New models and features in AI image, video, voice and music generation, from Midjourney, Sora, Veo, Suno and more.
LTX Studio just rolled out dubbing and captions features to help enterprise teams localize video content faster. The move expands the AI video platform into multilingual corporate workflows, though details on supported languages and pricing have not been disclosed yet.
ByteDance and Tsinghua just introduced DreamID-Omni, an AI model that turns reference portraits, text, and voice clips into talking videos. It eliminates lip-sync confusion in multi-person scenes and supports full video face-and-voice editing, with open-source code expected in March.
Google just launched Nano Banana 2 (Gemini 3.1 Flash Image), blending the reasoning and fidelity of its Pro model with blazing-fast Flash generation. It handles subject consistency for up to five characters, real-time web search grounding, and outputs ranging from 512px to 4K resolution. Why it matters: High visual consistency and real-time facts are usually slow and expensive; bringing both to a fast-tier model makes rapid storyboarding and production design vastly more accessible.
QuiverAI just opened public beta access to Arrow 1.0, a generative model built specifically for creating SVG vector graphics rather than standard raster images. It directly outputs scalable, editable vector assets, saving designers and developers the hassle of manual vector tracing.
Google just redesigned its creative platform Flow, folding experimental tools ImageFX and Whisk directly into a single workspace. Creators can now generate assets with the built-in Nano Banana model and immediately use them as ingredients for Veo video generations, alongside new lasso-based natural language precision editing.
Google just updated the Gemini app with a video templates gallery, eliminating the blank-page problem of complex prompting. Users can pick from cinematic styles like Cyberpunk or Action Hero, upload a photo of themselves or a pet to star as the main character, and export in 9:16 vertical video ready for Shorts and Reels.
Replit just rolled out Replit Animation, a new tool powered by Gemini 3.1 Pro designed to spin up viral videos in minutes. The company claims users can literally "vibecode" complete animations, and the announcement clip itself was built entirely inside the tool. It signals a aggressive expansion beyond code into AI multimedia creation.
AMC Theatres just pulled an award-winning AI short film called Thanksgiving Day from its pre-show screenings after intense pushback on social media. The short won a festival prize that promised nationwide cinema exposure, but moviegoers revolted over theaters embracing AI. Why it matters: Traditional theatrical spaces remain a minefield for generative AI, with audience sentiment pushing back hard against cinema adoption.
Leonardo.Ai just kicked off a new brand campaign titled "Yours to Create," urging artists and designers to bring generative tools into their daily workflows. The platform is also handing out 300 free tokens to creators who interact with its launch post on X. It is another clear sign that AI makers are eager to win over the creative community.
Tavus just unveiled Phoenix-4, a real-time human rendering engine that generates full-head motion with millisecond latency and explicit emotion control. Instead of relying on looped video clips and frozen expressions, it actively listens, nods, and shifts moods along with the conversation. Conversational digital humans are finally ditching the uncanny valley.
Google just integrated DeepMind’s latest music generation model, Lyria 3, into the Gemini app in beta. Users can type a prompt or upload photos and videos to generate a 30-second track complete with lyrics and cover art in seconds. All tracks carry SynthID watermarks, and desktop access is rolling out now for users 18 and older.
NVIDIA just introduced LoRAWeave, an image editing approach that learns transformations from visual examples instead of text prompts. Users provide a before-and-after pair alongside a target image, allowing the model to dynamically blend LoRA weights and replicate complex styles like claymation or sketches. It makes tricky, hard-to-prompt visual edits far more precise.
Anam just launched Cara-3, a real-time face-generation model built specifically for interactive AI avatars. It uses a two-stage pipeline to animate any reference image with natural lip-sync and gaze, clocking a 70ms time-to-first-frame on an H200. In blind evaluations, responsiveness correlated far higher with user trust than visual realism alone.
Moonlake AI just launched the open beta for its world modeling agent, promising to build playable games up to 100x faster. Instead of static 3D scenes, it generates physics, audio, and gameplay logic unified across interactive objects. It is rolling out to over 10,000 waitlisted creators, with subscriptions starting at $15 a month.
Krea AI just acquired Wand and launched its native iPad app. The new release pairs traditional drawing tools and custom brushes with Krea's real-time AI engine, letting you sketch on glass while watching the AI render every stroke on the fly.
Runway just rolled out Story Panels, a featured workflow designed to generate entire films, ads, or content from a single image. It lets creators build a catalog of shots with consistent characters, locations, and styles in just a few steps. It basically tackles AI video's biggest headache: keeping scenes from looking disconnected.
ByteDance’s Seed team just launched Seedance 2.0, a video creation model built on a unified multimodal audio-video architecture. Users can mix up to 9 images, 3 video clips, and 3 audio files as references to generate 15-second multi-shot scenes with synchronized dual-channel sound, notably smoothing out multi-person interactions and physical realism.
Researchers just unveiled LUVE, an ultra-high-resolution video generation framework built to synthesize crisp 2K and 4K clips without losing motion coherence. Using latent-space upsampling and dual-frequency experts, it renders fine details down to bee fuzz and ripples. Why it matters: Generating genuine 4K AI video remains notoriously tough, though code has not yet dropped.
Meta just rolled out new Meta AI-powered creative tools on Facebook, turning static profile photos into looping animations like waving or tossing confetti. The update also brings prompt-based image restyling to Stories and adds animated backdrops like falling leaves to text posts. Why it matters: Meta is making generative AI a casual, built-in social toy instead of a standalone utility.
Alibaba's Qwen team just launched Qwen-Image-2.0, a major upgrade to its image generation model. It brings native 2K resolution, seamless text rendering without glitchy letters, and handles up to 1K-token prompts for slides and posters. A lighter architecture also cuts inference times while unifying generation and editing.
