Open-Source Previs Studio for AI Video Camera Control — prompt skill for camera & shots

For AI agents: find the right skill in one call — curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>" returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the how-to page. From a terminal: curl -fsSL https://varg.ai/install | sh installs the vargai CLI (https://varg.ai/how-to/cli.md): vargai search and vargai install <slug> with no key, every varg model after vargai login.

Block the set, cast and camera in a browser greybox, then hand Seedance a first frame, reference clip and prompt per shot.

What it does

CozyClay is browser previs: build the set from primitives, add rigged characters, describe the action so an agent writes a motion spec that a deterministic compiler bakes and QA-checks, then put shots on a timeline with dolly rails and a lens view. Each shot exports a keyframe pack (first and last frame, greybox clip, camera, prompt), mp4, depth and normal passes, a contact sheet and an OTIO cut list for the video model. It runs with npx cozyclay on Node 22.19+, no GPU, and an agent can drive it from the in-app panel, the MCP server or the cclay live CLI. Licensed AGPL-3.0.

Use when

Install

Example output

https://github.com/NomaDamas/CozyClay/raw/main/public/media/cozyclay-seedance-vs-greybox.mp4 — example (credit: NomaDamas)

More camera & shots skills

Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.