FineVideo: behind the scenes

How Higgsfield turns simple ideas into cinematic social videos

Discover how Higgsfield gives creators cinematic, social-first video output from simple inputs using OpenAI GPT-4. 1, GPT-5, and Sora 2.

JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion

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.

Introducing Waypoint-1: Real-time interactive video diffusion from Overworld

Controllable Video Object Insertion via Multi-View Priors

arXiv:2604. 14556v2 Announce Type: replace-cross Abstract: Video object insertion places a user-specified object in an existing dynamic scene.

SmolVLM2: Bringing Video Understanding to Every Device

TeleMorpher: Toward Robust Simultaneous Motion-Location Editing

arXiv:2606. 19676v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success in image and video generation and editing.

OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data

arXiv:2606. 13432v1 Announce Type: cross Abstract: Cloning camera motion from reference videos is an important task in video generation, as videos provide intuitive and precise control.

A Dive into Text-to-Video Models

Build awesome datasets for video generation

EVIS: A Physics-Grounded Event Camera Plugin for NVIDIA Isaac Sim

Event cameras offer microsecond temporal resolution, low latency, and high dynamic range, making them attractive for robotics. However, labeled event-camera data for a specific robot and scene is scarce and expensive to collect, which slows the development of event-based perception and control.

MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention

arXiv:2606. 07639v1 Announce Type: cross Abstract: Video understanding is shifting from the offline paradigm -- taking a fully recorded video as input and producing a single answer after it ends -- toward real-time interaction, in which the model perceives new frames while still replying, revises its answer as new evidence appears, and remains silent when there is nothing to say.

OSVE: One Step Video Editing with One Step Diffusion Models

arXiv:2607. 19895v1 Announce Type: cross Abstract: Text-guided video editing with diffusion models is impractically slow, hindered by costly multi-step sampling and inversion.