New models and features in AI image, video, voice and music generation, from Midjourney, Sora, Veo, Suno and more.
Plai Labs just launched PlaiDay, a free text-to-video generator that lets you star in your own clips by uploading a selfie. The tool produces 3-second animated videos based on text prompts, relying on internal platform Orchestra. Why it matters: Adding personal likeness gives generative video a social hook, though facial rendering can still look pretty distorted.
AI video platform Kaiber just launched its official mobile app on iOS and Android. Known for powering music videos for artists like Linkin Park, the app brings text-to-video, image-to-video, and video-to-video tools alongside curated music presets to mobile devices. Users get 100 free credits, with paid tiers starting at $5 per month.
Runway just rolled out a quality update for its Gen-2 video generator, boosting fidelity and consistency across both text-to-video and image-to-video modes. The upgrade specifically targets AI video warping, making generated motion look significantly smoother.
Midjourney just launched Style Tuner, a tool that lets creators generate reusable aesthetic profiles. Running the /tune command creates a personalized web page where you pick your favorite visual samples, which spits out a custom style code you can attach to any future prompt.
Luma AI just launched Genie, a free research preview of its text-to-3D model accessible directly inside Discord. Users enter a prompt to get four simple 3D drafts in about 20 seconds, complete with glb export and a 20-minute refinement option. Why it matters: Generating usable 3D assets in seconds brings the Midjourney moment to game dev and virtual production.
Stability AI just introduced Stable 3D, an automated tool that turns text prompts and 2D images into textured .obj 3D models in minutes. Alongside it, the company rolled out an outdoor Sky Replacer tool and enterprise-ready model fine-tuning. For now, Stable 3D is available via private preview.
Deemos just launched Rodin Gen-1, a generative AI model that turns plain text prompts into complex 3D models with PBR textures. While the generated visual results look sharp, the studio notes that artists will still need to retopologize the meshes before dropping them into production.
The Beatles just announced that their final collaborative track, “Now and Then,” is dropping on November 2nd. Using the machine learning tech developed for Peter Jackson’s Get Back docuseries, producers successfully isolated John Lennon’s vocals from an unreleased 1970s demo cassette. It’s a remarkable showcase of AI unearthing lost music history without faking it.
YouTube Music just rolled out a generative AI tool to create custom playlist cover art, replacing the old four-album grid. Users can pick categories and prompts to get five tailored image options, though you still can't upload personal photos. It is currently rolling out to English users in the US.
YouTube is developing an AI voice-cloning tool that lets creators mimic famous musicians while recording audio, according to Bloomberg. The streaming giant is currently in talks with major record labels to license their music catalogs for AI training. Why it matters: Following a wave of viral AI deepfakes, YouTube is trying to legitimize voice cloning into an officially licensed creator tool—if record labels agree to sign on.
OpenAI just launched DALL·E 3 for ChatGPT Plus and Enterprise users, letting people generate and refine images directly inside conversations. The model brings major upgrades to tricky rendering tasks like text, hands, and faces, and follows detailed prompts much more faithfully. OpenAI also added guardrails to block requests mimicking living artists and shared progress on a 99% accurate image provenance tool.
Midjourney just launched its first official mobile app by teaming up with Sizigi Studios to release Niji Journey on iOS and Android. While primarily tailored for anime styles, users can toggle settings to generate standard Midjourney imagery as well. Existing subscribers can log in via Discord, finally getting an escape hatch from chat rooms.
Masterpiece Studio and NVIDIA just rolled out Masterpiece X – Generate, a browser-based text-to-3D playground powered by NVIDIA Picasso. Creators can turn simple text prompts into rigged and textured 3D models of humans, animals, or objects, then export them directly into Blender, Unity, or Unreal Engine. While it is not meant for AAA game assets, it dramatically lowers the barrier for rapid 3D prototyping.
ElevenLabs just teamed up with video generation platform Pictory AI to bring its realistic voice synthesis to automated video editing. Creators can now turn text scripts and blog posts into videos with human-sounding narration, initially focusing on English and German content.
Adobe just showcased 11 experimental AI prototypes during its MAX Sneaks session, spanning video, audio, 3D, and design. Highlights include Project Fast Fill, which brings generative fill to video frames via text prompts, and Project Primrose, a dynamic fabric dress that transforms patterns in real time. While these are research projects, they offer a glimpse into the next generation of creative editing tools.
Adobe just unveiled Firefly Image 2 at Adobe MAX, bringing photorealistic detail, camera-like controls, and style-matching capabilities. The company also debuted the first generative AI model for vector graphics inside Illustrator and rolled out text-to-template in Express. Commercial safety remains the core pitch.
Disney just found itself under fire from the creative community over a Loki Season 2 poster suspected of using generative AI in its background. While artists flagged artifacts in the Shutterstock stock image, Shutterstock later investigated and insisted the piece was crafted with traditional software rather than AI tools.
Meta's new Emu-powered sticker generator is already dodging its own guardrails. While direct sensitive prompts get blocked, simple synonyms and creative phrasing easily churn out kids with weapons, cartoon nudity, and graphic political caricatures. It is a stark reminder of how porous AI content moderation still is when rolled out to billions of users.
Getty Images just teamed up with Nvidia to launch Generative AI by Getty Images, an image generator trained strictly on Getty’s proprietary licensed library. The tool offers full copyright indemnification for commercial users and blocks prompts featuring real-world figures or specific artist styles. Why it matters: As copyright lawsuits mount across the industry, Getty is betting that legally bulletproof images will win over cautious enterprise clients.
YouTube just announced a suite of creator tools, headlined by Dream Screen, an experimental feature that generates video or image backgrounds for Shorts from simple text prompts. The company also launched YouTube Create, a free mobile editing app with auto-captions and beat matching. Dream Screen will begin testing with select creators later this year.
