Releases

Midjourney expanded project and folder organization in its alpha web application.

Midjourney retired the V8.0 alpha after V8.2 became available.

Midjourney launched its V8-era dedicated Edit Model.

Midjourney released V8.2 as the default model with improved aesthetics, image quality, personalization, and a new Edit Model.

Midjourney made V8.1 the default image model.

Midjourney released V8.1 with faster rendering, stronger prompt adherence, and native 2K HD images.

CEO David Holz said revenue had significantly surpassed $200 million in 2023 and had increased since then.

Midjourney released an early-access alpha of its V8 image model.

Midjourney expanded web personalization profiles and moodboard workflows.

Midjourney and Spellbrush released Niji V7 with improved coherency, line work, and prompt adherence.

Warner Bros. Discovery filed a copyright lawsuit against Midjourney.

Midjourney introduced higher-definition output for its video model.

Midjourney launched an experimental personalized media feed and streaming experience.

Midjourney added looping, end-frame control, and video generation through the Discord bot.

Midjourney released its first image-to-video model to the full community.

Disney and Universal filed copyright litigation challenging Midjourney's model training and outputs.

V7 introduced Omni Reference for carrying subjects and visual elements into new images.

V7 introduced a fast, lower-cost Draft Mode for rapid iteration.

Midjourney released V7 with improved prompt precision, image coherence, Draft Mode, and Omni Reference.

Midjourney launched Retexture for changing a scene's materials, lighting, and surfaces.

Midjourney launched editing for uploaded external images.

Midjourney introduced personalized Niji generation based on ranked preferences.

Midjourney opened its web creation platform to all users.

Midjourney launched its unified web editing platform for generative image modification.

Midjourney launched a unified editor for reframe, repaint, vary region, pan, and zoom.

Midjourney released V6.1 with improved details, image quality, speed, text, and personalization.

Midjourney expanded shared creation rooms and room visibility on the web.

Midjourney released new Style Reference algorithms and versioning.

Midjourney introduced Character Reference for preserving character appearance across generations.

Midjourney introduced Style Reference for transferring visual style from example images.

Midjourney and Spellbrush released Niji V6.

Midjourney released V6 with better prompt accuracy, text rendering, coherence, and image prompting.

Midjourney introduced its web-based Imagine creation interface.

Midjourney began offering creation through its own web application to eligible existing users.

Midjourney expanded community exploration and discovery of generated images.

Midjourney released V5.2 with improved aesthetics, shorter prompts, and Zoom Out.

Midjourney released V5.1 with stronger default aesthetics and coherence.

Midjourney and Spellbrush released Niji V5 for anime and illustrative generation.

Midjourney released V5 with improved photorealism and prompt understanding.

Midjourney and Spellbrush launched the Niji model collaboration focused on anime and illustration.

Midjourney released V4 with major improvements in realism, artistic coherence, and detail.

Midjourney released V3 as the default image model.

Midjourney opened its image-generation service to the public through its Discord bot.

Midjourney released its second-generation image model.

Midjourney released its first public text-to-image model.

David Holz founded Midjourney as an independent research laboratory focused on new mediums of thought and visual imagination.