be classified as 480p or 720p.
The table below shows how different starting image aspect ratios will affect your video's pixel dimensions:
| Starting Image Aspect Ratio | \nVideo Aspect Ratio* | \nSD Dimensions | \nHD Dimensions | \n
|---|---|---|---|
| 1:1 | \n1:1 | \n624 x 624 px | \n960 x 960 px | \n
| 4:3 | \n77:58 | \n720 x 544 px | \n1104 x 832 px | \n
| 2:3 | \n2:3 | \n512 x 768 px | \n784 x 1168 px | \n
| 16:9 | \n91:51 | \n832 x 464 px | \n1280 x 720 px | \n
| 1:2 | \n1:2 | \n448 x 880 px | \n672 x 1360 px | \n
*Midjourney may need to adjust the aspect ratio slightly in some cases. This means that your video's aspect ratio may be a little different than your starting image.
Once your videos have finished generating on the Create page, hover your mouse over them to play them.
You can also manually scrub (play the videos at your own speed) by holding the Control or Command key on your keyboard and moving your mouse back and forth over them.
When you right-click on a video from your Create or Organize page, you'll see three download options:
Downloading videos from Discord will download the raw video file.
"},{"id":33390994570509,"url":"https://midjourney.zendesk.com/api/v2/help_center/en-us/articles/33390994570509.json","html_url":"https://docs.midjourney.com/hc/en-us/articles/33390994570509-Logging-In-Connecting-Accounts","author_id":18023535838733,"comments_disabled":false,"draft":false,"promoted":false,"position":0,"vote_sum":0,"vote_count":0,"section_id":27646234144397,"created_at":"2025-01-10T21:56:25Z","updated_at":"2026-02-26T22:44:28Z","name":"Logging In & Connecting Accounts","title":"Logging In & Connecting Accounts","source_locale":"en-us","locale":"en-us","outdated":false,"outdated_locales":[],"edited_at":"2026-02-26T22:44:28Z","user_segment_id":null,"permission_group_id":33673142591629,"content_tag_ids":[],"label_names":[],"body":"Whether you're joining us for the first time or you're a returning member, it's important to log in with the correct account. This helps make sure you can enjoy using Midjourney on both our website and Discord without any issues. Every Midjourney plan lets you use both platforms—it's all about setting things up correctly.
If you’re new here, we’re excited to have you! Here’s how you can create an account:
Right now, you can create a Midjourney account using either a Discord account or a Google account. We don't have the option to create a username and password specific just to Midjourney. You will need to use Google or Discord as your login method.
Welcome back to Midjourney! If you've used our service before, even just a free trial, chances are it was before August 2024. Back then, Discord was the only option for account creation. To access your old image history and ensure a smooth experience, it’s crucial to log in with your Discord account first.
Warning: If you log in with Google and create a new subscription, you will not be able to connect a Discord account with past image history.
How to Reconnect:
Remember, starting with your Discord login is key to ensuring that everything syncs correctly. Once you're all set, feel free to explore and create new images. Welcome back and happy creating!
All our plans allow you to use Midjourney both on our website and in Discord. But if you want to make images in Discord, you will need to have a Discord account connected to your Midjourney account. You can do this, as well as add a Google login, on your Account Settings page on midjourney.com
In the Connected Accounts section, you'll find your login methods displayed along with their details. If a login method isn't connected yet, you will see a Connect button next to it. Just click this button to proceed with linking your account.
Set a unique, public user name that will be used in your public profile URL and in the file names of your downloaded images and videos. Your display name will be used on the Explore page and in the filenames of your creations.
Both of these can be edited and updated at any time.
Your Midjourney ID is also shown on this page. When you contact billing support, providing this ID is really helpful and highly encouraged. This helps us assist you more quickly and effectively.
Accounts can only be disconnected by our billing support team. If you need help with this, please reach out to billing support. You may be required to verify your account ownership before your login method can be disconnected.
Your account must have one method connected at all times, so make sure you have a secondary method already connected before contacting support.
If you're having trouble connecting your accounts or logging in, you might see a message like this:
This often occurs if you log into midjourney.com using Google, subscribe to a plan, and then try to connect a Discord account that has already created images with Midjourney. Each account now has its own image gallery, so they can't be linked or connected.
Solutions:
This means there’s already an account registered with that email address.
Solutions:
Our website is designed to ignite your imagination and provide all the tools you need to turn your ideas into stunning images and videos.
For newcomers, or if you just want a refresher on getting started, check out our Getting Started Guide.
Dive into the Explore page, the community showcase where you can browse a stunning array of images and videos crafted by fellow members.
With a search bar and views like For You, Random, Hot, and Top (by day, week, or month), it's easy to find personalized, popular and trending creations. The For You view is based mostly on your Global V7/V8 Personalization Profile.
Clicking on any image or video reveals details about its creator, prompt, and settings.
Hovering over an image or video will give you handy shortcuts to reuse the image and prompt text in your own prompts, find similar visuals, or like the image. Use the Likes view to see all your
liked images.
The Style Explorer is a visual way to discover new Style Reference codes (also called Style codes) and find inspiration for your creations. You can browse Style codes, try them instantly, and even save your favorites for later.
Click any Style code to open a gallery of example images that showcase its unique look. From there, you can:
--sref code to the Imagine barIf you find a Style code you love, hit the Like button to save it. Your favorites are collected under the Likes tab, making it easy to revisit and reuse your go-to Style codes whenever inspiration strikes.
Note: Liking style codes does not affect your Personalization profiles.
The Create page is the heart of your creation journey. It's where you bring your ideas to life and see your images and videos generate in real-time.
Once your creations are complete, they'll be right there for you to admire and fine-tune. This page is packed with tools and features that make it simple to continue evolving your work and modifying your creations. For more detailed information, see our Creating on Web article.
The Edit page is where you can access the Midjourney Editor, your gateway to uploading and editing any image using our advanced tools.
For more information, see our Editor article.
The Personalize page is your go-to place for creating custom image aesthetics by rating images. The Moodboards page lets you curate sets of images to create a unique look. You can manage multiple styles with both, capturing unique vibes or moods to meet your creative goals.
For more information, see our Personalization and Moodboards articles.
The Organize page is your hub for managing everything you create with Midjourney. You can search, filter, and sort your images and videos to easily navigate and organize your work.
Arrange your creations using folders or explore your work by date through the timeline bar.
Bulk actions make it easy to manage multiple images at once, whether you're liking, trashing, or organizing them further.
This page is all about keeping your creations organized and easily accessible. For more detailed information, see our Organizing Your Creations article.
The Tasks page is where you can dive into activities that help tailor your Personalization profiles and potentially earn some rewards. By participating in image ratings and surveys, you contribute valuable input, helping to shape community choices and future tools.
Plus, when you complete these tasks, you may earn extra benefits like additional GPU time. For more information, see our Complete Tasks article.
With your Midjourney subscription, you have the freedom to create images on both our website and Discord. Most features and tools are offered on both platforms, but sometimes they might have different names. You can choose the one that fits your style, or enjoy using both! If you need help connecting your subscription to Discord, check out our Connecting Accounts article.
Take a look at the table below to explore the key differences and similarities between making images on midjourney.com and Discord.
| Tool / Feature | \nmidjourney.com | \nDiscord | \n
|---|---|---|
| Making Images with Others | \n||
| Making Images on Your Own | \n||
| Chatting with the Community | \n||
| Editor | \n||
| Trashing Images | \n||
| \nCustom Suffixes & Option Sets* | \n||
| \nPublic/Private Images (after creation) | \n||
| Manage Personalization Profiles | \n
*Option Sets can be used on midjourney.com in prompts, but they can only be created and managed in Discord.
On midjourney.com, the Editor is your go-to for making precise tweaks to your images. With everything in one user-friendly spot, you can crop, Pan, and adjust the aspect ratio (and more!) all at the same time. Discord offers panning and aspect ratio changes too, but you'll need to do each step separately, which gives you a bit less control.
A standout feature of the Editor is that the Vary Region inpainting tool is built right into it. This lets you re-generate parts of your image while you make other changes, giving you a smoother creative experience.
Using your own images to guide your Midjourney creations is incredibly easy on midjourney.com. With the click of a button you can designate your image as an Image Prompt, Style Reference, or Character Reference—even use it as all three! Plus, you can swiftly add any of your Midjourney creations from your gallery to your prompt without hassle.
If you’re on Discord, you can still use reference images. However, you’ll first need to host your image on Discord, grab the image URL, and then add it to your prompt along with any specific parameters. It’s a bit more hands-on, but still doable!
Mixing and matching prompt text, image references and style references is a breeze on the website. In each image's \"Creation Actions\" section, you'll find \"Use\" tools. These let you effortlessly reuse prompt text and the image itself, making it simple to craft new prompts.
On Discord, you can achieve similar results, but it takes more manual steps. You’ll need image URLs, and you might find yourself copying, pasting, or using the re-roll 🔄 button to get everything just right.
"},{"id":33329261836941,"url":"https://midjourney.zendesk.com/api/v2/help_center/en-us/articles/33329261836941.json","html_url":"https://docs.midjourney.com/hc/en-us/articles/33329261836941-Getting-Started-Guide","author_id":18023535838733,"comments_disabled":false,"draft":false,"promoted":false,"position":0,"vote_sum":0,"vote_count":0,"section_id":33324274255373,"created_at":"2025-01-09T00:00:56Z","updated_at":"2026-03-24T21:29:25Z","name":"Getting Started Guide","title":"Getting Started Guide","source_locale":"en-us","locale":"en-us","outdated":false,"outdated_locales":[],"edited_at":"2026-03-24T21:29:25Z","user_segment_id":null,"permission_group_id":33673142591629,"content_tag_ids":[],"label_names":[],"body":"Before you dive into creating your first masterpiece, you'll need to subscribe to one of our plans. Here's how you can get started:
Video tutorial: Watch this quick video tutorial on making your first image below.
Writing and crafting prompts can be an art in and of itself. To learn more, check out our Prompt Basics and Art of Prompting articles.
Midjourney is even better with Personalization. Create moodboards and custom Personalization profiles that will help Midjourney generate images that uniquely match your individual style!
The creativity doesn't stop here! Learn how to enhance and refine your creations using upscalers, variations, zoom out, pan, Editor, and more in our Modifying Your Creations article.
Make your images come alive by transforming them into videos! Learn how to animate both your Midjourney creations and your own images on our Video article.
You can change your default generation settings at any time by clicking on the settings icon in the Imagine bar.
For more information on each setting, check out these articles: Aspect Ratio, Raw, Version, Draft Mode, Stylize, Weird, Variety, GPU Speed, Stealth, Video Resolution, and Video Batch Size.
Did you know that you can also provide Midjourney with images—not just text—to guide your creations?
Video tutorial: Watch this quick video tutorial on using images below.
For more information about all the tools and features available on your Create page, check out our Creating on Web article.
Your Organize page offers a clear view of all your Midjourney creations. Here, you can download, sort, and filter your creations. You can also organize them into folders easily. For more tips and tricks, check out our Organizing Your Creations article.
To ensure a safe and happy creative environment, stay informed about our Community Guidelines.
Feel like sharing your works of art? Connect with our community and seek guidance from fellow Midjourney enthusiasts or our helpers in our Discord server.
If you need help with your account or subscription, you can browse helpful billing articles or contact our billing team.
"},{"id":32859204029709,"url":"https://midjourney.zendesk.com/api/v2/help_center/en-us/articles/32859204029709.json","html_url":"https://docs.midjourney.com/hc/en-us/articles/32859204029709-Parameter-List","author_id":18023535838733,"comments_disabled":false,"draft":false,"promoted":false,"position":0,"vote_sum":0,"vote_count":0,"section_id":33329522730509,"created_at":"2024-12-19T15:58:36Z","updated_at":"2026-06-11T19:53:15Z","name":"Parameter List","title":"Parameter List","source_locale":"en-us","locale":"en-us","outdated":false,"outdated_locales":[],"edited_at":"2026-06-11T19:53:15Z","user_segment_id":null,"permission_group_id":33673142591629,"content_tag_ids":[],"label_names":[],"body":"Parameters are like special instructions you can use to guide how your images turn out. They help you customize things, like changing the shape of an image, or using a Personalization profile.
