Midjourney just added custom start and end frame support to its AI video features, letting creators morph between two distinct images or produce seamless loops. The video workflow is now directly accessible inside the Discord bot as well, though the web interface remains the recommended experience.
Midjourney just announced it is investigating opening up an Enterprise API so companies can integrate its image generation tools into their own services. The team has shared an application form to figure out what features businesses actually need and gather interest for upcoming updates.
Midjourney just launched V1, its first-ever video generation model. Available exclusively on the web, the tool turns any still image into four 5-second clips that can be extended up to 20 seconds. It carries over the company's trademark aesthetic at a claimed 25x lower cost than rivals, though it is currently image-to-video only and lacks native audio.
Disney and Universal just sued Midjourney in a major legal showdown, calling the AI image generator a "bottomless pit of plagiarism" for churning out unauthorized copies of Darth Vader, Shrek, and Minions. The entertainment giants also targeted Midjourney's upcoming video generator and demanded a jury trial.
Midjourney just launched Omni-Reference, a new feature built to drop specific characters, objects, and vehicles directly into generated scenes. It basically acts as a "put THIS in my image" command, giving creators tighter consistency control without endlessly rerolling prompts.
Midjourney just rolled out an update to its V7 model, boosting overall quality alongside hand and body coherence without requiring new settings. The release introduces a redesigned lightbox editor with smart segmentation, plus a new experimental --exp aesthetic parameter that adds punchy detailing and tone mapping to your generations.
Midjourney just rolled out the alpha version of its V7 image model, marking its first major release in nearly a year. Built on a brand-new architecture, V7 improves prompt adherence, body and hand coherence, and turns on personalization by default. It also introduces a Draft Mode that renders 10x faster at half the cost, though standard upscaling tools aren't live yet.
Midjourney just wrapped up its months-long "RELAX-ATHON" perks as it preps its server clusters for the V7 rollout. The company hinted that users will start having even more fun "soon," signaling that its long-awaited next-gen image model is finally right around the corner.
Midjourney just teamed up with NYU researchers to tackle AI's biggest creative flaw: bland, repetitive writing. By introducing two new training methods called DDPO and DORPO, they reward rare and unique high-quality responses during fine-tuning on models like Llama 3.1. It turns out the image generator has serious ambitions for text, too.
Midjourney just rolled out Pinterest-inspired moodboards and multi-profile personalization, letting creators train custom aesthetic models directly from curated image collections. Users now only need 40 image ratings to build a profile instead of 200, and can seamlessly switch between distinct named styles for different creative projects.
Midjourney just revealed Patchwork, a standalone web-based infinite canvas designed for collaborative storytelling. Powered by at least three LLMs, it lets up to 100 users map out characters, events, and scenes together in real time. It is rolling out as an early research preview for users who link their Discord and Google accounts.
A striking photo of 70 cars wrecked by Spain's Valencia floods went viral, only for users to immediately dismiss it as "AI slop." Generative AI is now so pervasive on social feeds that people are predisposed to disbelieve reality itself. While platforms push more synthetic content for engagement, the byproduct is an erosion of trust in genuine news photos.
A mysterious new AI image generator called Red Panda just claimed the top spot on Artificial Analysis's Text-to-Image Arena leaderboard. It boasts an Elo score of 1172 and a 72% win rate, beating out Midjourney v6, DALL-E 3, and FLUX 1.1 [pro]. The creator remains unknown, but it is likely an unreleased model undergoing blind testing before launch.
Jason M. Allen, the creator who sparked backlash in 2022 for winning an art contest with a Midjourney image, is now suing the U.S. Copyright Office after it rejected his registration. Allen claims copycats are ripping off 'Théâtre D’opéra Spatial' on OpenSea and Etsy, arguing his extensive prompting and Photoshop edits count as human authorship.
Midjourney just announced it is officially getting into hardware, setting up a specialized team in San Francisco. The bootstrapped image generator previously hired former Neuralink staffer and Apple Vision Pro engineer Ahmad Abbas. With new video and 3D models already in the works, Midjourney might be crafting dedicated physical gear for creative AI.
Midjourney just opened its web app to everyone, ditching the requirement to use its clunky Discord server. Anyone logging in with a Google or Discord account now gets a free trial of 25 image generations before needing a paid plan. Why it matters: It dramatically lowers the barrier to entry for casual creators who just want a clean browser UI.
Midjourney just launched a unified web editor that brings inpainting and canvas expansion together into a single screen. It swaps out the old box selectors for a precision virtual brush, giving artists much finer control over visual edits. Anyone who has generated at least 10 images can jump in now, plus web rooms now sync directly with Discord.
A federal judge just allowed a major copyright and trademark lawsuit by artists against Stability AI, Midjourney, DeviantArt, and Runway to move forward. The ruling gives artists the green light to pursue claims over Midjourney's 4,700-artist style list and Stability's alleged induced infringement. Why it matters: The case now enters the discovery phase, meaning AI image makers may soon be forced to open up their closely guarded training black boxes.
Midjourney just launched V6.1 as its new default image model. The update delivers cleaner hands, faces, and textures, smarter text rendering, and a 25% boost in standard generation speeds, alongside an upgraded 2x upscaler. Inpainting and zooming still temporarily fall back to V6.0.
Grok's standalone web codebase was just found to contain direct references to Midjourney, backing up earlier rumors of a partnership between xAI and the leading image platform. If true, Grok 1.5 could soon leverage Midjourney via API to output visuals, alongside upcoming image upload and vision capabilities.
