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
- HeyGen Details Avatar V Tech: Reading Full Video Preserves Micro-expressions — HeyGen · 2026-08-14
- MiniMax Music 3 Studio Workflow Goes Live on Hugging Face — _akhaliq · 2026-08-14
- Turning a Single Comic Sketch into a 24-Second Parkour Animation: Full Workflow and Prompts — BanghuaZ · 2026-08-14
- AI-Powered 3D Penguin Vibes to Any Song in Real-Time — realsohamparekh · 2026-08-14
- Testing MiniMax H3 Video Acceleration: Turbo vs. Sage Quality Loss — Full_Tomato_5627 · 2026-08-14
- Phosphene AI Launches Storyboard Feature for Video Generation — cocktailpeanut · 2026-08-14