Parameters always go at the end of your text prompt, after you've described what you want to see. Using them successfully is all about placement and formatting.
vibrant California poppies--ar 2:3 (No space before the dashes)
vibrant California poppies - - ar 2:3 (Extra space between the dashes)
vibrant California poppies --ar 2:3, (Using punctuation in parameters)
vibrant California --ar 2:3 poppies (Prompt text after parameters)
| \nAspect Ratio Midjourney images start as squares, but you can change this using the aspect ratio parameter --aspect or --ar | \n\nChaos Spice up your image results with the chaos parameter --chaos or --c | \n\nOmni Reference Want to use a person's likeness or the form of an object? You can provide Midjourney with an Omni Reference! (replaces Character Reference in V7) --oref | \n
| \nNo Tell Midjourney what you don't want in your image using the no parameter --no | \n\nPersonalization Create custom image styles with personalized profiles and moodboards --profile or --p | \n\nQuality Control the detail and processing time of your images with the quality parameter --quality or --q | \n
| \nRepeat Want to generate multiple image sets from a single prompt? Use the repeat parameter --repeat or --r | \n\nSeed Use the seed parameter for testing and experimenting --seed | \n\nStealth Mode Make your creations private on the Midjourney website --stealth | \n
| \nRaw Mode Gain more control over your images with Raw Mode --raw | \n\nStylize Control the artistic flair in your images with the stylize parameter --stylize or --s | \n\nStyle Reference Want to match the look and feel of another image? You can provide Midjourney with a Style Reference! --sref | \n
| \nTile Create seamless repeating patterns with the tile parameter --tile | \n\nVersion Explore and switch between Midjourney's model versions using the version parameter --version or --v | \n\nDraft Generate draft images in V7 at half the GPU cost using --draft | \n
| \nWeird Make your images quirky and unconventional with the weird parameter --weird or --w | \n\nFast Mode Switch your GPU speed to Fast Mode --fast | \n\nImage Weight Control the impact of image prompts --iw | \n
| \nRelax Mode Switch your GPU speed to Relax Mode --relax | \n\nTurbo Mode Switch your GPU speed to Turbo Mode --turbo | \n\nNiji Use our model focused on anime and Eastern aesthetics --niji | \n
| \nPublic Mode Make your creations public on the Midjourney website --public | \n\nMotion Low/High Motion settings for video generations --motion low and --motion high | \n\nVideo Looping & End Frames Create looping video generations with --loop and set a custom end frame using --end | \n
| \nBatch Size Control the number of videos generated from each video prompt using --bs | \n\nStyle Weight Control the strength of your Style References with --sw | \n\nStyle Reference Versions Select your style reference version using --sv | \n
| \nVideo Generate videos in Discord using --video | \n\nSD / HD Images Generate V8.1 images at higher resolution (2048px) using --hd or in standard resolution (1024px) using --sd | \n\n |
For information about legacy parameters, visit our Legacy Features article.
"},{"id":32083055291277,"url":"https://midjourney.zendesk.com/api/v2/help_center/en-us/articles/32083055291277.json","html_url":"https://docs.midjourney.com/hc/en-us/articles/32083055291277-Terms-of-Service","author_id":18023535838733,"comments_disabled":false,"draft":false,"promoted":false,"position":0,"vote_sum":0,"vote_count":0,"section_id":33329694407821,"created_at":"2024-11-21T23:14:16Z","updated_at":"2026-08-17T20:06:41Z","name":"Terms of Service","title":"Terms of Service","source_locale":"en-us","locale":"en-us","outdated":false,"outdated_locales":[],"edited_at":"2026-05-27T23:54:08Z","user_segment_id":null,"permission_group_id":33673142591629,"content_tag_ids":[],"label_names":[],"body":"
Version Effective Date: May 27, 2026
Thank you for using the Midjourney platform. These Terms of Service (“Terms”) govern the relationship between Midjourney, Inc. (“Midjourney”,”we”,”our”) and the entity or person (“Customer, “You”, “Your”) using or accessing our services, applications, or platform through our website available at midjourney.com (the “Site”), through any of our Discord servers, or by any other means (together, the “Services”). These Terms explain what rights you have with respect to images, videos, and other assets which you might generate with the Service (the \"Assets\"), or prompts you might enter into the Service (the “Inputs”), your use of the Services, and other important topics like arbitration. Our privacy policy outlines how we handle your data here. Please carefully read these Terms, along with our privacy policy, and all other documents referenced in these Terms, including the Subscription Plans page and the Community Guidelines below. Together with the Terms, these documents form a single binding agreement between us (the “Agreement”).
This Agreement is effective when the Customer is presented with this Agreement and proceeds to use or access the Services (the \"Effective Date\") or to receive or distribute Assets. This agreement may be updated and presented again to the Customer from time to time. Continued use of the Services constitutes acceptance of the updated terms. If You do not agree to this Agreement, please stop using or accessing the Services.
We are constantly improving the Services to make them better. The Services are subject to modification and change, including but not limited to the art style of Assets, the algorithms used to generate the Assets, and features available to the Customer. No guarantees are made with respect to the Services’ quality, stability, uptime or reliability. Please do not create any dependencies on any attributes of the Services or the Assets. We will not be liable to You or Your downstream customers for any harm caused by Your dependency on the Service.
Both the Services and the Assets are provided to Customer on an \"AS IS\" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Assets and assume any risks associated with use of the Services.
Midjourney reserves the right to suspend or ban Your access to the Services at any time, and for any reason. You may not access or use the Services for purposes of developing or offering competitive products or services. You may not reverse engineer the Services or the Assets. You may not use automated tools to access, interact with, or generate Assets through the Services. You may not resell or redistribute the Services or access to the Service. Only one user may use the Services per registered account. Each user of the Services may only have one account.
You may not use the Service to try to violate the intellectual property rights of others, including copyright, patent, or trademark rights. Doing so may subject you to penalties including legal action or a permanent ban from the Service.
We reserve the right to investigate complaints or reported violations of this Agreement and to take any action we deem appropriate including but not limited to reporting any suspected unlawful activity to law enforcement officials, regulators, or other third parties and disclosing any information necessary or appropriate to such persons or entities relating to user profiles, e-mail addresses, usage history, posted materials, IP addresses and traffic information.
By accessing the Services, You confirm that You are at least 13 years old and meet the minimum age of digital consent in Your country. If You are old enough to access the Services in Your country, but not old enough to have authority to consent to our terms, Your parent or guardian must agree to our terms on Your behalf.
Please ask Your parent or guardian to read these terms with You. If You are a parent or legal guardian, and You allow Your teenager to use the Services, then these terms also apply to You and You are responsible for Your teenager’s activity on the Services.
Midjourney tries to make its Services PG-13 and family friendly, but the Assets are generated by an artificial intelligence system based on user queries. This is new technology and it does not always work as expected. No guarantees are made as to the suitability of the Assets for the Customer.
By using the Services, You may provide Midjourney with personal information like Your email address, user name, billing information, favorites, outputs, and text prompts that You enter, or sample images or other content that You upload to the Service. Our privacy policy can be found here.
You own all Assets You create with the Services to the fullest extent possible under applicable law. There are some exceptions:
Please consult Your own lawyer if You want more information about the state of current intellectual property law in Your jurisdiction. Your ownership of the Assets you created persists even if in subsequent months You downgrade or cancel Your membership.
Inputs, Assets, and other content such as messages, photos, videos, and documents that you may provide to the Services (such as through uploading, posting, sharing, or chat messages) are collectively, “Content”. You are responsible for all Content that you provide or generate, including ensuring that it does not violate any applicable laws or this Agreement, and that you have all necessary rights and permissions to provide the Content.
By using the Services, You grant to Midjourney, its affiliates, successors, and assigns a perpetual, worldwide, non-exclusive, sublicensable no-charge, royalty-free, irrevocable copyright license to reproduce, prepare derivative works of, publicly display, publicly perform, sublicense, and distribute the Content You input into the Services, as well as any Assets produced by You through the Service. This license survives termination of this Agreement by any party, for any reason.
Please note: Midjourney is an open community which allows others to use and remix Your Content whenever they are posted in a public setting. By default, Your Content is publicly viewable and remixable. As described below, You grant Midjourney a license to allow this.
If You purchased the Stealth feature as part of Your “Pro” or \"Mega\" subscription or through the previously available add-on, we agree to make best efforts not to publish any Assets You make in any situation where you have engaged stealth mode in the Services.
Please be aware that any Assets You make in a shared or open space, such as a Discord chatroom, is viewable by anyone in that chatroom, regardless of whether Stealth mode is engaged.
Notification Procedures
We respect the intellectual property rights of others. If you believe that material located on or linked to by the Services violates your copyright or trademark, please send a notice of claimed infringement by using this form or by email to takedowns@midjourney.com with the subject \"Takedown Request\", and include the following:
You may also send notices containing the above-required information to the following Address:
Midjourney, Inc.
Attn: Takedowns Department
611 Gateway Blvd. Ste 120
South San Francisco, CA, 94080-7066,
US
Upon receipt of a notice that complies with the foregoing, we reserve the right to remove or disable access to the accused material or disable any links to the material; notify the party accused of infringement that we have removed or disabled access to the identified material; and terminate access to and use of the Services for any user who engages in repeated acts of infringement.
Please be aware that if you knowingly misrepresent that material or activity on the Services is infringing your copyright, you may be held liable for damages (including costs and attorneys’ fees) under Section 512(f) of the DMCA.
Counter-Notification Procedures
If you believe that material was removed or access to it was disabled by mistake or misidentification, you may file a counter-notification with us by submitting a written notification to our copyright agent designated above. Such notification must include substantially the following:
In the event a dispute, controversy, or claim arises out of or relating to these Terms (“Dispute”), the Dispute will be resolved by binding arbitration rather than in court. The parties will first try in good faith to settle any Dispute within 30 days after the Dispute arises. If the Dispute is not resolved within 30 days, it shall be resolved by binding arbitration by the American Arbitration Association’s International Centre for Dispute Resolution in accordance with its Expedited Commercial Rules in force as of the date of this Agreement (\"Rules\"). The parties will mutually select one arbitrator. The arbitration will be conducted in English in Santa Clara County, California, USA. By agreeing to mandatory arbitration as set forth herein, You and Midjourney knowingly and irrevocably waive any right to trial by jury in any action, proceeding, or counterclaim, except that either party may apply to any competent court for injunctive relief necessary to protect its rights pending resolution of the arbitration. The arbitrator may order equitable or injunctive relief consistent with the remedies and limitations in the Agreement. The arbitral award will be final and binding on the parties and its execution may be presented in any competent court, including any court with jurisdiction over either party or any of its property.
Each party will bear its own lawyers’ and experts’ fees and expenses, regardless of the arbitrator’s final decision regarding the Dispute.
If You purchase an unlimited plan, we will try to reasonably offer You unlimited access to the Services. However, we reserve the right to rate limit You to prevent quality decay or interruptions to other customers.
We may invoice You for Your use of the Services through a third party payment service provider. The third party service provider’s terms of service shall govern and supersede this Agreement in case of conflict, solely with respect to payment processing.
You are free to cancel Your plan at any time. We reserve the right to modify or discontinue any aspect of the Service, including pricing and features, at any time. We also reserve the right to terminate Your access to the Service for any reason, including for violation of the Community Guidelines or other inappropriate use of the Service. Any violation of Community Guidelines is a breach of this Agreement. You will not be refunded for the current subscription period, but You will not be charged after the current subscription period has ended. Additional information and policies regarding our subscription plans, including details on billing, taxes, refunds, and authorization, can be found here.
We provide the service as is, and we make no promises or guarantees about it.
You understand and agree that we will not be liable to You or any third party for any loss of profits, use, goodwill, or data, or for any incidental, indirect, special, consequential or exemplary damages, however they arise. Our aggregate liability under this Agreement will not exceed the amount You paid for the Services that gave rise to the claim during the 12 months before the claim.
You are responsible for Your use of the service. If You harm someone else or get into a dispute with someone else, we will not be involved.
To the extent permitted by law, you will indemnify and hold us harmless, our affiliates, and our personnel, from and against any costs, losses, liabilities, and expenses (including attorneys’ fees) from third party claims arising out of or relating to your use of the Services and Assets or any violation of these Terms.
You and Midjourney agree that any cause of action arising out of or related to the Services must commence within one (1) year after the cause of action accrues. Otherwise, such cause of action is permanently barred.
Midjourney’s Image Editor tool (“Editor”) and the Video Model (\"Video\") are provided as part of the Services and are subject to the terms and conditions outlined in this Agreement. By accessing and using Editor and/or Video, you agree to comply with the conditions set forth in this section, which govern Editor and Video availability and usage. If you do not agree to these Editor and Video terms and conditions, you must not access and must stop using the tool.
Subject to your compliance with this Agreement, Midjourney grants you the right to access and use Editor and Video. In using these tools, you shall not violate any applicable laws, this Agreement, Midjourney Community Guidelines, or any other Midjourney policies or guidelines that are made available to you. In order to use these tools, you must meet the age requirements as outlined in this Agreement. Midjourney reserves the right to remove any content that you upload or generate using Editor and/or Video, or suspend or ban your access to them at any time, and for any reason.
You are responsible for all content, including any images, videos, and prompts, that you input or generate when using Editor and/or Video.
