Midjourney
Midjourney is a paid AI image and video generator from the independent lab Midjourney, Inc. Plans run from $10 to $120 a month with no free tier, and its default model since Jul 24, 2026 is V8.2.
Midjourney is a subscription AI image generator, made by the San Francisco lab Midjourney, Inc., whose current default model is V8.2, released on Jul 24, 2026; plans cost $10, $30, $60 or $120 a month (as of Nov 6, 2026), there is no free tier, and every plan can also turn an image into a short video. It is best known for a strong default look: images come out styled and polished even from short prompts, and Personalization learns your own taste from images you rate.
Pick Midjourney when the look of the image matters most and you will work in its web app. Pick something else when you need readable text inside the image (Ideogram or GPT Image), precise edits by plain instruction (Nano Banana), an API for your own app (Midjourney publishes none in its docs; Flux and Nano Banana do), open weights you can run yourself (Stable Diffusion or Flux), or a tool whose maker states it was trained only on licensed images (Adobe Firefly). The Best AI Image Generator guide compares them all.
Quick facts
| Maker | Midjourney, Inc. (independent; CEO David Holz) |
| Launched | Open beta in Jul 2022 |
| Get it | midjourney.com (web) and Discord |
| Price | Basic $10 a month, no free tier (as of Nov 6, 2026) |
| Default model | V8.2, since Jul 24, 2026 |
| Anime model | Niji 7, since Jan 9, 2026 |
| Video | Image to video, 5 seconds, extendable to 21 seconds |
| Best for | Styled, artistic images with little prompt work |
| Open weights | No |
Plans and prices
| Plan | Monthly | Yearly | Fast GPU time | What else you get |
|---|---|---|---|---|
| Basic | $10 | $96 ($8 a month) | 3.3 hours | Fast mode only; SD video |
| Standard | $30 | $288 ($24 a month) | 15 hours | Unlimited Relax images; HD video |
| Pro | $60 | $576 ($48 a month) | 30 hours | Stealth Mode, Relax SD video, 12 fast jobs at once |
| Mega | $120 | $1,152 ($96 a month) | 60 hours | As Pro, with 12 fast video jobs at once |
Source: Comparing Midjourney Plans, as of Nov 6, 2026. Extra fast time costs $4 an hour on every plan, and yearly billing saves 20%.
Fast GPU time is the meter: an image job uses some minutes of it, and "Relax" queues jobs at no cost but more slowly. A V8.1 or V8.2 job costs 0.8 minutes in SD and 1.3 minutes in HD. Midjourney's terms let any paying subscriber use their images commercially, but a company with more than $1,000,000 a year in gross revenue must be on Pro or Mega.
Features
Image models. V8.2 became the default on Jul 24, 2026 and, in Midjourney's words, aims at bolder, more sophisticated images and better Personalization. It brought the Edit Model, which replaced Omni Reference, Character Reference and Retexture with one way to change an image using reference images and plain instructions. V8.1 (Apr 14, 2026) made standard jobs about four to five times faster than earlier versions and added HD images at 2048 pixels without upscaling. Older versions back to V6 can still be chosen with --v.
Personalization and moodboards. You rate pairs of images to build a profile, or collect images into a moodboard, and Midjourney steers new images toward that taste. This is the main thing rivals do not copy closely.
Video. Midjourney's first video model, V1, launched on Jun 18, 2025. It animates any image into four 5-second clips, with low or high motion, an optional end frame or loop, and up to four 4-second extensions (21 seconds at most). Video is 480p, or 720p on Standard and up, and a batch of four SD clips costs 8 minutes of fast time. It has no sound and does not start from text alone, so for longer clips with audio see Veo, Kling, Runway or the Best AI Video Generator.
Privacy of your images. Images made on Basic and Standard are visible in Midjourney's public gallery; Stealth Mode, on Pro and Mega only, keeps them private.
Lawsuits
Disney and Universal sued Midjourney for copyright infringement in federal court in Los Angeles in Jun 2025, citing images of characters such as Darth Vader and the Minions. Warner Bros. Discovery filed a similar suit in Sep 2025 over Superman, Batman and Scooby-Doo. Midjourney has denied the claims, arguing its training is transformative. In Jun 2026 a magistrate judge ordered the studios to hand over some data on their own use of AI. No ruling on the merits had been reported as of Nov 6, 2026.
