New models and features in AI image, video, voice and music generation, from Midjourney, Sora, Veo, Suno and more.
Alibaba researchers just introduced LHM, a reconstruction model that creates high-fidelity, animatable 3D humans from a single 2D image. By relying on 3D Gaussian splatting and a multimodal transformer, it generates fully articulated avatars in seconds without requiring hand or face post-processing.
Pika just teased a new video manipulation tool that lets users modify specific characters or objects while leaving the rest of the frame completely intact. It solves one of AI video's biggest headaches—unwanted background warping—though access is currently limited to selected Creative Partners.
Captions just launched Mirage, an AI model designed specifically for generating UGC-style video ads with virtual spokespersons. Users can supply a script or audio to produce realistic avatars featuring nuanced body language and micro-expressions, with full control over outfits, backdrops, and emotions. It dramatically lowers the bar for scaling testimonial-style ad creative.
Freepik just added Google's flagship video model Veo 2 to its AI Suite, giving users the ability to convert static images directly into high-fidelity video clips. The integration connects image generation, retouching, and motion inside a single workflow. The catch: it is reserved exclusively for Freepik Premium subscribers.
Hedra just unveiled Character-3, an omnimodal AI model that handles image, text, and audio all at once, alongside its Hedra Studio platform. Instead of chaining separate tools to stitch lip-sync and character motion, creators can now generate expressive, synchronized video in a single unified workflow.
Prime Video just started experimenting with AI-assisted dubbing for select licensed movies and TV shows. The initial test covers 12 titles previously lacking dubbed tracks, offering English and Latin American Spanish with human localization pros reviewing the output for quality control.
Deutsche Telekom just partnered with ElevenLabs to embed its Gen FM audio tech directly into the Magenta AI app, letting users turn news articles into podcasts in seconds. The telecom giant also invested in ElevenLabs’ Series C round. It signals a major shift toward making AI speech a default smartphone interface.
Stability AI just teamed up with Arm to run its text-to-audio model, Stable Audio Open, directly on smartphone CPUs without an internet connection. Powered by Arm's KleidiAI libraries, generating an 11-second audio clip dropped from 240 seconds to under 8 seconds—a 30x speedup for on-device creators.
OpenAI just launched its AI video generation tool Sora in the EU and the UK. The rollout officially brings the popular video model to users and creators across both markets.
Ideogram just rolled out Ideogram 2a, its fastest and most cost-effective image model yet, generating photorealistic graphics and typography in seconds. The update cuts pricing by 50% compared to version 2.0 across both the web app and API. Ideogram also introduced public inspiration feeds that let anyone browse top community prompts without logging in.
Pika just launched Pika 2.2, bringing 10-second video generation and crisp 1080p resolution to its platform. The update introduces Pikaframes, giving users control over key frame transitions anywhere between 1 and 10 seconds for more complex visual storytelling.
Mystic just introduced its new Structure Reference tool, giving creators precise control over structural integrity during image generation. It lets users preserve composition across drastically different styles—from cartoons to photorealism—aimed at film, 3D, and architectural concept workflows.
Wonder Dynamics just rolled out Motion Prediction, a new AI model designed to solve occlusion issues in markerless motion capture. It accurately predicts character poses even when actors are hidden behind objects or framed out, reducing manual cleanup for animators.
Alibaba's Tongyi Lab just released Wan2.1, an open-source video generation suite that beats top models like Sora on key benchmarks while running 2.5x faster. It supports bilingual text rendering and video-to-audio, and includes a lightweight 1.3B model that runs locally on an RTX 4090 GPU.
Luma AI just rolled out a new Video to Audio feature in Dream Machine, letting you add sound to your generated clips. You can create audio with a single click or steer it with text prompts. It's currently in beta and free for all users.
Google just quietly revealed pricing for its Veo 2 video generation model, charging 50 cents per second of generated video—which translates to $30 per minute or $1,800 per hour. Unlike OpenAI bundling Sora into a $200 monthly plan, Google is taking a pure pay-as-you-go approach as high-end video generation models finally test commercial waters.
Freepik just partnered with Google to roll out the Veo 2 video generation model, while Google quietly revealed its pricing at 50 cents per second. That adds up to $30 per minute for clips that can run two minutes or longer. Unlike OpenAI bundling Sora into a $200 monthly plan, Google is betting on pay-as-you-go video production.
Pika just launched its official app on the iOS App Store, bringing its AI video generation features straight to mobile. Users can now generate clips on their phones and share them directly to social platforms.
YouTube just upgraded its Shorts feature Dream Screen with Google DeepMind's Veo 2 model, allowing creators to generate standalone AI video clips from text prompts rather than just backgrounds. It offers better real-world physics and camera styling alongside SynthID watermarking, rolling out first in the US, Canada, Australia, and New Zealand.
Stable Diffusion 3.5 Large, alongside Stable Image Ultra and Core, is now available in the Microsoft Azure AI Foundry model catalog. The model brings both text-to-image and image-to-image capabilities with improved prompt adherence, letting enterprise teams integrate visual generation directly into their existing cloud stacks.