You represent and warrant that you have all necessary rights and permissions to provide, edit, generate, and share such content, including obtaining necessary permission from anyone who may be depicted in the content that you upload and edit using Editor, or input and generate using Video. You will not upload content, enter prompts, or use Editor or Video in any way that infringes or violates any third-party intellectual property or privacy rights.
Midjourney may make available certain programs or features that allow users to submit translations relating to the Midjourney Site and Services (“Community Localization”). The translations, localization suggestions, updates, and other language-related content that You submit as part of the Community Localization program are the “Translations”. By submitting any Translations to Midjourney, You agree to the terms and conditions set forth in this Section 12. If You do not agree to these terms and conditions, You must not submit any Translations to the Community Localization program.
By submitting Translations to the Community Localization program, You represent and warrant: (i) that You have all rights necessary to submit the Translations and to grant the rights to Midjourney as described below, (ii) that Your Translations do not and will not violate any third party intellectual property rights, privacy rights, publicity rights, or applicable law, and (iii) Midjourney’s exercise of its rights in the Translations as contemplated by this Section 12 will not violate any applicable law or contractual obligation.
Midjourney may use, host, store, publicly display, create derivative works of, copy, adapt, modify, reject, remove, or stop use of any Translations at any time and for any reason, and may suspend or terminate Your participation in the Community Localization program at any time for any reason. You understand that Translations are provided voluntarily, and without expectation of any compensation or attribution.
You hereby irrevocably assign, transfer, and convey to Midjourney and Midjourney accepts, all rights, title, and interest (including all intellectual property and proprietary rights) in and to the Translations, and waive any moral rights you may have therein. To the extent any rights in any Translations cannot be assigned to Midjourney under applicable law, You grant to Midjourney a perpetual, irrevocable, exclusive, worldwide, sublicensable, transferable, royalty-free, and fully paid-up license to host, store, adapt, monetize, reproduce, copy, modify, prepare derivative works of, publicly display, publicly perform, and distribute the Translations for any purpose. This Section 12 survives the termination of this Agreement by any party, for any reason.
For more information about V8.2, see our Version article.
There are several ways you can use your own pictures when creating prompts with Midjourney. In this article, we'll focus on Image Prompts, but there are also Style References, Omni Reference, and Moodboards using Personalization. You can even mix and match to get exactly what you want in your images!
Image Prompts let you guide Midjourney by including an image along with your text prompt. Midjourney looks at your image's core elements, and uses it as a source of inspiration for your new and unique image.
To add an image to your prompt, start by clicking on the image icon in the Imagine bar. This opens the images panel, allowing you to upload new images or pick from those you've already uploaded. You can even select multiple images to use in your prompt!
Click your image in the uploads library to automatically add it as an Image Prompt. You can also drag and drop your image into any of the image sections to use it in different ways. To remove your image from the Imagine bar, hover your mouse over it and click the X icon.
\nIf you want to use your images with multiple prompts, click the lock icon to keep your images pinned to the Imagine bar.
Image Reference Types: Starting Frame
Image Prompt
Style Reference
Omni Reference (V7)
To use Image Prompts in Discord, paste your image URL at the beginning of your text prompt. If you want to use multiple images, separate each URL with a space. To easily use multiple images without a text prompt, check out the Blend command.
\nIt's important to ensure that you have a valid image URL, meaning the image should already be online. If your image is stored on your computer or device, you can host it on Discord to generate an image URL.
\nMidjourney uses Image Prompts and references as inspiration to guide new creations, not to copy them exactly. If you're looking to make precise changes on your own images, check out the Editor.
If you want more control over how much your Image Prompt affects the final image, try using the image weight parameter --iw.
If you don't set an --iw value, Midjourney will use the default setting. By choosing a higher weight, your Image Prompt will have a bigger impact on the finished image.
Remember, different Midjourney versions may have different image weight ranges.
| \n | Version 8.1 | \nVersion 7 | \nNiji 7 | \n
|---|---|---|---|
| Image Weight Default | \n1 | \n1 | \n1 | \n
| Image Weight Range | \n0 - 3 | \n0 - 3 | \n0 - 2 | \n
--stylize or --weird parameters.Creating with Midjourney starts with a prompt. A prompt is simply the text or phrase you use to tell Midjourney what kind of image or video you want.
Your prompt could be just one word or a complete phrase. The more thought you put into your prompt, the more unique and interesting your creation can be. So, take a moment to think about what you want to see, and use your words to guide the creative process.
Short and simple prompts typically generate the best images with Midjourney. Use phrases that clearly describe what you want to see. Think of it like giving a quick snapshot of your idea. Avoid making long lists or detailed instructions; these can confuse the process.
Show me a picture of lots of blooming California poppies, make them bright, vibrant orange, and draw them in an illustrated style with colored pencils
Colored pencil illustration of bright orange California poppies
The words you pick matter! Try using specific synonyms. For example, instead of \"big,\" consider \"huge,\" \"gigantic,\" or \"enormous.\" Being precise can help get better results.
Plural words like \"cats\" can be vague. Instead, use specific numbers like \"three cats.\" Or go for collective nouns like \"flock of birds\" instead of just \"birds.\"
Describe what you do want instead of what you don’t. If you mention a party with “no cake,” a cake might still appear. For excluding items, read about the no parameter.
Your prompts can be simple—even a single word or emoji works. Short prompts let the default Midjourney style fill in the gaps. But if specific elements are important to you, be sure to include them. Fewer details mean more variety, but you get less control over the outcome.
Be clear about details that matter to you. Here are some areas to consider:
Once you're comfortable with basic prompts, start exploring more advanced options! Add one or more Image Prompts, use multiple text phrases, and apply tools called parameters. These give you the ability to create more complex or specific images. Experiment by mixing different elements to boost your creativity!
Midjourney has a vibrant community that loves problem-solving and helping others! If you need more help or tips, make sure to visit our Prompt Craft channel on Discord.
To get started with a Midjourney plan, first create or log in to your account and head over to your Manage Subscription Page on midjourney.com.
If you need help getting logged in for the first time or want to access an old account, don’t worry! Check out our Logging In & Connecting Accounts article for step-by-step help.
Once you're on your Manage Subscription page, scroll down to the plans section. Find your perfect plan and press the Subscribe button below it. If you're not sure which plan to choose, our Comparing Midjourney Plans article can help you decide.
Note: All Midjourney plans are subscriptions, meaning they automatically renew on a monthly or yearly basis unless you set your plan to cancel.
Yearly billing is selected by default, meaning the full year is paid upfront. If you'd rather pay each month, please click the \"Monthly Billing\" tab before selecting a plan.
To complete your purchase, check out using our payment processor, Stripe. If you have any questions during this process, we've got you covered with the helpful articles below.
Keep in mind that once your billing email is set during checkout, you'll need to reach out to our billing support team if you want to change your email. Remember, we can't change invoices after they've been issued. So, double-check that the payment details you enter at checkout are exactly what you want to see on your invoice.
After your payment goes through, you'll get a confirmation email. This email includes both your invoice and receipt. It will be sent to the billing email you used during the Stripe checkout process, which might be different from the one you use to log in to midjourney.com.
If you return to your Manage Subscription page, you should now see that your plan is active and ready to use.
When you purchase a Midjourney subscription, sales tax or Value Added Tax (VAT) may apply, depending on your location. Stripe, our payment processor, calculates your tax rate at checkout using your billing information. Any taxes due are added to your subscription price, and you'll see the total amount before you complete your payment.
This process is automated based on your billing details. Our billing support team cannot modify the taxes charged for your subscription. However, if you're part of an organization that should be tax-exempt, please refer to our Setting Your Organization's Tax Status article for guidance.
Note: Tax requirements may change over time. Just because your past purchases were tax-free doesn’t mean future purchases will be as well.
"},{"id":27868831972365,"url":"https://midjourney.zendesk.com/api/v2/help_center/en-us/articles/27868831972365.json","html_url":"https://docs.midjourney.com/hc/en-us/articles/27868831972365-Accepted-Payment-Methods","author_id":16249248189965,"comments_disabled":true,"draft":false,"promoted":false,"position":0,"vote_sum":0,"vote_count":0,"section_id":16016608509709,"created_at":"2024-06-25T06:37:17Z","updated_at":"2026-01-05T21:57:24Z","name":"Accepted Payment Methods","title":"Accepted Payment Methods","source_locale":"en-us","locale":"en-us","outdated":false,"outdated_locales":[],"edited_at":"2025-12-10T16:45:05Z","user_segment_id":null,"permission_group_id":33673142591629,"content_tag_ids":[],"label_names":[],"body":"Midjourney uses Stripe as our payment processor, which means you can only use payment methods that Stripe accepts. Generally, you can pay with major credit and debit cards like Visa, Mastercard, and American Express, as well as some digital wallets such as Apple Pay, Amazon Pay, Alipay, Google Pay, and Link in some regions. The options you see during checkout are the ones available to you.
We can only accept the payment methods shown at checkout, and our billing support team can't help set up any alternatives unless you're buying in bulk as a company.
Unfortunately, PayPal isn't currently supported.
Stripe is a PCI Service Provider Level 1, the most stringent level of certification available in the payments industry.
"},{"id":25384024738573,"url":"https://midjourney.zendesk.com/api/v2/help_center/en-us/articles/25384024738573.json","html_url":"https://docs.midjourney.com/hc/en-us/articles/25384024738573-Canceling-Your-Subscription","author_id":15621413033997,"comments_disabled":true,"draft":false,"promoted":false,"position":0,"vote_sum":0,"vote_count":0,"section_id":27646307671309,"created_at":"2024-03-27T14:51:09Z","updated_at":"2026-03-25T21:05:27Z","name":"Canceling Your Subscription","title":"Canceling Your Subscription","source_locale":"en-us","locale":"en-us","outdated":false,"outdated_locales":[],"edited_at":"2026-03-25T21:05:27Z","user_segment_id":null,"permission_group_id":33673142591629,"content_tag_ids":[],"label_names":[],"body":"You can cancel your Midjourney subscription at any time by going to your Manage Subscription Page and clicking the Cancel Plan button.
Your cancellation will become effective at the end of your current billing cycle, and you'll still have access to all of your subscription features—including any remaining Fast time—until then.
Canceling your subscription does not delete your generated images or account history. Any private images you have will stay private. You can choose to resubscribe at any time.
If you have an upgrade or downgrade scheduled, make sure to cancel that change first by using the Cancel Change button before you proceed with canceling your subscription.
Welcome to the Create page on midjourney.com, your hub for generating amazing images! While you can use the Imagine bar on many pages, the Create page is where you can watch your images come to life right in front of your eyes.
The Imagine bar is where you type your prompts. Hit the send button or press enter on your keyboard, and your images will start generating. You'll find several helpful tools in the Imagine bar:
Add or upload images to your prompt
Adjust your default settings
Next to the Imagine bar you'll find buttons for folders,
Personalization,
Conversational mode, and
searching your prompts.
Hold Ctrl (or Cmd on Mac) and hit Enter. This runs your prompt and keeps the text in the Imagine bar, so you can easily use the prompt again.
Click the image icon, and you'll get instant access to your images menu. This is your go-to spot for uploading new images to Midjourney or picking from your uploads library to enhance your prompt.
Note: The maximum image file size you can upload to Midjourney is 10MB.
Drag an image from your uploads library into the Imagine bar and drop it into your desired section:
Once an image is added to your prompt, you can use the toggle buttons in the Imagine bar to switch between using the image to generate videos or still images
.
Hover over any image in your uploads library and you'll see a button with three dots. Click it to reveal these options:
When you open the images menu, two extra buttons appear on the Imagine bar.
When you click the settings icon, you can adjust the default settings that will automatically apply to all your prompts.
The central feature of the Create page is the creation feed. Here, you can watch your images generate in real-time and revisit all your finished creations.
When you hover your mouse over any image in the feed, shortcut buttons pop up that let you quickly trash the image,
like the image, create subtle or strong variations of that image, or use it to create a video.
To the right of the images, you'll see the prompt text, parameters, and reference images that were used to generate your images. Hover over this section to access more shortcut buttons.
With these, you can use the prompt in the Style Creator,
Run batch as HD if you originally used SD,
rerun the same prompt immediately,
use the prompt text and images for a new creation,
trash images from your feed (with the option to remove from trash on your Organize page), or explore
more options.
When you're on the Create page, you'll see a folder button right next to the search bar at the top. Clicking this reveals all your folders and folder groups.
If you click a folder to open it, you'll see a dedicated creation space just for that folder, and you can generate images directly inside it!
Ready to leave a folder? Just click the X in the folder button next to the search bar.
For more information about folders, check out our Using Folders article.
When you click on an image from your creation feed it will open fullscreen, giving you more options and tools.
At the top, near the prompt text, you'll find a toolbar packed with useful features.
