Product
Midjourney
Midjourney is an AI image generation service from Midjourney, Inc. Its open beta began on 12 July 2022 through a Discord bot, and it later added a website, video generation and new model versions.
Era Large models
- Release date
- Developer
- Midjourney
What it is
Midjourney is a generative image service run by Midjourney, Inc. A user describes a picture in text, and the service generates images from that description.
Origins
The first model, V1, came out in February 2022. The open beta, which made the service available to the public, began on 12 July 2022.[1][2]
At first the service was used entirely through a Discord bot. David Holz, its founder, described it as both an image generator and a social network.[3]
Main features
Subscriptions and commercial use. In August 2022 subscriptions cost $10 or $30 a month, and commercial use had only just been permitted.[3]
Moderation. Moderation moved from a list of banned words to AI-based moderation starting in May 2023.[1]
Website. A website interface launched in August 2024, alongside the V6.1 model.[4]
V7. Released in April 2025, V7 made personalization on by default. It also introduced Draft Mode, at half the cost and ten times the speed, and a voice mode on the web.[5]
Video. Video generation launched on 18 June 2025 with the V1 Video model, which was initially web-only.[6]
V8. The V8 alpha, released on 17 March 2026, made image generation about five times faster and added a native 2K --hd mode.[7]
Its place in development
Some Midjourney images have spread online as fakes. Viral fakes made with Midjourney include an image of Pope Francis in a white puffer coat, which circulated in March 2023.[1]
In August 2022, Théâtre D’opéra Spatial, a picture made with Midjourney by Jason Allen, won first place for digital art at the Colorado State Fair. The result prompted debate among artists.[1][8]
The service has moved through several major model versions, from V1 in 2022 to V8 in 2026, and it has added a website, video generation and a voice mode along the way.[1][4][5][6][7]
CapabilitiesImage generation
TechniquesGenerative models
ApplicationsConsumer appsCreative tools
HistoryProduct history
20261
-
ReleaseMidjourney releases the V8 alpha
Midjourney released the V8 alpha on 17 March 2026, generating images about five times faster, with a native 2K --hd mode, improved text rendering, new prompt parameters and a Grid Mode interface. Point releases followed later that year.
20253
-
ReleaseMidjourney launches its first video model
On 18 June 2025, Midjourney released V1, its first video model, which turns images into short clips and names real-time open-world simulation as a long-term goal.
-
PolicyDisney and Universal sue Midjourney
In 2025 Disney and Universal, followed by Warner Bros. Discovery, sued the AI image service Midjourney for copyright infringement; the three cases were later consolidated.
-
ReleaseMidjourney releases the V7 alpha
On 4 April 2025 Midjourney opened the V7 alpha to its community. It brought default personalization, a faster and cheaper Draft Mode, voice prompting on the web, and a conversational prompt bar.
20233
-
ReleaseMidjourney releases V6
On 21 December 2023 Midjourney released version 6 of its image model in alpha, trained from scratch over nine months and better at rendering text. V6.1 followed on 30 July 2024 with faster, more coherent output and became the default model.
-
ReleaseMidjourney releases V5
Midjourney released version 5 of its text-to-image service in alpha on 15 March 2023, after founder David Holz said it would arrive that week. Test images showed a higher default resolution and a wider range of styles, and point releases followed through the summer.
-
PolicyArtists sue Stability AI, Midjourney and DeviantArt over training data
In January 2023 three artists filed a class-action copyright suit against Stability AI, Midjourney and DeviantArt, saying their image generators were trained on artists' work without permission — an early test of how copyright law applies to generative AI.
20223
-
ReleaseMidjourney releases V4 in alpha
On 5 November 2022 Midjourney released the alpha version of V4, its fourth numbered image model, which was trained on Google TPUs and was described as a large jump in quality over V3.
-
MilestoneMidjourney image wins the Colorado State Fair digital art prize
In August 2022 an image made with Midjourney by Jason Allen, Théâtre D'opéra Spatial, took first place in the digital art category at the Colorado State Fair, setting off a widely reported argument about AI-generated art.
-
ReleaseMidjourney opens its public beta
On 12 July 2022 Midjourney opened its text-to-image generator to the public as an open beta, run entirely through a bot on Discord, with subscriptions costing $10 or $30 a month.
Developed by1
Powered by3
Notes and sources
- Midjourneyhttps://en.wikipedia.org/wiki/Midjourney
- Midjourney open beta announcementhttps://twitter.com/midjourney/status/1547108864788553729
- David Holz, founder of AI art generator Midjourney, on the future of imaginghttps://www.theregister.com/2022/08/01/david_holz_midjourney/
- Midjourney launches website interface for its AI image generatorhttps://petapixel.com/2024/08/23/midjourney-launches-website-interface-for-its-ai-image-generator/
- V7 Alphahttps://updates.midjourney.com/v7-alpha/
- Introducing Our V1 Video Modelhttps://updates.midjourney.com/introducing-our-v1-video-model/
- V8 Alphahttps://updates.midjourney.com/v8-alpha/
- An A.I.-Generated Picture Won an Art Prize. Artists Aren’t Happy.https://www.nytimes.com/2022/09/02/technology/ai-artificial-intelligence-artists.html
Cite this page: Midjourney. TellWorld, https://www.tellworld.net/products/midjourney. Updated 2026-11-08