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)→
More from Multimodal
- Flux 3 Klien first impressions: occasional body horror like SD3, otherwise solid — rionix88 · 2026-10-16
- XGRIDS builds world's largest 3DGS town: 23.5 km² and 6.2 billion Gaussian Splats — bilawalsidhu · 2026-10-16
- IMMERSION: AI film compilation links 12 shorts with one continuous camera move — AI_Andrew · 2026-10-16
- A song with vocals, lyrics and 3D head animation created entirely by Opus 5.5 — repligate · 2026-10-16
- Alibaba open-sources CommerceGen-Studio for commercial-grade e-commerce images — alibabagroup · 2026-10-16
- EVA-Cap: Fudan and OPPO align video captioning with atomic audiovisual events via GRPO — Fudan-University · 2026-10-16