The More Options button lets you copy important details like the prompt, Job ID, seed, image, or image URL. You can report any image that violates our Community Guidelines, choose to make it private or public, download, search similar images, run the prompt as HD, trash it, and even open it in Discord (if it was created there).
Next to this, you'll find icons to download the image,
spotlight it on your profile, and mark your favorites with a
like.
Above the Creation Actions, there's a folder icon. If your image is already in a folder, you'll see the folder name right there. If not, you can click the folder icon to quickly add the image to a folder.
In the Creation Actions section, you can further tweak your images and continue working with them. For a full breakdown of all these tools and features, check out our Modifying Your Creations article.
"},{"id":33329329805581,"url":"https://midjourney.zendesk.com/api/v2/help_center/en-us/articles/33329329805581.json","html_url":"https://docs.midjourney.com/hc/en-us/articles/33329329805581-Modifying-Your-Creations","author_id":18023535838733,"comments_disabled":false,"draft":false,"promoted":false,"position":1,"vote_sum":0,"vote_count":0,"section_id":32013365472909,"created_at":"2025-01-09T00:03:19Z","updated_at":"2026-03-24T21:50:26Z","name":"Modifying Your Creations","title":"Modifying Your Creations","source_locale":"en-us","locale":"en-us","outdated":false,"outdated_locales":[],"edited_at":"2026-03-24T21:50:26Z","user_segment_id":null,"permission_group_id":33673142591629,"content_tag_ids":[],"label_names":[],"body":"Once you've made an image with Midjourney, your creative journey doesn't have to stop there. You have a range of tools at your fingertips to modify and enhance your images.
To get started, click on your image from your Create or Organize Page to open it and reveal more options. Here's a quick look at the Creation Actions.
Variations (Vary) in Midjourney let you create multiple versions of your image with subtle or strong differences. This is particularly useful when you’re happy with your original image but are curious about changes that could make it even better.
Upscaling takes your image to the next level by enlarging its dimensions. Creative Upscale not only boosts the size but also adds subtle improvements, perfect for when your image needs that extra polish. To enlarge your image without altering it, use Subtle Upscale.
Remix is a powerful feature that lets you make iterations on your image by changing the prompt text. With Remix, you have the freedom to change both the prompt and the parameters you've set, allowing you to creatively steer how your images develop. Remix works a bit different on our website than on Discord, so be sure to check out our Remix article.
The Midjourney Editor includes Pan, Zoom Out, and Vary Region (the erase tool) all in one interface, if you'd like to make several changes at once. You can also use the individual tools on their own.
With Pan, you can expand the canvas of your image in a specific direction to add more content and change its aspect ratio.
Zoom Out gives you the ability to add more context and elements around all four sides of your original image, effectively expanding it beyond its current borders.
Vary Region/Erase is perfect for editing specific parts of your image, allowing for precise alterations without changing the rest of the image.
Under Creation Actions on our website you also have the \"Use\" buttons which allow you to quickly and easily use your generated image as an Image Prompt, Style Reference, or add the prompt text to your Imagine bar to make changes and run the prompt again.
The animate tools give you the ability to turn your image into a captivating 5 second video. Use the Auto buttons to jump right in, or the Manual buttons to adjust your prompt text for the video. Learn more on our Video article.
• Don't be a jerk.
• Don't use our tools to make images that could inflame, upset, or cause drama. That includes gore and adult content. See our Community Guidelines for more information.
• Be respectful to other people and the team.
Before you jump into creating images in Discord with Midjourney, you'll need a subscription. Don't worry, the process is simple! For a step-by-step guide, take a look at our How to Subscribe article.
After you’ve subscribed, you’re all set to follow these steps and start making creative images in Discord. Let's get started!
To start interacting with the Midjourney Bot, join the Midjourney Server:
+ button at the bottom of the server list.Join a Server button.Join.Learn more about Discord servers.
After joining the Midjourney server on Discord, you'll see several channels listed in the sidebar.
On the Midjourney Server
Locate and select any channel labeled general-# or newbie-1 through newbie-10. These channels are designed for beginners to start using the Midjourney Bot. The Midjourney Bot will not generate images in other channels.
Note: newbie channel numbers 11 and up have been archived and can no longer be used.
\nOn Other Servers
You can generate images with the Midjourney Bot on any Discord server that has invited the Midjourney Bot. Look for instructions on your server on where to use the Bot.
Interact with the Midjourney Bot on Discord using commands. Commands are used to create images and videos, change default settings, monitor subscription information, and perform other helpful tasks. The /imagine command generates a unique image from a short text description, known as a prompt.
/ in the message box. You’ll see a list of commands pop up above./imagine. This helps narrow down the options, just like a search field./imagine in the list, click it. If you aren't seeing any Midjourney commands, try our command troubleshooting tips.Before generating any images, the Midjourney Bot will prompt you to accept the Terms Of Service. You must agree to these terms to proceed with image creation.
After submitting a text prompt, the Midjourney Bot processes your request, creating four unique image options within a minute. This process utilizes advanced Graphics Processing Units (GPUs), and each image generation counts towards the GPU time included with your Midjourney subscription. To monitor your available GPU time (Fast Time Remaining) use the /info command.
Once your initial image grid has been generated, two rows of buttons become available underneath your image grid.
U1 U2 U3 U4 Image Selection
In earlier versions of Midjourney, the U buttons were used for upscaling images. With the latest version, images are immediately generated at 1024 x 1024 pixels size. Now, the U buttons help you separate out your chosen image from the image grid, making it easier to download and giving you access to additional editing and generation tools.
🔄 Reroll a Prompt
The 🔄 Reroll button reruns a prompt. In this case, it would rerun the original prompt producing a new grid of images.
V1 V2 V3 V4 Image Variation
The V buttons are used to create variations of the selected image. Each button generates a new image grid that maintains the general style and composition of the selected image.
After singling out an image, an expanded set of options becomes available.
🪄 Vary (Strong) 🪄 Vary (Subtle)
Create a stronger or subtle variation of your selected image, generating a new grid of four options.
🔍 Zoom Out 2x 🔍 Zoom Out 1.5x 🔍 Custom Zoom
Zoom out of your image, extending the canvas beyond its original boundaries without changing the content of the original image. The newly expanded canvas will be filled-in using guidance from the prompt and the original image.
⬅️ ➡️ ⬆️ ⬇️
The Pan buttons allow you to expand the canvas of an image in a chosen direction without changing the content of the original image. The newly expanded canvas will be filled in using guidance from the prompt and the original image.
❤️ Favorite
tag your best images to easily find them on the Midjourney website.
Web ↗️
Open the image in your gallery on midjourney.com
Click on the image to open it to full size, and then right-click and choose Save image. On mobile, long-tap the image and then tap the download icon in the top right corner.
All images are immediately available to view on midjourney.com
When you generate in Discord, your creations live in whichever channel you generated them in. If you move between multiple channels or are having trouble finding your creations, here are some tips to help you:
Are you having difficulty finding yourself while working with other users on the Midjourney server? You can interact with the Midjourney Bot one-on-one in a direct message. Images created within your direct messages are still subject to content and moderation rules and are visible on the Midjourney website.
Learn the basics of writing prompts and explore how descriptions of artistic mediums, locations, and time periods change an image with the art of prompting.
Learn how to upload and blend your own images using the /blend command.
Need help or have questions? Try these commands:/help Displays useful information and tips about the Midjourney Bot./ask Provides answers to questions about the Midjourney Bot.
You can also visit the #support channel on the Midjourney Discord for additional assistance.
For billing and subscription help, please visit Billing Support.
"},{"id":32180011136653,"url":"https://midjourney.zendesk.com/api/v2/help_center/en-us/articles/32180011136653.json","html_url":"https://docs.midjourney.com/hc/en-us/articles/32180011136653-Style-Reference","author_id":18023535838733,"comments_disabled":false,"draft":false,"promoted":false,"position":1,"vote_sum":0,"vote_count":0,"section_id":32013397184397,"created_at":"2024-11-26T00:14:27Z","updated_at":"2026-07-27T16:02:04Z","name":"Style Reference","title":"Style Reference","source_locale":"en-us","locale":"en-us","outdated":false,"outdated_locales":[],"edited_at":"2026-07-27T16:02:04Z","user_segment_id":null,"permission_group_id":33673142591629,"content_tag_ids":[],"label_names":[],"body":"For more information about V8.2, see our Version article.
A Style Reference is a way to capture the visual vibe of an existing image and apply it to your new Midjourney creations. It doesn't copy objects or people, just the overall style—like colors, medium, textures, or lighting—helping you achieve a consistent visual theme.
Style References are compatible with Midjourney versions 6 and later.
Video tutorial: Watch this quick video tutorial on Style References below.
To add an image to your prompt, start by clicking on the image icon in the Imagine bar. This opens the images panel, allowing you to upload new images or pick from those you've already uploaded. You can even select multiple images to use in your prompt!
Drag and drop your image from the uploads library into the Style Reference section. To remove your image from the Imagine bar, hover your mouse over it and click the X icon.
\nIf you want to use your images with multiple prompts, click the lock icon to keep your images pinned to the Imagine bar.
Image Reference Types: Starting Frame
Image Prompt
Style Reference
Omni Reference (V7)
--sref parameter to the end of your prompt, then pasting your image URL. If you want to use multiple images, separate each URL with a space. the look of this image but a dog
copy this style and make a bunny
detailed portrait of a dog
ballpoint pen sketch of a bunny
The style weight parameter --sw, allows you to control how strongly the style of your reference influences your new image. You can set this parameter to any value between 0 and 1000, with the default being --sw 100. If using V7, you may notice that style weight has more impact when used with style codes than with images.
Note: --sw is not compatible with Moodboards.
Instead of uploading an image as your Style Reference, you can use a Style Reference Code to apply a specific look from the Midjourney internal style library. Each numerical code produces a unique visual style, and can be used by adding --sref <code> to the end of your prompt.
Use --sref random in your prompt and Midjourney will apply a random style code. After submitting your prompt, \"random\" converts to a style code.
Once your prompt has a style code, using rerun/reroll or variations keeps the same style code. If you use --sref random with a permutation, repeat, or V8.1 Draft mode prompt, each image will have a different style code.
You can use the --sw parameter with style codes to adjust the influence they have on your image. You can also mix style codes by using more than one, and combine images with style codes.
You cannot create a style code based on an uploaded image. See the instructions above to use an uploaded image as a Style Reference.
The Style Explorer is a visual way to discover new style codes and find inspiration for your creations. You can browse style codes, try them instantly, and even save your favorites for later.
Click any style code to open a gallery of example images that showcase its unique look. From there, you can:
--sref code to the Imagine barIf you find a style code you love, hit the Like button to save it. Your favorites are collected under the Likes tab, making it easy to revisit and reuse your go-to style codes whenever inspiration strikes.
Note: Liking style codes does not affect your Personalization profiles.
If you're interested in creating your own custom style codes, see our Style Creator article.
There are six versions of the Style Reference feature in Midjourney version 7 when using images. Use the --sv parameter to choose between them.
--sv 6 is default.--sv 4 is the old V7 sref model (prior to June 16, 2025).
Each version offers a unique way of interpreting and applying your Style Reference, so experiment and see what works best for you!
\nNote: Sref random and sref codes are only compatible with --sv 4 and --sv 6
There are four versions of the Style Reference feature in Midjourney version 6. Use the --sv parameter to choose between them. --sv 4 is default. Each version may offer a unique way of interpreting and applying your Style Reference, so experiment and see what works best for you!
--sv 1 The original style reference algorithm, more “vibey”--sv 2 The second iteration of style references--sv 3 An updated version of the more “vibey” --sv 1--sv 4 An updated version of --sv 2
Note: style reference version (--sv) is not compatible with Moodboards.
--sref URL1::2 URL2::1 URL3::1 For more information on how weights work, see our article on Multi-Prompts & Weights.--sv 4 to your prompt (uses the old V7 model) or switch to V6.--c or --chaos For more information about V8.2, see our Version article.
Chaos (also called Variety on midjourney.com) lets you add more variety to the image results you get from each prompt.
By default chaos is set to 0, and Midjourney creates four images based on your prompt. If you want each image to look more different, increase the chaos value.
You can set the chaos value anywhere between 0 and 100, but keep in mind that higher values mean the images can be quite different and may not stick as closely to your prompt, giving you unpredictable results.
Video tutorial: Watch this quick video tutorial on chaos/variety below.
Add --c # to the end of your prompt in the Imagine bar.
You can choose a default Variety setting for all your images in the settings panel. To do this, click the settings button in the Imagine bar. Once you set it, this will apply to all your future prompts.
Add --c # to the end of your prompt in Discord.
We have 4 main rules
Thank you for helping us make Midjourney a safe, welcoming space for everyone.
If you see someone violating these guidelines, you can report it here.
Please use these incredible powers with joy, wonder, responsibility and respect.
