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.
ByteDance has released Bernini, an open-source framework that combines an MLLM planner and a DiT renderer to perform six video generation and editing tasks.
Research on the DF26 benchmark shows that both humans and existing detection technologies perform at random levels in detecting the latest AI-generated videos.
VDN-H3 applied hybrid attention to MiniMax H3 to increase video generation speed by up to 74x, but usage is prohibited in South Korea due to license restrictions.
xAI has released the Grok Imagine Video 1.5 agent, powered by its latest Image 2.0 model.
Researchers from Westlake University and NTU released the Code World Model, where a coding agent manages world rules in code and a video model renders them.
H3-World is a technology that enables precise text-based control of character and camera movements with minimal data.
World Labs has unveiled 'Atlas', an integrated world model that generates camera-controllable 1440p HD video from text, image, and 3D data inputs.
World Labs has released Atlas, a spatial intelligence-specialized omni world model that integrates text, image, and 3D processing.
Vercel AI Gateway is offering a 50% discount on request costs for MiniMax H3 and H3 Max models until September 13.
The SGLang Diffusion team accelerated the MiniMax-H3 video generation model by up to 6.24x on eight NVIDIA H200 GPUs using Cache-DiT and SubBlock sparse attention.
Google has released Gemini Omni 1.1 Flash, featuring 4K upscaling and scene extension capabilities.
JD Open Source has released JoyAI-Echo, which supports 5-minute video generation and omnmodal world models.
Alibaba's Wan 3.0 video model has launched on Vercel AI Gateway, offering integrated video generation capabilities.
Vercel AI Gateway has added asynchronous video generation capabilities via webhooks and polling.
Alibaba has released the Wan3.0 model, capable of generating 30-second videos from documents.
The Robbyant team released LingBot-World 2.0, a 14B open-source world model capable of real-time interaction at 720p 60fps.
Meta has released initial beta test results for its Muse video model, demonstrating high image quality and potential audio support.
Tencent ARC released SCoPE, a video generation model that controls camera trajectories.
Magic Hour CEO compared the creative video production capabilities of Fable 5 and Sol 5.6.
Sand AI has released the MAGI-2 preview, a 114B parameter audio-visual MoE model.
Redis developer antirez released h3.c, a C/Metal-based inference engine that runs the MiniMax H3 model on Apple Silicon.
MiniMax has released H3, an open-weight model that generates video and stereo audio simultaneously.
Wan-Animate-2 supports video-based character animation and text-based viewpoint control.
Creators used Gemini Omni to implement everything from camera angle shifts to video style transformations.