A mysterious new video model called HappyHorse-1.0 just debuted at #1 across both text-to-video and image-to-video leaderboards. Early testing highlights its ability to generate seamless multi-shot clips and accurately follow detailed directional prompts. Why it matters: Dual dominance on major benchmarks indicates a serious new contender has quietly entered the heated AI video race.
Runway just brought Seedance 2.0 to its platform, letting creators generate full multi-shot video sequences complete with sound design and dialogue. It takes text, images, video, or audio as prompts. The catch: it is currently limited to Unlimited and Enterprise users outside the US.
Researchers just introduced Vanast, a unified framework that merges virtual try-on with human motion. You feed it a single portrait, clothing images, and a pose video, and it generates a fluid animation of the person wearing the new outfit while keeping their face and body shape intact. Code is expected to drop soon.
OpenAI's next-gen image model, GPT-Image-2, has reportedly leaked onto the Arena platform under several tape-themed aliases. Developer Pieter Levels noted the mystery models demonstrate exceptionally strong world knowledge and text rendering, potentially beating Nano Banana Pro. OpenAI has yet to officially confirm the testing.
Researchers just introduced MMPhysVideo, a new framework designed to stop AI-generated videos from warping and defying physical common sense. Instead of guessing the next frame purely by pixels, it combines geometry and motion trajectories into unified multimodal training without bloating inference latency, and the team plans to fully open-source the project.
Google just added Veo 3.1 video generation to Google Vids, giving all personal accounts 10 free video generations each month. Paid Google AI Pro and Ultra subscribers also get custom music generation via Lyria 3 and directable AI avatars, along with a Chrome screen recorder and direct-to-YouTube publishing. It turns Google's business-focused video suite into an accessible creative hub for casual users and power creators alike.
Alibaba just launched Wan2.7-Image, a unified model that combines image generation, editing, and understanding. It renders print-quality text across 12 languages, offers precise facial and HEX color controls, and outputs up to 12 consistent images per prompt, solving a major headache for multi-panel creators.
Alibaba just rolled out Wan 2.7 Image, a unified model that handles both generation and precision editing. It focuses on lifelike human faces with natural variation, lets creators lock brand palettes using up to eight hex codes, and renders multi-language text up to 3,000 tokens. Why it matters: Pumping out up to 12 consistent shots in a single prompt makes storyboards and marketing assets far easier to build.
Google just launched Veo 3.1 Lite, its most cost-effective video generation model yet. It delivers the same speed as Veo 3.1 Fast at less than half the cost, supporting text-to-video and image-to-video at up to 1080p. Developers can access it now via Google AI Studio and the Gemini API, with price cuts for Veo 3.1 Fast slated for April 7.
LongCat just launched LongCat Audio Edit, a diffusion-based TTS model capable of cloning anyone's voice with just a few seconds of audio. It comes in a 3.5B parameter flagship version and a 6GB lightweight variant that fits comfortably on consumer GPUs.
ByteDance just introduced DreamLite, a compact 0.39B diffusion model that handles both text-to-image generation and image editing directly on smartphones. It can generate a 1024×1024 image in around 3 seconds on an iPhone, swap styles, and remove objects completely offline. While fine details still lag behind massive server models, it brings fast, private image manipulation right to local devices.
Researchers just introduced TokenDial, a framework that lets users tweak text-to-video attributes like smoke volume or dance motion using a continuous slider. By learning token offsets without retraining base models, it replaces prompt guesswork with predictable, fine-grained control over both visuals and dynamics.
Suno just rolled out v5.5 of its AI music generation platform, aiming to make songs sound much more personal and expressive. The update lets creators weave their own voice, sonic identity, and musical tastes into tracks, though Suno hasn't dropped any technical specs or model benchmarks yet. It's a clear push to turn generic AI tunes into signature tracks.
Google just introduced Lyria 3 Pro, its most advanced music generation model that crafts tracks up to 3 minutes long with built-in structural awareness for intros, verses, choruses, and bridges. It is now rolling out across Google AI Studio, Vertex AI, ProducerAI, and the Gemini app for paid subscribers. Every output includes SynthID watermarking to prevent artist impersonation.
Lovart just launched Move Object, letting users reposition elements in an image without messing with masks or layers. Grab a lasso or box selection, drag the object anywhere, and optionally add a prompt tweak to get a clean, seamless output. It basically kills the annoying loop of manual inpainting and constant re-rolls.
RealMaster can convert 3D rendered game footage into photorealistic video without messing up underlying geometry. Unlike competing editors that distort details, it preserves original shapes, shadows, and motion logic, making it equally useful for upgrading synthetic autonomous driving simulation datasets.
OpenAI just announced it is discontinuing its video generation model Sora. The web and mobile apps will go offline on April 26, 2026, with the API shutting down on September 24. Users need to export their creations before data is permanently deleted; unused credits can be applied to Codex.
The Sora team just announced that it is saying goodbye to the platform, confirming plans to shut down both its app and API. The team acknowledged the disappointing news, thanked the creator community, and promised to release a concrete timeline along with details on preserving existing user projects soon.
Smallest.ai just launched Lightning V3, a TTS model engineered specifically for streaming conversational agents instead of static narration. It handles 15 languages with fluid mid-sentence code-switching, accepts explicit prompts for whispering and emotional intensity, and can clone voices from just 5 to 15 seconds of raw audio. Why it matters: conversational realism requires realistic cognitive hesitation, not just robotic fluency.
Instagram is rolling out a new "AI Transition" tool for Stories that uses AI morphing to stitch multiple still photos into a seamless video clip. Users just pick two or more images, let Meta AI generate the sequence, and can even save it to repost on Reels. It requires accepting Meta AI terms and is currently rolling out to select accounts.
Microsoft just launched MAI-Image-2, pushing its in-house model to #3 on the Arena.ai text-to-image leaderboard. The update focuses on lifelike photorealism, cleaner in-image typography for slides and posters, and richer complex scenes. It is already rolling out across Copilot and Bing Image Creator, giving designers a direct alternative to existing image generators.