The Editor is a powerful new tool for unleashing imagination. It’s not for creating images that might deceive, harass, or maliciously harm others.
Anyone attempting to violate our Community Guidelines using the Editor will face suspension or banning without refund. Use this tool with respect and consideration for others.
Occasionally prompts will unintentionally produce not safe for work content. Please self-police these images by using the ❌ emoji reaction or by right-clicking selecting Apps and then clicking Cancel Job to delete the image in Discord.
Users may flag any image for moderator review by right-clicking selecting Apps, and then clicking Report Job within Discord or the website by selecting the Options button under an image and clicking Report.
To manage your Midjourney image generation subscription, simply log in to midjourney.com.
For help logging in, see our Logging In & Connecting Accounts article.
If you're looking to access your magazine subscription instead, please refer to our Managing Your Magazine Subscription article for assistance.
Once you're logged in at midjourney.com, head over to your Manage Subscription Page. Here’s what you can do:
This FAQ applies to Midjourney Magazine subscriptions. If you have questions about individual orders placed on mag.midjourney.com for past issues or books, see the Midjourney Store Orders FAQ instead.
Midjourney Magazine ships monthly, towards the end of each month. When you subscribe, your first issue will be the one that ships near the end of the following month. For example, if you subscribe in June, your first issue will be shipped at the end of July. Delivery times can vary from 1 to 6 weeks, depending on your location.
| Issue | \nPayment | \nIssue Deadline | \nEstimated Ship Date | \n
|---|---|---|---|
| 35 | \nJan 1-31 | \nJan 31 | \nLate Feb/early March | \n
| 36 | \nFeb 1-28 | \nFeb 28 | \nLate March/early April | \n
| 37 | \nMarch 1-31 | \nMarch 31 | \nLate April/early May | \n
| 38 | \nApril 1-30 | \nApril 30 | \nEarly June | \n
| 39 | \nMay 1-31 | \nMay 31 | \nEarly July | \n
| 40 | \nJune 1-30 | \nJune 30 | \nLate July/early August | \n
| 41 | \nJuly 1-31 | \nJuly 31 | \nLate Aug/early Sept | \n
| 42 | \nAug 1-31 | \nAug 31 | \nLate Sept/early Oct | \n
| 43 | \nSept 1-30 | \nSept 30 | \nLate Oct/early Nov | \n
Shipping address changes must be made before the Issue Deadline in order to apply to that issue.
To keep costs low, magazine issues ship without tracking, using slower shipping methods. Please allow up to 6 weeks for delivery after shipping. Magazines for North America, South America, Australia, and parts of Asia are shipped from Canada, while deliveries to Europe, the Middle East, Africa, and other parts of Asia ship from the UK.
To update your shipping address, enter your billing email into the magazine subscription portal and follow the link sent to your email. Address changes must be made before the Issue Deadline in the table above in order to apply to that issue. If you encounter any problems with the portal, such as being redirected to your Midjourney image generation subscription instead, contact billing support for assistance.
Your magazine subscription is separate from your image generation subscription. Manage it by entering your billing email in the magazine subscription portal and using the access link sent to your inbox. For issues accessing the portal, contact billing support for help.
To cancel, enter your billing email in the subscription portal, and use the link to access your account. Click \"Cancel Plan\" to stop future issues. Any issues you’ve already paid for will still be sent. If issues arise during this process, reach out to billing support.
You can subscribe up to four times to receive extra copies of each issue. For past issues, visit mag.midjourney.com, but note that stock may be limited.
We reserve copies for schools, stores, and community groups monthly. To apply for our distribution list, please fill out this form. Please be aware that you may be responsible for customs/duties/import fees and brokerage fees payable to the shipping carrier prior to delivery.
No digital version is available. The magazine celebrates community creativity through print, offering a pause from screen time to enjoy art at a different pace.
We compile the top-rated community images on Midjourney, shortlist a few hundred, and publish select ones based on criteria such as clarity, originality, and composition. Direct submissions are not accepted.
If your magazine hasn’t arrived within 6 weeks post-shipping, contact billing support. Remember, issues ship at the end of the month following your payment and may take 1 to 6 additional weeks for delivery. Please note that undelivered magazines as a result of an incorrect address do not qualify for refunds or replacements.
We do our best to protect the magazines by having them wrapped in plastic for shipping, but unfortunately minor damage can sometimes still happen, and we are unable to guarantee pristine condition with the available shipping method.
For any other magazine subscription concerns, contact billing support for assistance.
"},{"id":27870484040333,"url":"https://midjourney.zendesk.com/api/v2/help_center/en-us/articles/27870484040333.json","html_url":"https://docs.midjourney.com/hc/en-us/articles/27870484040333-Comparing-Midjourney-Plans","author_id":16249248189965,"comments_disabled":true,"draft":false,"promoted":false,"position":1,"vote_sum":0,"vote_count":0,"section_id":28005319720845,"created_at":"2024-06-25T09:01:48Z","updated_at":"2026-05-18T20:20:25Z","name":"Comparing Midjourney Plans","title":"Comparing Midjourney Plans","source_locale":"en-us","locale":"en-us","outdated":false,"outdated_locales":[],"edited_at":"2026-05-18T20:20:24Z","user_segment_id":null,"permission_group_id":33673142591629,"content_tag_ids":[],"label_names":[],"body":"Midjourney offers four subscription tiers: Basic, Standard, Pro, and Mega. See the chart below for a comparison of plan features.
You can get a 20% discount on your subscription by committing to an annual plan, where the full year fee is paid upfront.
| \n | Basic Plan | \nStandard Plan | \nPro Plan | \nMega Plan | \n
|---|---|---|---|---|
| Monthly Price | \n$10 | \n$30 | \n$60 | \n$120 | \n
| Annual Price | \n$96 ($8 / month) | \n$288 ($24 / month) | \n$576 ($48 / month) | \n$1,152 ($96 / month) | \n
| Fast GPU Time | \n3.3 hr/month (200 minutes) | \n15 hr/month | \n30 hr/month | \n60 hr/month | \n
| Relax GPU Time | \nUnlimited Images | \nUnlimited Images & SD Video | \nUnlimited Images & SD Video | \n|
| Video Resolution | \nSD | \nSD & HD | \nSD & HD | \nSD & HD | \n
| Purchase Extra GPU Time | \n$4/hr | \n$4/hr | \n$4/hr | \n$4/hr | \n
| Work Solo in Discord Direct Messages | \n||||
| Stealth Mode | \n||||
| Maximum Concurrent Prompts (images) | \n3 Fast | \n3 Fast or Relax | \n12 Fast or 3 Relax | \n12 Fast or 3 Relax | \n
| Maximum Concurrent Prompts (videos) | \n1 Fast | \n3 Fast | \n6 Fast or 3 Relax | \n12 Fast or 3 Relax | \n
| Maximum Repeat / Permutation Size | \n4 jobs | \n10 jobs | \n40 jobs | \n40 jobs | \n
| Maximum Queued Jobs | \n10 jobs | \n10 jobs | \n10 jobs* (3 Relax videos) | \n10 jobs* (3 Relax videos) | \n
| Rate Images to Earn Free GPU Time | \n||||
| Usage Rights | \nGeneral Commercial Terms** | \nGeneral Commercial Terms** | \nGeneral Commercial Terms** | \nGeneral Commercial Terms** | \n
*Queue size will extend to accommodate repeat/permutation jobs.
**If you have subscribed at any point, you are free to use your images/videos in just about any way you want. You must purchase the Pro or Mega plan if you are a company making more than $1,000,000 USD in gross revenue per year. For complete details, please see the Terms of Service.
Plan availability and features are subject to change. Our Terms of Service apply to all subscriptions.
You're eligible for a refund only if you've used less than 20 GPU minutes throughout the lifetime of your account. This includes both Fast/Turbo and Relax time.
If you qualify for a refund, you'll automatically see the option to request one when you cancel your subscription. If you don't see the refund option, we're unable to provide a refund.
Refund eligibility does not apply if your account is suspended or terminated due to a violation of our Terms of Service or Community Guidelines.
Refund processing may take up to 10 business days, depending on your bank's processing times, but you'll receive a refund confirmation email from Midjourney within a few minutes.
Before requesting a refund, make sure to cancel any other plan changes you have scheduled using the Cancel Change button.
If you encounter any error messages, wait an hour and try again—your renewal payment might still be processing. If the issue persists, contact billing support for assistance.
To review or update your payment details on an active subscription, log in to midjourney.com and go to your Manage Subscription Page.
From there, click the Edit Billing button. This opens your billing portal in a new window. Inside the portal, you can add new card details by clicking + Add payment method.
Click the ... (ellipsis) button to set a card as your default payment method.
If you need to delete a payment method, use the X button, but remember you must keep at least one payment method on file as long as your subscription is active.
For smooth transactions, ensure your billing address matches the address on file with your credit card issuer. This helps avoid any unsuccessful payments.
If your subscription has ended, you won't see the Edit Billing button on your Manage Subscription Page. Instead, enter your email address here. You will receive an email with a link to access your billing portal within a few minutes. Make sure to check your spam folder if you don't receive it right away.
Please note, if you also have a subscription to Midjourney Magazine using the same email address, the form might send you a link to your magazine subscription billing portal instead. If this occurs, or if you encounter any other issues accessing your billing history, please reach out to billing support for assistance.
"},{"id":36285124473997,"url":"https://midjourney.zendesk.com/api/v2/help_center/en-us/articles/36285124473997.json","html_url":"https://docs.midjourney.com/hc/en-us/articles/36285124473997-Omni-Reference","author_id":18023535838733,"comments_disabled":false,"draft":false,"promoted":false,"position":2,"vote_sum":0,"vote_count":0,"section_id":32013397184397,"created_at":"2025-05-01T23:34:52Z","updated_at":"2026-07-27T16:02:40Z","name":"Omni Reference","title":"Omni Reference","source_locale":"en-us","locale":"en-us","outdated":false,"outdated_locales":[],"edited_at":"2026-07-27T16:02:40Z","user_segment_id":null,"permission_group_id":16016582504461,"content_tag_ids":[],"label_names":[],"body":"Adding an Omni Reference image to the Imagine bar will automatically run the prompt in V7. For more information about V8.2, see our Version article.
Using an Omni Reference allows you to put characters, objects, vehicles, or non-human creatures from a reference image into your Midjourney creations.
You can use it in combination with Personalization, Moodboards, stylize, and Style References!
Omni Reference is compatible with Midjourney version 7.
• Omni Reference is not compatible with features like inpainting or outpainting that still use V6.1.
• Using Omni Reference will cost 2x more GPU time compared to regular V7 images.
• Omni Reference image results currently are not compatible with Vary Region, Pan, or Zoom Out. To edit these images please load them into the Editor on midjourney.com and remove the image reference and any --oref or --ow parameters.
• Omni Reference is currently not compatible with Fast Mode, Draft Mode & Conversational Mode, or --q 4.
To add an image to your prompt, start by clicking on the image icon in the Imagine bar. This opens the images panel, allowing you to upload new images or pick from those you've already uploaded.
Drag and drop your image from the uploads library into the Omni Reference section. You can only use one image with Omni Reference. To remove your image from the Imagine bar, hover your mouse over it and click the X icon.
\nIf you want to use your images with multiple prompts, click the lock icon to keep your images pinned to the Imagine bar.
Image Reference Types: Starting Frame
Image Prompt
Style Reference
Omni Reference (V7)
To use an Omni Reference in Discord, start by adding the --oref parameter to the end of your prompt, then pasting your image URL. You can only use one image with Omni Reference.
It's important to ensure that you have a valid image URL, meaning the image should already be online. If your image is stored on your computer or device, you can host it on Discord to generate an image URL.
\n--exp values you may want to also use a higher Omni Reference Weight, as these will all compete for influence.Midjourney provides you with powerful tools for unleashing your imagination. When using our tools to create with external images, we have additional necessary precautions you should be aware of.
\nBy using external images with Midjourney, you agree to the following rules in addition to our Terms of Service.
\nIf you disagree with these rules, do not use Midjourney with external images.
\nYou will likely encounter friction with our moderation — seemingly innocent prompts may be blocked by our filters. Blocked jobs don't cost you any credits. GPU time will only be deducted when you see your results.
\nWe encourage you to use this tool and your imagination with joy, wonder, responsibility, and respect.
\nFor additional information on policies, including privacy, payments, and disputes, refer to our Terms of Service.
\nThe omni reference weight parameter --ow allows you to control how much detail from your reference image appears in your new image. You can set this parameter to any value between 1 and 1,000, with the default being --ow 100.
Unless you are using a very high stylize value, it's best to keep your weight below 400, otherwise your results may be unpredictable.
On midjourney.com you can use the Omni Strength slider in the Imagine bar to adjust the weight.
