Type a name, or just describe what you need. Results blend keyword and meaning-based search. 17 matches, each with an EU availability status.
Agent
Research project on proactive streaming video agents that infer implicit, evolving user intent and decide when to help.
Model
Streaming real-world video super-resolution using sparse large-model keyframes and a lightweight propagation network.
Research
Research video generation model controlled by local or global force signals, with causal streaming generation.
Model · Alibaba
Alibaba research model for real-time, long-horizon streaming character audio-video generation.
Model · NVIDIA
NVIDIA research system where a code game engine drives a two-step streaming MiniMax-H3 video model for real-time rendering.
Research code that streams video generation chunk by chunk from a rough 3D proxy, built on Code World Model.
Research model for real-time, talking video agents with a single streaming Transformer; 640×368 output at ~200 ms latency.
Research framework for real-time, causal streaming video editing with diffusion, running at about 12.66 FPS.
Model · JD
Open-weights 16B autoregressive diffusion model from JD for real-time, instruction-guided editing of streaming video.
Model · MiniMax
MiniMax video model reportedly fast enough to generate 15-second clips in about 13 seconds, used for live AI streams.
Research model for real-time, audio-driven talking-head video generation from a reference image, using one-step inference.
Library
Open-source command-line toolkit and libraries to record, convert, filter and stream audio and video.
3D reconstruction model that recovers geometry and camera poses from photos or video using a loop transformer.
Alibaba's real-time audio-visual interactive character video model that renders speech and free-form actions.
Alibaba research model for real-time conversational avatars using one transformer over text, audio and video.
Model · Microsoft
Microsoft AI's streaming speech-to-text model for near real-time transcription, succeeded by MAI Transcribe 2.
Alibaba's fast multimodal Qwen model with text, image, audio and video input, 1M-token context and real-time streaming.
