AI Briefing#video-generation
The latest AI and developer news about #video-generation, with the original source and a short summary.
The latest AI and developer news about #video-generation, with the original source and a short summary.
The new tools include Character Poster, Character Arc, Pixel Machine, Lucid Glass, and Pocket Studio, which are available in the Google Flow studio today.
The model couples a Qwen3.5-9B language model with a 29B MMDiT diffusion backbone to predict video outcomes of actions.
The engine allows AI agents to write standard React and TypeScript code that compiles to GPU-accelerated video, motion graphics, and interactive 3D games, with a 90-frame render taking about one second on Apple Silicon.
The model compresses MiniMax-H3 to 13.7B parameters for 4-8 step generation, running on consumer RTX 5090 GPUs in 92 seconds for 5.2-second clips.
The 16B parameter checkpoints support multi-sensor driving generation and bimanual robot action prediction under the OpenMDW1.1 license.
The model supports clips up to 15 seconds long and offers 30% lower costs than its predecessor, with availability in Google Vids and via API.
The update extends native video generation from 10 to 15 seconds and reduces costs by 30% compared to Omni 1.1, with general availability on the Gemini API and Google Cloud.
The model supports 3-15 second clips with native audio, up to 30 seconds total via extension, and 4K resolution.
The model supports up to 12 reference files, exports five separate audio stems, and ranks #1 among open-weights models and #7 overall on DesignArena’s text-to-video leaderboard.
The release includes full model weights and a creation Skill, with INT4 and INT8 weights planned for later.
The model uses a separate motion branch connected via cross-attention to handle arbitrary skeletons and register motion in 3D scenes.
The open-source tool supports 2D/3D scene composition and integrates models from Sora, Midjourney, and Grok under MIT and Apache-2.0 licenses.
Claude Dashboards and Motion are in beta for paid plans, while Docs, Slides, and Design are now available on the Free plan.
Pollo AI's new Agent feature reduces model-switching time by over 50% for its 26 million users by routing tasks between GPT-5.6 and GPT-6 Astra.
Tencent ARC Releases WorldCrafter: Open-Source Video World Model with Implicit 3D Memory
The lightweight model generates 1-15 second video clips with native audio in resolutions up to 1080p.
The new models include a 29B Pro version and a 3B Lite version, with immediate support for ComfyUI and Diffusers.
The model uses a new dataset of 20,774 clips and a Motion Adapter to ensure view-consistent video generation.
A 201M-parameter SemanTok AR model matches or outperforms a VideoFlexTok AR model 3.4x its size.
The new APIs allow programmatic generation of visuals using models from Google, OpenAI, ByteDance, and Creatify, available for Pro plans and above.
The open-source agent generates deterministic MP4s by having the LLM write HTML/CSS/JS code that is rendered via headless Chromium and ffmpeg, rather than using a generative video model.
Meta has introduced Muse Realtime Avatar, a system that generates synchronized, expressive video from speech tokens with subsecond latency, outperforming Runway and HeyGen in user preference tests.
Higgsfield AI launched new video features in one day using GPT-6 Astra to support ad creation for small businesses.
Video Rebirth has open-sourced 'HyperFlow,' a data-free self-distillation LoRA that reduces MiniMax-H3 inference steps from 49 to 8.