The Midjourney server is a vibrant space where you can generate images, collaborate with others, find technical support, receive official announcements, submit feedback, and engage in stimulating discussions. Our community is welcoming and ready to help newcomers get started on their creative journey. If you’re eager to dive in, be sure to check out our Discord Quickstart guide!
Explore and navigate through various channels within our server. For assistance, visit the #support channel to connect with guides and moderators. Ready to create images? Head over to the #newbies or #general channels.
\nEasily spot the Midjourney Bot and see the list of our dedicated Midjourney team, guides, and moderators. If you can't find the Member List, just click the Member List icon to reveal it.
Here, you can access your Direct Messages (top icon) and view all the servers you've joined.
\nThis is where the real-time conversation happens! Feel free to chat and interact with other server members in this space.
\nYou can interact with the Midjourney Bot in Discord by using emoji reactions. Once your images are ready, hover your mouse over the message area. A small menu will appear on the right side. Click on the \"Add Reaction\" button, which looks like a smiley face. This brings up a menu with emojis.
Using a mobile device? Long press on the message area and click the smiley face button in the menu that pops up to reveal the emoji reaction menu.
There are two emojis you can use to interact with the Midjourney Bot, but keep in mind these only work on your own images.
If you want to receive your completed image generation to your direct messages (DMs), use the envelope emoji ✉️ as a reaction on the Midjourney Bot's message. This will send the images straight to your DMs, and include helpful details like the image's seed number and Job ID.
\nWhen used on an image grid, the envelope emoji will send each of the four images separately. Be sure to choose the plain envelope emoji. If you have difficulty finding it, take advantage of the emoji search bar.
\nThe red X emoji ❌ can do two different things depending on the status of your creations:
\nStop Generating: If your creations are still generating and you use the red X emoji ❌, it will cancel the job. This means the job will stop processing. Use the info command to see your currently running and queued jobs.
\nTrash Creations: If your creations are already complete, reacting with the red X emoji ❌ will remove them from Discord, your Organize and Create pages on midjourney.com, and the Archive tab on your profile.
\nIf you change your mind your can bring them back to Discord using the show command. You can restore them on midjourney.com by going to your Organize page and clicking the \"In Trash\" checkbox filter option to reveal them and use the \"Remove from Trash\" option.
\nImportant: Trashed creations are not private. Others might still find them on the Explore page, in ranking, or see them if they have the job ID or creation URL.
\nNote: Prior to October 2025, the red X emoji ❌ functioned differently. Creations ❌ed in Discord before this cannot be removed from trash.
\nTrashing creations does not delete them. You cannot delete individual creations, but if you're interested in permanently removing all images, videos, and your account data, please visit our Data Deletion and Privacy FAQ page.
\nIf you're having trouble using emoji reactions on a job, look below the action buttons for a tiny message that says \"Only you can see this.\" This message means your images are ephemeral. Ephemeral images are visible only to you when they first generate in Discord and will vanish when you refresh the page.
Ephemeral jobs are part of the Midjourney moderation system. They are triggered by certain words or phrases in your prompt that could result in inappropriate images. To keep things safe, these images are private to you and will disappear unless you generated them in a direct message with the Midjourney Bot.
Want to make them visible to others and use emoji reactions? Just use the show command. Your images will pop back into view, and you can then interact with them as usual.
"},{"id":33329788681101,"url":"https://midjourney.zendesk.com/api/v2/help_center/en-us/articles/33329788681101.json","html_url":"https://docs.midjourney.com/hc/en-us/articles/33329788681101-Legacy-Features","author_id":18023535838733,"comments_disabled":false,"draft":false,"promoted":false,"position":2,"vote_sum":0,"vote_count":0,"section_id":33329522730509,"created_at":"2025-01-09T00:18:30Z","updated_at":"2026-07-09T17:33:32Z","name":"Legacy Features","title":"Legacy Features","source_locale":"en-us","locale":"en-us","outdated":false,"outdated_locales":[],"edited_at":"2026-07-09T17:33:31Z","user_segment_id":null,"permission_group_id":33673142591629,"content_tag_ids":[],"label_names":[],"body":"If you’re curious about the older versions of Midjourney and the features they offer, you’ve come to the right place. As we keep moving forward with the latest updates, we also want to acknowledge and explore the tools and options from previous models that helped shape Midjourney to what it is today.
The Niji 6 model, released on June 7, 2024, features improved rendering of Japanese text, handling short Japanese kana text effectively and even rendering simple Chinese characters. It offers better image detail, particularly in elements like the structure of anime eyes, and addresses certain minor image artifacts that affected a small number of previous generations.
Version 5.2 was released in June 2023. It was the default model from June 22, 2023 to February 14, 2024. Version 5.2 produces more detailed, sharper results with better colors, contrast, and compositions. It also has a slightly better understanding of prompts than earlier models and is more responsive to the full range of the --stylize parameter.
Version 5.1 was released on May 4th, 2023. It was the default model from May 3, 2023 to June 22, 2023. Version 5.1 has a stronger default aesthetic than earlier versions, making it easier to use with simple text prompts. It also has high coherency, excels at accurately interpreting natural language prompts, produces fewer unwanted artifacts and borders, has increased image sharpness, and supports advanced features like repeating patterns with --tile.
Version 5 was released in March 2023. It was the default model from March 30, 2023 to May 3, 2023. Version 5 produces more photographic generations than the V5.1 model, and produces images that closely match the prompt but may require longer prompts to achieve your desired aesthetic.
The Niji 5 model was released in April 2023. It can be fine-tuned with specific --style parameters including:
• --style cute creates charming and adorable characters, props, and settings.
• --style expressive has a more sophisticated illustrated feeling.
• --style original uses the original Niji Model version 5, which was the default before May 26th, 2023.
• --style scenic makes beautiful backgrounds and cinematic character moments in the context of their fantastical surroundings.
Default Parameter Values
| \n | Aspect Ratio | \nChaos | \nQuality | \nSeed | \nStop | \nStylize | \n
|---|---|---|---|---|---|---|
| Default Value | \n1:1 | \n0 | \n1 | \nrandom | \n100 | \n100 | \n
| Range | \nany | \n0-100 | \n0.25, 0.5, 1 | \n0-4294967295 | \n10-100 | \n0-1000 | \n
Upscalers: Version 5 features the Upscale (2x) and Upscale (4x) tools, which are not compatible with Pan or tile.
Version 4 was released in November 2022. It was the default model from December 20, 2022 to March 30, 2023. Version 4 is an entirely new codebase and brand-new AI architecture (compared to previous versions) designed by Midjourney and trained on the new Midjourney AI supercluster. Version 4 has more knowledge of creatures, places, objects, and more than previous versions. It's much better at getting small details right and can handle complex prompts with multiple characters or objects. Version 4 supports advanced functionality like image prompting and multi-prompts, and has very high coherency and excels with Image Prompts.
Version 4 has three slightly different \"flavors\" with slight tweaks to the stylistic tuning of the model. Experiment with these versions by adding --style 4a, --style 4b, or --style 4c to the end of a V4 prompt. 4c is the default and support aspect ratios up to 1:2 or 2:1. 4a and 4b only support 1:1, 2:3, and 3:2 aspect ratios.
The first Niji model, Niji 4, was released on December 20, 2022.
Default Parameter Values
| \n | Aspect Ratio | \nChaos | \nQuality | \nSeed | \nStop | \nStyle | \nStylize | \n
|---|---|---|---|---|---|---|---|
| Default Value | \n1:1 | \n0 | \n1 | \nrandom | \n100 | \n4c | \n100 | \n
| Range | \n1:2–2:1 | \n0-100 | \n0.25, 0.5, 1 | \n0-4294967295 | \n10-100 | \n4a, 4b, 4c | \n0-1000 | \n
Upscalers: Earlier Midjourney model versions start by generating a grid of low-resolution image options for each Job. You can use a Midjourney upscaler on any of these images to increase the size and add additional details. The table below shows image sizes for 1:1 ratio images. For more information view our Upscalers article.
| Model Version | \nStarting Grid | \nDefault Upscale | \nDetail Upscale | \nLight Upscale | \nBeta Upscale | \n
|---|---|---|---|---|---|
| Version 4 | \n512 x 512px | \n1024 x 1024px | \n1536 x 1536px | \n1536 x 1536px | \n2048 x 2048px | \n
| Niji 4 | \n512 x 512px | \n1024 x 1024px | \n1024 x 1024px | \n1024 x 1024px | \n2048 x 2048px | \n
The --test and --testp models were introduced in August 2022 as part of an effort to gather community feedback and improve upon new features. These test models allow members to explore upcoming capabilities, and they can be used alongside the --creative parameter for more varied compositions. When using these models, keep in mind that they support --stylize values ranging from 1250 to 5000, offering strong artistic influence.
There are some limitations with the test models. They do not support multi-prompts or image-prompts and have a maximum aspect ratio of 3:2 or 2:3. When the aspect ratio is 1:1, they generate two initial grid images, but with other aspect ratios, they produce only one initial grid image. Additionally, in crafting prompts, note that words at the beginning of your prompt may hold more weight than those at the end. These unique characteristics make the test models an exciting option for experimental image creation.
\nUpscalers: Initial grid images are 512 x 512px and the only option to upscale is Beta Upscale, which creates a 2048 x 2048px image when using 1:1 aspect ratio. For more information view our Upscalers article.
\nVersion 1 was the default model from February 2022 to April 2022. Version 1 is very abstract and painterly with low coherency.
\nVersion 2 was the default model from April 2022 to July 2022. Version 2 is creative, colorful, and painterly with low coherency.
\nVersion 3 was the default model from July 2022 to November 2022. Version 3 generates highly creative compositions with moderate coherency.
V3 Legacy Parameter: --sameseed Seed values create a single large random noise field applied across all images in the initial grid. When --sameseed is specified, all images in the initial grid use the same starting noise and will produce very similar generated images.
--hd is an early alternative model that generates busy, detailed, and abstract images with low coherency.
Upscalers: Earlier Midjourney model versions start by generating a grid of low-resolution image options for each Job. You can use a Midjourney upscaler on any of these images to increase the size and add additional details. The table below shows image sizes for 1:1 ratio images. For more information view our Upscalers article.
| Model Version | \nStarting Grid | \nDefault (Detail) Upscale | \nLight Upscale | \nBeta Upscale | \nMax Upscale | \n
|---|---|---|---|---|---|
| Version 1-3 | \n256 x 256px | \n1024 x 1024px | \n1024 x 1024px | \n1024 x 1024px | \n1664 x 1664px | \n
| hd | \n512 x 512px | \n1536 x 1536px | \n1536 x 1536px | \n2048 x 2048px | \n-- | \n
| \nStyle Tuner Codes --style code | \n\nTest Models --test --testp | \n\nCreative --creative | \n
| \nSameseed --sameseed | \n\nUplight --uplight | \n\nStop --stop | \n
| \n | \n | \n\n |
--width and --w (replaced with Aspect Ratio)
--height and --h (replaced with Aspect Ratio)
--fast (replaced with Quality)
--vibe (now known as model version 1)
--upanime
--hq
--newclip
--nostretch
--old
--upbeta
For information on the current default version (V7), please visit our Version article.
| \n | Affects Initial Images | \nAffects Variations & Remix | \nV6 | \nV5 | \nV4 | \nV3 | \nTest & Testp | \nNiji 4 | \nNiji 5 | \n
|---|---|---|---|---|---|---|---|---|---|
| Max. Aspect Ratio | \nany | \nany | \n1:2 / 2:1 | \n5:2 / 2:5 | \n3:2 / 2:3 | \n1:2 / 2:1 | \nany | \n||
| Chaos | \n\n | ||||||||
| Image Weight | \n\n | 0-3 default 1 | \n0.5-2 default 1 | \n0.5-2 default 1 | \nany default 0.25 | \n\n | \n | 0.2-2 default 1 | \n|
| No | \n|||||||||
| Quality | \n\n | 0.5-2 | \n0.25-1 | \n0.25-1 | \n0.25-2, 5 | \n\n | 0.25-1 | \n0.25-1 | \n|
| Repeat | \n\n | ||||||||
| Seed | \n\n | ||||||||
| Sameseed | \n\n | \n | \n | \n | \n | \n | \n | ||
| Stop | \n|||||||||
| Style | \n\n | \n | raw | \nraw | \n4a, 4b | \n\n | \n | \n | expressive, cute, scenic, original | \n
| Stylize | \n\n | 0-1000 default 100 | \n0-1000 default 100 | \n0-1000 default 100 | \n625-60000 default 2500 | \n1250-5000 default 2500 | \n\n | 0-1000 default 100 | \n|
| Tile | \n\n | \n | \n | ||||||
| Weird | \n\n | \n | \n | \n | \n | \n | |||
| # of Initial Images | \n-- | \n-- | \n4 | \n4 | \n4 | \n4 | \n2 or 1 if custom aspect ratio | \n4 | \n4 | \n
In previous Midjourney model versions, images generated at smaller sizes. You can still enlarge these images using a legacy upscaler. These tools not only increase the size but also add more details. There are various legacy upscalers you can choose from for images made with earlier models. Keep in mind, using a legacy upscaler will use GPU minutes.
