Newsletter image

Subscribe to the Newsletter

Join 10k+ people to get notified about new posts, news and tips.

Do not worry we don't spam!

By pressing the Subscribe button, you confirm that you have read and are agreeing to our Privacy Policy and Terms of Use

Search

GDPR Compliance

We use cookies to ensure you get the best experience on our website. By continuing to use our site, you accept our use of cookies, Privacy Policy, and Terms of Service.

MidJourney V7 Is Here: A Peek at What is New

MidJourney V7, released on April 3, 2025, in alpha, introduces several updates for AI image generation. Key features include improved text prompt comprehension, enhanced image texture, default personalization (after unlocking), and a new Draft Mode for quick, cost-effective sketches. Turbo and Relax Modes from previous versions remain for speed and budget adjustments. New parameters include --v 7 for accessing V7 and --draft for Draft Mode. Personalization requires ranking 200 image pairs on MidJourney’s site, and compatibility with some V6 features is maintained, though Remix and Character Reference are unavailable. Users can experiment with V7 by adding specific commands and adjusting settings to fit their workflow. While still developing, V7 offers practical improvements without major overhauls.

Runway Gen-4: AI Video Consistency Unveiled

Runway's Gen-4, released on March 31, 2025, is a groundbreaking AI tool for video creation, addressing the issue of character inconsistency in AI-generated videos. With just one reference image, it ensures character appearance remains consistent across various scenes, lighting, and poses. Key features include character consistency, uniformity of objects and locations, high-quality output, and short scene generation, making it ideal for filmmakers and marketers. Gen-4 is user-friendly, requiring no retraining, and offers significant cost and time savings. While some worry about potential job impacts, the tool is celebrated for enhancing creative storytelling. Its launch coincides with significant developments in the AI industry, further highlighting its importance. Gen-4 promises to make storytelling more accessible and affordable, marking a major advancement in AI video technology.

Gemma 3: Google Open-Source Gambit

Google's new AI model, Gemma 3, aims to outperform rivals while operating on a single GPU, making AI more accessible to developers and startups. Built on Google's Gemini 2.0 architecture, it promises high performance and versatility, handling text, images, and videos efficiently. However, despite being labeled "open," its use is restricted by an Apache 2.0 license with limitations on commercial use and redistribution. This has sparked debate in the open-source community, with some seeing it as a controlled offering rather than true open-source freedom. While early adopters have found innovative uses for Gemma 3, its constraints pose challenges for larger-scale applications. The broader question remains whether tech giants like Google can fully embrace open-source principles without relinquishing control.