Midjourney vs the alternatives
- GPT Image in ChatGPT: better at following long instructions and putting exact text in images, and usable free in ChatGPT; Midjourney's default style is more artistic.
- Nano Banana in Gemini: stronger for editing a photo you already have by describing the change, with a free tier.
- Ideogram: built around text and typography, such as posters and logos.
- Flux and Stable Diffusion: open weights you can run on your own computer, with APIs.
- Adobe Firefly: for work where Adobe's statement about licensed training data matters, inside Photoshop and Express.
Frequently asked questions
Is Midjourney free? No. Midjourney has no free tier as of Nov 6, 2026: you must subscribe to a plan, the cheapest being Basic at $10 a month or $96 a year.
What is the latest Midjourney version? The default Midjourney model is V8.2, released on Jul 24, 2026, after V8.1 (Apr 14, 2026) and V7 (Apr 3, 2025). Niji 7 is the separate anime model.
Can Midjourney make videos? Yes. Midjourney's video model turns an image into 5-second clips that can be extended to 21 seconds, at 480p on every plan and 720p from the $30 Standard plan up.
Does Midjourney have an API? Midjourney's own documentation describes only the website and Discord, and no official API is offered there as of Nov 6, 2026.
Can I use Midjourney images commercially? Yes, any paying Midjourney subscriber may use their images commercially, but companies earning over $1 million a year must be on the Pro or Mega plan.
Sources
- Comparing Midjourney Plans, Midjourney, read Nov 6, 2026
- Version, Midjourney, read Nov 6, 2026
- Video, Midjourney, read Nov 6, 2026
- Midjourney launches its first AI video generation model, V1, TechCrunch, Jun 18, 2025
- Midjourney's AI art goes live for everyone, PCWorld, Jul 2022
- Disney and Universal sue AI image company Midjourney, NBC News, Jun 11, 2025
- Warner Bros. Discovery Sues Midjourney for Copyright Theft, PetaPixel, Sep 5, 2025
- Midjourney Faces Discovery Limits Into Studios' AI Use, Law360, Jun 16, 2026
- Midjourney Update | August 2026: New EDIT Model | How It Works & What It Can Do, Woollyfern, Sep 1, 2026 (video)
- Introducing Midjourney V1 Video, Midjourney, Jun 18, 2025 (video)
Moments
Midjourney Update | August 2026: New EDIT Model | How It Works & What It Can Do
Woollyfern
Introducing Midjourney V1 Video
Midjourney
See also
-
IdeogramIdeogram is an AI image generator built for graphic design and text inside images. It is free with 30 credits a week, Plus costs $20 a month, and its newest model, Ideogram 4.5, focuses on precise multi-step editing. -
GPT ImageGPT Image is OpenAI's image generation model family, used in ChatGPT (as ChatGPT Images) and in the API. The latest, ChatGPT Images 2.6, arrived on Nov 4, 2026; it is free to try in ChatGPT with limits, and the API version costs $30 per million image output tokens. -
Nano BananaNano Banana is Google's name for its Gemini image generation and editing models. The newest, Nano Banana 2.1, came out on Oct 6, 2026; it is free to use with limits in the Gemini app and costs about $0.034 per 1K image in the Gemini API.
-
FluxFlux is the family of image (and now video) models from Black Forest Labs, some with open weights you can run yourself. The newest open image model, Flux 3 Image Klein (Oct 15, 2026), is free for commercial use under $5 million in revenue, and the API starts at $0.009 an image. -
Stable DiffusionStable Diffusion is Stability AI's family of open image models (SD 1.5, SDXL, SD 3.5) that anyone can download and run on their own computer. SD 3.5 is free to use commercially for those under $1 million in annual revenue, and Stability's API charges from $0.025 an image.
-
Adobe FireflyAdobe Firefly is Adobe's AI app for images, video and audio, with its own Firefly models (trained, Adobe says, on licensed and public domain content) and partner models from Google, OpenAI and others. It has free daily generations, and paid plans start at $9.99 a month.