Midjourney model versions 5.x produce 1024 x 1024 pixel images. You can then use the Upscale (2x) or Upscale (4x) tools to increase the size of your image to 2048 x 2048 pixels or 4096 x 4096 pixels respectively. V5 upscale tools are not compatible with the Pan tool or the tile parameter.
Each of these upscalers changes your image in different ways. All sizes are in pixels and for square aspect ratios.
| Version | \nInitial Image | \nV4 Default Upscale | \nLight Upscale | \nBeta Upscale | \nDetail Upscale | \nMax Upscale** | \n
|---|---|---|---|---|---|---|
| V4 | \n512 x 512 | \n1024 x 1024 | \n1536 x 1536 | \n2048 x 2048 | \n1536 x 1536 | \n-- | \n
| V1-V3 | \n256 x 256 | \n-- | \n1024 x 1024 | \n1024 x 1024 | \n1024 x 1024* | \n1664 x 1664 | \n
| Niji | \n512 x 512 | \n1024 x 1024 | \n1024 x 1024 | \n2048 x 2048 | \n1024 x 1024 | \n-- | \n
| test / testp | \n512 x 512 | \n-- | \n-- | \n2048 x 2048 | \n-- | \n-- | \n
| hd | \n512 x 512 | \n-- | \n1536 x 1536 | \n2048 x 2048 | \n1536 x 1536* | \n-- | \n
* = the default upscaler for each Midjourney version model.
** Max Upscale is an older resource-intensive upscaler and is only available when in Fast Mode.
When using legacy versions, the --uplight or --upbeta parameters in your prompt will turn the U# buttons in Discord into Light Upscale or Beta Upscale shortcut buttons.
Note: The --upbeta parameter is deprecated, and Beta Upscale may not function reliably.
The Style Tuner was a Discord feature in Midjourney version 5.2 and was one of the first steps toward developing Personalization, Moodboards, and the Style Explorer. The /tune command no longer works, and new Style Tuners cannot be created.
You can still access previously created Style Tuners using the /list_tuners command, and existing --style code parameters can still be used.
Remaster is a Discord button for upscaled images generated using legacy versions of Midjourney. It automatically remixes your prompt into version 5.2. Remaster any previously upscaled job by clicking the 🆕 Remaster button beneath the upscaled image.
Stop is a parameter compatible with versions 6 and earlier. Using --stop allows you to end the image creation process before it's fully completed, resulting in softer, less detailed images.
The default stop value is 100, meaning the image completes fully unless you specify otherwise. You can choose a value between 10 to 100. This value represents the percentage of the process you'd like to stop at.
Rooms were shared spaces on the Midjourney website where members could chat and generate creations together. They were discontinued on February 26, 2026. For events, collaboration, and socializing check out the Midjourney Discord server.
"},{"id":33329462451469,"url":"https://midjourney.zendesk.com/api/v2/help_center/en-us/articles/33329462451469.json","html_url":"https://docs.midjourney.com/hc/en-us/articles/33329462451469-Organizing-Your-Creations","author_id":18023535838733,"comments_disabled":false,"draft":false,"promoted":false,"position":2,"vote_sum":0,"vote_count":0,"section_id":33329398561549,"created_at":"2025-01-09T00:07:25Z","updated_at":"2026-06-11T17:01:53Z","name":"Organizing Your Creations","title":"Organizing Your Creations","source_locale":"en-us","locale":"en-us","outdated":false,"outdated_locales":[],"edited_at":"2026-06-11T17:01:52Z","user_segment_id":null,"permission_group_id":33673142591629,"content_tag_ids":[],"label_names":[],"body":"Welcome to the Organize page on midjourney.com, your centralized hub for managing all your creations!
Video tutorial: Watch this quick video tutorial on organizing your creations below.
On the right side of the page you'll find a toolbar with a variety of options you can use to filter your images. Selecting filters will temporarily hide all other creations that don't match your filters.
\nIf it seems like some of your images are missing, it might be because a filter is applied. To view all your images again, make sure to uncheck all filter boxes.
\nThese let you customize the look and layout of your Organize page
\nNext to the toolbar, you'll notice a thin gray bar resembling a scroll bar. Hovering over it reveals a timeline displaying the specific days you've generated images. Click on any date to jump straight to images created on that day.
\nJust like on your computer, Folders let you neatly organize your images. But here's the fun part: you can now create images directly inside them!
Click the Folder icon next to the Imagine bar to view your folders, create new ones, or create Folder Groups. Give your folders unique names and drag and drop images into them. You can also drag folders into different Folder Groups.
When you enter a prompt in the Imagine bar with a folder open, the results will appear right inside the folder.
The image feed of your folder will appear differently depending on whether you are viewing it from the Create page or the Organize page.
For more information, check out our Using Folders article.
On the Organize and Create pages, there's a search bar at the top designed just for your personal image collection.
\nWhile other parts of midjourney.com allow you to search images from other users, this search feature focuses on your own creations.
\nYou can search by using words or phrases from your prompt text, as well as specific attributes, like parameters, individual reference images, Personalization profiles, and more.
\nScroll through the list of attributes and click to add them to the search bar. Combining prompt text and multiple attributes allows you to narrow down your search and quickly find the images you're looking for.
\nSaved Searches (previously called Smart Folders) help you organize your images in a very easy way. With these searches, you don't need to add or remove images manually—everything sorts itself automatically based on the terms you provide.
\nWhen you set up a Saved Search, only prompts that include all your search terms will appear. It doesn't matter what order the terms are in. For example, if you add \"cat dog\" you'll get images where both words are used in the prompt.
\nIf you want results for either word, just separate them with a comma. Keep in mind that Saved Searches will also find part of a word. So if you add \"cat\" you'll get results including \"catapult\" too.
\nEasily select multiple images at once by clicking and dragging or using shift + click. You can also select all the images generated on a single day by clicking the plus + icon next to the date.
After selecting, a bulk actions pop-up will appear at the bottom of your screen. This pop-up shows the number of images selected and presents several action options.
You can download images directly, or click the More button for additional actions such as liking or unliking, adding or removing from trash, making private or public, and adding or removing from folders.
If you want to clean up your workspace you can use the trash feature to remove creations you no longer need. Here's how it works:
When you trash a creation, it won't be visible on your Create or Organize pages, and it won't show up in the Archive tab of your Profile page. If you change your mind, you can still find trashed creations by checking the In Trash filter on your Organize page and use the Remove from Trash option to bring them back.
Important: Trashed creations are not private. Others might still find them on the Explore page, in rating, or see them if they have the Job ID or creation URL.
To trash creations in Discord, simply use the ❌ emoji reaction. For more details, take a look at our Discord Overview article.
Trashing creations does not delete them. You cannot delete individual creations, but if you're interested in permanently removing all images, videos, and your account data, please visit our Data Deletion and Privacy FAQ page.
"},{"id":32083472637453,"url":"https://midjourney.zendesk.com/api/v2/help_center/en-us/articles/32083472637453.json","html_url":"https://docs.midjourney.com/hc/en-us/articles/32083472637453-Privacy-Policy","author_id":18023535838733,"comments_disabled":false,"draft":false,"promoted":false,"position":2,"vote_sum":0,"vote_count":0,"section_id":33329694407821,"created_at":"2024-11-21T23:37:21Z","updated_at":"2026-08-17T20:06:41Z","name":"Privacy Policy","title":"Privacy Policy","source_locale":"en-us","locale":"en-us","outdated":false,"outdated_locales":[],"edited_at":"2025-12-05T18:22:02Z","user_segment_id":null,"permission_group_id":33673142591629,"content_tag_ids":[],"label_names":[],"body":"\n \n
\n \n\n \n
Last Updated: June 2, 2025
This privacy policy (the “Policy”) describes Midjourney, Inc. (“Midjourney”)’s practices with respect to personal data that is collected when you access midjourney.com (the “Site”), or access or use the Midjourney services, applications, or platform through the Site, Discord servers administered by Midjourney, or by any other means (collectively, the “Services”) . Midjourney is a communications technology incubator that provides image generation services to augment human creativity and foster social connection.
As used in this Policy, “personal data” means any information that relates to, describes, or could be used to identify an individual, directly or indirectly.
Applicability: This Policy applies to personal data that Midjourney collects, uses, and discloses and which may include: (i) data collected through the Services, (ii) data collected through the process of training Midjourney machine learning algorithms, (iii) data collected through Midjourney websites, and (iv) data collected from third party sources. Third party sources may include, but not be limited to: public databases, commercial data sources, and the public internet. When you make purchases, we use third-party payment processors to collect credit card or other financial information. Midjourney does not store the credit card or payment information you provide, only confirmation that payment was made.
This Policy does not apply to the following information:
Changes: We may update this Policy from time-to-time to reflect changes in legal, regulatory, operational requirements, our practices, and other factors. Please check this Policy periodically for updates. If any of the changes are unacceptable to you, you should cease interacting with us. When required under applicable law, we will notify you of any changes to this Policy.
Definitions: Through this Policy, You, or Your means the individual accessing or using the Service, or the company, or other legal entity on behalf of which such individual is accessing or using the Service, as applicable. Company (referred to as either \"the Company\", \"We\", \"Us\" or \"Our\" in this Agreement) refers to Midjourney LLC. Usage Data refers to data collected automatically, either generated by the use of the Service or from the Service infrastructure itself (for example, the duration of a page visit).
2.1 Types of Data Collected
2.1.1 Personal Data
While interacting with the Services, You may provide certain personally identifiable information that could be used to contact or identify You. Personally identifiable information may include, but is not limited to:
2.2 Use of Your Personal Data
Midjourney may use Personal Data for the following purposes:
We may share Your personal information in the following situations:
2.4 Retention of Your Personal Data
The Company will retain Your Personal Data only for as long as is necessary for the purposes set out in this Privacy Policy. We will retain and use Your Personal Data to the extent necessary to comply with our legal obligations (for example, if we are required to retain your data to comply with applicable laws), resolve disputes, and enforce our legal agreements and policies.
The Company will also retain Usage Data for internal analysis purposes. Usage Data is generally retained for a shorter period of time, except when this data is used to strengthen the security or to improve the functionality of Our Service, or We are legally obligated to retain this data for longer time periods.
2.5 Transfer of Your Personal Data
Your information, including Personal Data, is processed at the Company's operating offices and in any other places where the parties involved in the processing are located. It means that this information may be transferred to — and maintained on — computers located outside of Your state, province, country or other governmental jurisdiction where the data protection laws may differ from those in Your jurisdiction.
Your consent to this Privacy Policy followed by Your submission of such information represents Your agreement to that transfer.
The Company will take all steps reasonably necessary to ensure that Your data is treated securely and in accordance with this Privacy Policy and no transfer of Your Personal Data will take place to an organization or a country unless there are adequate controls in place including the security of Your data and other personal information.
The security of Your Personal Data is important to Us, but remember that no method of transmission over the Internet, or method of electronic storage is 100% secure. While We strive to use commercially acceptable means to protect Your Personal Data, We cannot guarantee its absolute security.
Our Service does not address anyone under the age of 13. We do not knowingly collect personally identifiable information from anyone under the age of 13. If You are a parent or guardian and You are aware that Your child has provided Us with Personal Data, please contact Us. If We become aware that We have collected Personal Data from anyone under the age of 13 without verification of parental consent, We take steps to remove that information from Our servers.
If We need to rely on consent as a legal basis for processing Your information and Your country requires consent from a parent, We may require Your parent's consent before We collect and use that information.
Our Service may contain links to other websites that are not operated by Us. If You click on a third party link, You will be directed to that third party's site. We strongly advise You to review the Privacy Policy of every site You visit.
Third party sites and services (including Discord) have separate practices regarding the protection of personal data that you provide to them. We have no control over and assume no responsibility for the content, privacy policies or practices of these third party sites or services.
We may update Our Privacy Policy from time to time. We will notify You of any changes by posting the new Privacy Policy on this page.
We will let You know via email and/or a prominent notice on Our Service, prior to the change becoming effective and update the \"Last updated\" date at the top of this Privacy Policy.
You are advised to review this Privacy Policy periodically for any changes. Changes to this Privacy Policy are effective when they are posted on this page.
Europe
If You are located in the European Economic Area (the “EEA”), Switzerland, or the United Kingdom (the “UK”) Our legal basis for collecting and using the Personal Data described in this Policy will depend on the personal data concerned and the specific context in which we collect it. However, we will normally collect personal data from you only where we have your consent to do so, where we need the personal data to perform a contract with you, or where the processing is in our legitimate interests and not overridden by your data protection interests or fundamental rights and freedoms. In some cases, we may also have a legal obligation to collect personal data from you.
