Kling team's Coda-DaVinci reimagines video generation via Code2Video agents
KlingTeam · hf · 2026-11-20
KlingAI Research, with Nanjing University, PKU, HKUST(GZ), and Tsinghua, released Coda-DaVinci, a Code2Video framework: instead of directly generating pixels, a task-adaptive agentic pipeline builds 3D proxies, runs physics simulation, and coordinates multiple agents before rendering video.
- 3D proxies provide structural control while physics simulation improves plausibility, targeting structural controllability, physical realism, and visual quality jointly
- Homepage and open-source code are available alongside the paper
More from Multimodal
- Alibaba's TaoTex diffusion model generates native 3D materials, beating TRELLIS.2 — jiqizhixin · 2026-11-20
- AI turns Mediterranean illustration into interactive 3D world; Three.js wall-crash demo costs $6.98 — Saboo_Shubham_ · 2026-11-20
- Tencent's WeMM-Video pushes open-source omni-modal video understanding — tencent · 2026-11-20
- Kling's EgoCaptioner uses 50k samples and GRPO to master egocentric video captioning — KlingTeam · 2026-11-20
- WM^MLLM: Princeton and NVIDIA turn multimodal LLMs into editable world models — OpenEnvisionLab · 2026-11-20
- Open-source repo offers 500+ AI-generated low-poly 3D landmarks for maps under CC0 — tomjohndesign · 2026-11-20