Tencent Open-Sources SCoPE for Precise Camera Control in Video Generation

_akhaliq · x · 2026-08-14

Tencent's ARC Lab team has open-sourced the SCoPE (Sightline-Coordinate Positional Encoding) model, designed to provide precise camera motion control for video diffusion transformers.

The model integrates camera sightlines as positional coordinates into a pretrained video diffusion model. It generates videos based on a first frame, text prompt, and camera trajectory while preserving the original image-to-video prior.

Built on the Wan2.2-I2V model, the release includes self-contained weights (approx. 67GB) with everything required for inference, allowing developers to easily run local video generation with custom camera poses.

Related event: Tencent Open-Sources SCoPE for Precise Camera Control in Video Generation(2 posts)→

Original post →

More from Multimodal

Multimodal channel →