Midjourney may share information internally or with third parties, as further described in this Policy. When we share Personal Data of individuals in the EEA, Switzerland or UK with third parties, we make use of a variety of legal mechanisms to safeguard the transfer including the European Commission-approved standard contractual clauses, as well as additional safeguards where appropriate.
Midjourney uses cookies and similar technologies for analytics and advertising purposes, including to help tailor content and ads. These non-essential cookies will only be used with your explicit consent. You can manage or withdraw your consent at any time by visiting the Privacy Settings page. Essential cookies, which are necessary for the website and our Services to function, are always active. Please refer to our Cookie Policy for more information.
Additionally You have the following data protection rights:
In order to exercise Your rights please visit www.midjourney.com/account and follow the instructions listed at the bottom of the page to delete your account and data. Survey data that you may have submitted can also be accessed and deleted at this link. To access or review your account information, please follow the instructions listed here.
California
This Statement applies solely to residents of California or individuals whose information has been collected in California. Midjourney has adopted and included this notice to comply with the California Consumer Privacy Act of 2018 (“CCPA”). Any terms used in this Statement that are defined in the CCPA have the same meaning given therein.
INFORMATION WE COLLECT
| # | \nCategory | \nCollected? | \nDisclosed? | \n
|---|---|---|---|
| 1 | \n\nIdentifiers. Name, alias, postal address, unique personal identifier, online identifier, Internet Protocol (IP) address, email address, account name, social security number, driver’s license number, passport number, or other similar identifiers | \nYES | \nYES | \n
| 2 | \n\nPersonal information categories under the California Customer Records statute (Cal. Civ. Code § 1798.80(e)). A name, signature, Social Security number, physical characteristics or description, address, telephone number, passport number, driver’s license or state identification card number, insurance policy number, education, employment, employment history, bank account number, credit card number, debit card number, or any other financial information, medical information, or health insurance information. Some personal information included in this category may overlap with other categories. | \nYES | \nYES | \n
| 3 | \n\nProtected classification characteristics under California or federal law. Age (40 years or older), race, color, ancestry, national origin, citizenship, religion or creed, marital status, medical condition, physical or mental disability, sex (including gender, gender identity, gender expression, pregnancy or childbirth and related medical conditions), sexual orientation, veteran or military status, genetic information (including familial genetic information). | \nYES (only the information you share upon consent as part of an applicable survey) | \nYES | \n
| 4 | \n\nCommercial information. Records of personal property, products or services purchased, obtained, or considered, or other purchasing or consuming histories or tendencies. | \nYES | \nYES | \n
| 5 | \n\nBiometric information. Genetic, physiological, behavioral, and biological characteristics, or activity patterns used to extract a template or other identifier or identifying information, such as, fingerprints, faceprints, and voiceprints, iris or retina scans, keystroke, gait, or other physical patterns, and sleep, health, or exercise data. | \nNO | \nNO | \n
| 6 | \n\nInternet or other similar network activity. Browsing history, search history, information on a consumer’s interaction with a website, application, or advertisement. | \nYES | \nYES | \n
| 7 | \n\nGeolocation data. Physical location or movements. | \nNO | \nNO | \n
| 8 | \n\nSensory data. Audio, electronic, visual, thermal, olfactory, or similar information. | \nYES (only images you upload to our services) | \nYES | \n
| 9 | \n\nProfessional or employment-related information. Current or past employment history or performance evaluations. | \nNO | \nNO | \n
| 10 | \n\nEducation Information under California Family Educational Rights and Privacy Act (20 U.S.C. section 1232g, 34 C.F.R. Part 99) Information that is not “publicly available personally identifiable information” as defined in the California Family Educational Rights and Privacy Act (20 U.S.C. section 1232g, 34 C.F.R. Part 99). Includes education records directly related to a student maintained by an educational institution or party acting on its behalf, like grades, transcripts, class lists and student schedules, identification codes, financial information, or disciplinary records. | \nNO | \nNO | \n
| 11 | \n\nInferences Conclusions that could be used to create a profile reflecting an individual’s preferences, characteristics, psychological trends, predispositions, behavior, attitudes, intelligence, abilities, aptitude. | \nYES. | \nYES | \n
YOUR RIGHTS AND CHOICES
The CCPA provides individuals residing in California or whose Personal Information was collected in California with specific rights regarding their Personal information. The below describes your rights and how you may exercise them.
Access to Specific Information and Data Portability Rights
You have the right to request that Midjourney disclose certain information to you about our collection and use of your Personal Information over the past twelve (12) months. Once Midjourney receives and confirms your verifiable information access request, Midjourney must disclose to you: (i) the categories of Personal Information we collected about you; (ii) the categories of sources for the Personal Information we collected about you; (iii) our business or commercial purpose for collecting or, if applicable, selling that Personal Information; (iv) the categories of third parties with whom we share that Personal Information; (v) the specific data points or pieces of Personal Information we collected about you. If we disclosed for a business purpose or sold your Personal Information, Midjourney must also provide separate lists that: (x) identify the personal information categories that were sold to each category of recipient in connection with sales of your Personal Information; and (y) identify the personal information categories that were provided to each category of recipient in connection with business purposes disclosures of your Personal Information..
Deletion Request Rights
You have the right to request that Midjourney delete any of your Personal Information that we collected from you and/or retained. Unless subject to a certain limited exception, once Midjourney receives and confirms your verifiable data deletion request, we will delete (and direct our service providers to delete) your personal information from our records. Midjourney will notify you promptly if it determines it must deny your deletion request.
Do Not Sell or Share Opt-Out Rights
You have the right to opt-out of any “sale” or “sharing”, as defined by the CCPA, of Personal Information by Midjourney. While, Midjourney does not sell your information, we may share it, for example, through advertising cookies that allow our third party partners to deliver relevant and personalized ads. You can opt-out of such sharing at any time by updating your preferences in the Privacy Settings page.
EXERCISING YOUR RIGHTS
To exercise your access, data portability, and deletion or do not sell opt-out rights described above, please visit www.midjourney.com/account and follow the instructions listed at the bottom of the page to delete your account and data (including any survey responses), or go here and follow the instructions listed to access or review your account information.
You may only make a verifiable consumer request for access or data portability up to two times within a 12-month period. You may make a verifiable do not sell opt-out request at any time. Any such request must: (i) provide sufficient information that allows Us to reasonably verify that you are the person about whom we collected personal information or an authorized representative thereof; and (ii) describe your request with sufficient detail such that we may understand, evaluate, and respond to it. Midjourney cannot respond to your request or provide you with personal information if we cannot verify your identity or authority to make the request and confirm the personal information relates to you. Making a verifiable consumer request does not require you to create an account with Midjourney. Midjourney will only use personal information provided in a verifiable consumer request to verify the requestor’s identity or authority to make the request. Only you or a person registered with the California Secretary of State that you authorize to act on your behalf may make a verifiable consumer request related to your Personal Information. You may also make a verifiable consumer request on behalf of your minor child.
Response Timing and Format
We endeavor to respond to a verifiable consumer request within 45 days of its receipt. If we require more time (up to 90 days), we will inform you in writing of the extension period and the reason for it. Midjourney will deliver any required or requested responses or other communications in writing to you by email. Any disclosures we provide will only cover the 12-month period preceding the verifiable consumer request’s receipt. If applicable, the response we provide will also explain any reasons we cannot comply with a request. For data portability requests, Midjourney will provide your personal information in a format that is readily usable and transferable. Midjourney does not charge a fee to process or respond to your verifiable consumer request unless such requests become excessive, repetitive, or manifestly unfounded or as otherwise permitted by the CCPA. If we determine that a request warrants charging a fee, we will notify you and provide you with a cost estimate before completing your request.
"},{"id":32016412137741,"url":"https://midjourney.zendesk.com/api/v2/help_center/en-us/articles/32016412137741.json","html_url":"https://docs.midjourney.com/hc/en-us/articles/32016412137741-GPU-Speed-Fast-Relax-Turbo","author_id":18023535838733,"comments_disabled":false,"draft":false,"promoted":false,"position":2,"vote_sum":0,"vote_count":0,"section_id":28005319720845,"created_at":"2024-11-19T20:04:13Z","updated_at":"2026-06-10T20:52:51Z","name":"GPU Speed (Fast, Relax, Turbo)","title":"GPU Speed (Fast, Relax, Turbo)","source_locale":"en-us","locale":"en-us","outdated":false,"outdated_locales":[],"edited_at":"2026-06-10T20:52:51Z","user_segment_id":null,"permission_group_id":33673142591629,"content_tag_ids":[],"label_names":[],"body":"
Turbo mode is not currently supported in V8.1. For more information about V8.1, see our Version article.
Midjourney uses powerful Graphics Processing Units (GPUs) to handle the prompts you give it and turn them into images and videos. When you subscribe to Midjourney, you're actually buying time to use these GPUs. Think of GPU time like the data you get with a cell phone plan. We offer 3 different GPU speeds to chose from: Fast, Relax, and Turbo.
Note: It's important to understand that GPU time is different from the time you're spending on our website or in Discord, and even from the actual time you wait for your creations. GPU time is only used when Midjourney is actively working to create images/videos for you.
When you're in Fast Mode, you're tapping into your Fast time. This is a set amount of GPU time you receive each month with your Midjourney subscription. Each time your subscription renews, your Fast time is reset. So, it's smart to use up your Fast time before the month ends, because any unused time doesn't carry over to the next month.
To check how much Fast time you have left, head to your Manage Subscription page and look at the usage details. If you're in Discord, you can use the info command to see your remaining Fast time.
Processing one image prompt usually takes about one minute of GPU time, and one video prompt about eight minutes. But remember, different tasks can use more or less. Upscaling images, using nonstandard aspect ratios, or older model versions might require more time. Creating variations or using lower quality settings often uses less.
| \n | Approximate GPU Cost | \n
|---|---|
| SD Prompt (set of 4 images) | \n0.8 minutes | \n
| HD Prompt (set of 4 images) | \n1.3 minutes | \n
| Variation | \nless than 1 minute | \n
| Grid Upscale (Discord only) | \n0 (no cost) | \n
| Creative/Subtle Upscale | \n2 minutes | \n
| Omni Reference Prompt (V7) | \n2 minutes | \n
| Batch of 4 SD Videos | \n8 minutes | \n
| Batch of 4 HD Videos | \n26 minutes | \n
If you need more Fast time before your plan renews, you can purchase additional Fast time on your Manage Subscription page or you may be able to complete tasks on our website to earn free Fast time.
Relax Mode for images is only available to those with Standard, Pro, and Mega Plans. When you switch to Relax Mode, you're using your Relax time, which is unlimited. This means you can create as many images as you want each month without using your Fast time. The tradeoff? Images will take longer to generate compared to Fast Mode.
Relax Mode for SD videos is limited to the Pro and Mega Plans.
In Relax Mode, your prompt requests wait in line to be processed as GPUs free up. This means you might experience wait times ranging from 0 to 30 minutes. How long you wait can depend on how much you've used Relax Mode compared to other users. If you use Relax Mode less often, you'll typically have shorter wait times.
Permutation prompts, the repeat parameter, HD resolution videos, and Max Upscale (a legacy upscaler) are not available while using Relax mode. Relax Mode for videos (SD resolution) is only available on the Pro and Mega Plans.
Want your images super fast? Turbo Mode is for you! When you switch to Turbo Mode, you're using your Fast time. This mode taps into a special, high-speed GPU pool that can generate images up to four times faster than Fast Mode.
Keep in mind that Turbo Mode uses double the Fast time for each image. You can enjoy Turbo Mode with Midjourney versions 5 and later. If the Turbo GPUs aren’t available or you're on an older version, your job will switch automatically to Fast Mode.
Remember, Turbo Mode is experimental, so its availability and costs might change anytime.
Your website and Discord settings are synced. This means that if you change your settings in one place, they'll automatically change in the other—including your generation speed. Double-check your settings to make sure they're set the way you want them before you generate images and videos!
With Settings: You can choose a default GPU speed for all your images in the settings panel by clicking the settings button in the Imagine bar. Once you set it, this speed will apply to all your future prompts.
With Parameters: To override your default generation speed for a specific prompt, you can add the --fast, --relax, or --turbo parameter at the end of your prompt in the Imagine bar.
With Commands: Use /relax, /fast, or /turbo as a standalone command in Discord to switch between speeds.
With Settings: Use the settings command and choose 🐢 Relax Mode 🐇 Fast Mode or ⚡ Turbo Mode from the menu.
With Parameters: To override your default speed for a specific prompt, you can add the --fast, --relax, or --turbo parameter at the end.