S2PD: Serial-to-Parallel Diffusion for Physically and Logically Consistent Video Generation introduces a hybrid diffusion approach that first applies autoregressive diffusion at high noise levels and then switches to parallel diffusion at low noise levels. This method coordinates interdependent events to produce valid state transitions while reducing sampling time compared to fully serial generation. Implemented with a pixel‑space diffusion transformer and a LoRA‑fine‑tuned pretrained video model, S2PD outperforms bidirectional baselines in rule adherence and achieves greater temporal stability and sampling efficiency across games, physical simulations, and real video.
arXiv:2601. 09881v2 Announce Type: replace-cross Abstract: Large video diffusion and flow models have achieved remarkable success in high-quality video generation, but their use in real-time interactive applications remains limited due to their inefficient multi-step sampling process.
Diffusion-based video restoration recovers realistic details, but its practical deployment is limited by two efficiency bottlenecks: costly VAE encoding and decoding, and the quadratic cost of full se...
arXiv:2607. 13031v1 Announce Type: new Abstract: When one ball strikes another, then another, video models should predict the consequences of each bounce.
arXiv:2607. 03803v1 Announce Type: cross Abstract: The growing demand for image-to-video creation on mobile devices has increasingly focused on cinematic motion effects like bullet time, dolly zoom, slow motion, etc.
We explore large-scale training of generative models on video data. Specifically, we train text-conditional diffusion models jointly on videos and images of variable durations, resolutions and aspect ratios.
When one ball strikes another, then another, video models should predict the consequences of each bounce. In controlled experiments on multi-ball hard-sphere dynamics, we find that the performance of standard bidirectional video diffusion degrades as the causal chain lengthens, even when provided more denoising steps.
ActDiff-VC is a diffusion-based video compression framework designed for ultra‑low‑bitrate scenarios. It partitions videos into variable‑length segments, transmits keyframes only when necessary, and encodes temporal dynamics with a compact set of tracked point trajectories. Conditioned on these sparse signals, a conditional diffusion decoder reconstructs the remaining frames, achieving significant bitrate reductions and perceptual quality gains compared to strong learned codecs.
arXiv:2403. 07711v5 Announce Type: replace-cross Abstract: Given the remarkable achievements in image generation through diffusion models, the research community has shown increasing interest in extending these models to video generation.
arXiv:2508.15774v2 Announce Type: replace Abstract: Visual diffusion models achieve remarkable progress, yet they are typically trained at limited resolutions due to the lack of high-resolution data...
FastVR is a streaming video restoration framework that uses a one‑step diffusion model to achieve strong restoration quality and temporal consistency while processing 1080p video at 11 FPS on a single H20 GPU. It addresses efficiency bottlenecks by combining a lightweight VAE with chunk‑wise causal attention, and improves inference speed and restoration quality through velocity consistency regularization and continuous trajectory learning during training. Experiments demonstrate that FastVR outperforms diffusion baselines in efficiency and achieves state‑of‑the‑art performance on both synthetic and real‑world benchmarks.
arXiv:2609.15863v1 Announce Type: new Abstract: Video diffusion models are stochastic and hard to control: precise content often requires repeated sampling without guaranteed success, and long-horizo...
Real-time video editing requires low-latency causal generation with bounded computational resources while preserving source fidelity and long-term temporal consistency. We present JoyAI-Video-Edit, a 16B-parameter autoregressive diffusion framework for real-time, open-ended video editing without access to future frames or a predefined video duration.