NewsLTX-2.5 ships as a 22B open-weight video model with audiovideo generation
Every SLOP TV News story about video generation.
NewsLTX-2.5 ships as a 22B open-weight video model with audio
ExplainersMiniMax H3 cuts sampling to 4 steps with two open releases
NewsTencent's Hy-Nomas world model ships with no published scores
NVIDIA
NVIDIA JCA co-generates 3D motion and video for any rig
The NVIDIA Research paper keeps 3D motion in a separate model that handles any skeleton, attached to a pretrained video generator by a few cross-attention layers.
HeyGen
HeyGen Video generates picture and sound at $0.02 a second
The model turns one prompt into a 5 to 15 second clip with dialogue, ambience and effects, and HeyGen halves the price through October 31.
mcp
This week in media MCPs: Unity ships 32 skills and two servers retire
Runway and ElevenLabs retired their local MCP servers in the same week Unity shipped 32 official skills for coding agents. Every media-creation MCP server and skill pack we track, with the date each figure was read.
Pruna
Pruna's P-Video-2-Pro-Reference starts at $0.015 a second
Built on MiniMax H3, the model takes up to 9 images, 3 videos and 3 audio files as references, which Pruna bills separately from the output.
Veo 3.1
Google to shut down Veo 3.1 preview models on October 22
The deprecations page points developers to gemini-omni-1.1-flash, Google's August 27 successor, and warns the October 22 date is the earliest possible.
Multics
Tencent opens Multics, a world model for 10 players
One 4-player checkpoint generates video for 6, 8 and 10 players without retraining, using communication across player, group and global levels.
Agnes-Video-2.0-MoE
Agnes Video 2.0 MoE ships open weights under Apache 2.0
The 28.7-billion-parameter model generates video with audio, but its Apache 2.0 label stops at the Agnes core weights and excludes the text encoder and VAE.
HiDream
HiDream's vivago R1 AI video agent goes global
The Beijing lab's agent joins script, storyboard and edit in one chat workflow, and HiDream says it plans to add a model ranked No. 4 for image-to-video.
Prism
Tencent Hunyuan's Prism renders 2K video with sound in one pass
The Fudan and Tencent Hunyuan model is MIT-licensed and open on GitHub, but native 2K output needs four or more 80 GB GPUs.
Kling 4.0
Kling 4.0 doubles its AI video clip length to 30 seconds
Kuaishou's video unit says Kling 4.0 is in testing with selected users, a lite version is open to annual subscribers, and the full model ships in October.
HiDream
HiDream.ai's HiDream V1 Video Model Debuts at 1080p With Synced Audio
HiDream.ai's new omnimodal model can pick its own clip length between 5 and 20 seconds, and the company says it debuted at No. 4 and No. 8 on two video leaderboards.