---
title: "Open-Source Previs Studio for AI Video Camera Control — AI video prompts for camera & shots, with examples"
description: "Block the set, cast and camera in a browser greybox, then hand Seedance a first frame, reference clip and prompt per shot. Install in Claude Code, Codex and Grok with one command."
url: https://varg.ai/how-to/skills/cozyclay-previs
updated: 2026-10-31
---

# 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.

- **Type:** [Prompt](https://varg.ai/how-to/prompts.md) · [Camera & shots](https://varg.ai/how-to/browse/skills/camera.md)
- **Slug:** `cozyclay-previs`
- **Status:** live
- **Publisher:** NomaDamas (community)
- **Source:** https://github.com/NomaDamas/CozyClay
- **Works in:** Claude Code

## 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

- Lock blocking and camera before generating an AI video shot
- Get the same camera move on every Seedance take
- Draw dolly rails and cut a shot timeline for a scene
- Export a greybox reference clip, first and last frame and prompt
- Let Claude Code or Cursor stage a scene over MCP

## Install

- Claude Code: `npx cozyclay`
- Any MCP client: `npx -y cozyclay mcp`
- Any agent, with the vargai CLI: `vargai install cozyclay-previs`

## Example output

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

## More camera & shots skills

- [fal Cinematography](https://varg.ai/how-to/skills/fal-cinematography.md): Direct cinematic stills and video: shot language, camera moves, lenses, lighting, grade and film texture.
- [Storyboard Creation](https://varg.ai/how-to/skills/inference-sh-storyboard-creation.md): Storyboard a video before generating: shot types, angles, moves, the 180-degree rule, annotated panels.
- [Video Shotcraft](https://varg.ai/how-to/skills/video-shotcraft.md): 124 shot recipe cards and a tested Remotion template for cinematic product promos built from real UI screenshots.
- [Control AI Video Cuts and Camera With a Blender Greybox](https://varg.ai/how-to/skills/blender-greybox-ai-video-cuts.md): A Blender greybox clip drives Seedance 2.5's video reference: 7 shots, 6 hard cuts landing within 0.07 s of plan.
- [Playable 3D Previz for Seedance Reference Video in ComfyUI](https://varg.ai/how-to/skills/comfyui-scene-camera-action.md): ComfyUI nodes: build a 3D blockout set, act it with WASD, cut live cameras and export a 720p reference clip for Seedance or MiniMax H3.
- [Direct Eastern Xianxia Fantasy Video Shot by Shot](https://varg.ai/how-to/skills/xianxia-cinematic-video-director.md): Xianxia scene idea, keyframe or reference video to story spine, continuity locks, shot list and per-shot camera-move prompts.

## 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.

- Any agent with a terminal: `curl -fsSL https://varg.ai/install | sh` (Windows: `irm https://varg.ai/install.ps1 | iex`), then `vargai login` and every model is a command — `vargai generate_video …`, `vargai estimate_cost …` (https://varg.ai/how-to/cli/)
- Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg` (skill + hosted MCP)
- Codex, Cursor, Gemini CLI, OpenClaw: `npx skills add vargHQ/skills --skill varg-ai -a <agent> -y`
- Grok and any agent that reads SKILL.md: `npx skills add vargHQ/skills --skill varg-ai`, or point it at the skill's SKILL.md
- Claude.ai, ChatGPT, any MCP client: connect `https://mcp.varg.ai/mcp`
- API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt