Research project for real-time autoregressive generation of multi-shot video narratives from shot-level prompts.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
CausalCine (also referred to as Causal Scene) is a research video generation system that produces long, multi-shot videos autoregressively and streams them in real time. It takes shot-level prompts and reuses memory across shots to keep characters and scenes consistent through a narrative.
According to a YouTube creator summary, it outperforms other long-video autoregressive approaches such as Infinity Rope, LongLive, MemFlow and Self-Forcing. The project page offers a video gallery and comparisons against these baselines. These claims come from the project page and the creator's coverage, and have not been independently verified here.
At the time of the source material, only a project page and paper were reported; no public code, model weights, demo or product access was found. The vendor or authoring institution is not stated in the fetched material.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Video generation system that streams long multi-shot videos in real time from shot-level prompts, reusing memory for consistency. Outperforms Infinity Rope, LongLive, MemFlow and Self-Forcing; only a paper is out so far.
Closest neighbours by meaning, not just by category.
Research
Research method for long-context video generation using hierarchical latents and coarse-to-fine rollout.
Research
Research memory router that lets a frozen autoregressive video generator reuse selected past KV entries for consistency.
Model
Research method for multi-shot text-to-video with frame-accurate cuts, fades and camera moves, built on Wan2.1-T2V-14B.
Research
Research framework for long, consistent video generation using a persistent 3D world state as memory.
Model
Research framework for real-time, causal streaming video editing with diffusion, running at about 12.66 FPS.
Model · Black Forest Labs
Black Forest Labs' video generation model in the FLUX 3 family, with native audio and clips up to 20 seconds.
