# Earth Zoom-Out — trending format for cinematic & short films

> **For AI agents:** find the right skill in one call — `curl -s "https://skills.varg.ai/api/search?q=<what the person wants>"` returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add `.md` to its path. Before generating anything, show the person the options on the use-case page.

One unbroken pull-back from a subject to orbit and beyond, often all the way back home again.

- **Slug:** `want-earth-zoom-out`
- **Status:** wanted
- **Publisher:** AI Video Explorer (community)
- **Source:** https://x.com/rand_shao/status/2113738231661609045
- **Cost:** ~120 credits / 10 s clip (estimate) — Kling v3 at 11.8 credits/s without audio (catalog of 2026-10-23); Seedance 2.5 at 720p runs 33–50 credits/s.

## What it does

A single unbroken camera pull-back: from a subject (a sea turtle on a reef, a person on a rooftop) up through the city, the planet and out into space, sometimes reversing all the way home. Higgsfield shipped it as a one-click "Earth Zoom Out" effect in June 2025, and an October 2026 post of the format reached 3.7M views. An agent takes one photo or a text subject, prompts a first frame with Nano Banana 2.1, then generates the pull-back with a strong video model (Seedance 2.5, Kling v3 or Veo 3.1), stitching two clips at a hidden cut when one generation cannot cover the whole range of scale.

## Status

A format people ask for that has no dedicated skill yet. Make it with the skills on the use-case pages below, or with varg directly.

Example: https://x.com/rand_shao/status/2113738231661609045

How an agent would make it: Subject photo or prompt → first frame (Nano Banana 2.1) → continuous pull-back prompt (subject → city → planet → space) on Seedance 2.5 / Kling v3 / Veo 3.1 → optional reverse or hidden-cut stitch

**Models it drives:** nano_banana_2_1, seedance_2_5, kling_v3, veo_3_1

## Example output

https://skills.varg.ai/previews/want-earth-zoom-out.mp4 — From the creator's YouTube cut linked in the post: the unbroken pull-back rises from a hurricane over the ocean through the curve of the Earth to the whole planet in space (48–56 s of 180 s; the post has no attached video) (credit: AI Video Explorer (@rand_shao), https://x.com/rand_shao/status/2113738231661609045)

## Used for

- [Trending AI video formats](https://skills.varg.ai/use-cases/trending-formats.md): What's going viral now — formats you can make for your brand today, with the skill for each.

## More cinematic & short films skills

- [Previz to Seedance](https://skills.varg.ai/skills/varg-previz.md): Plan multi-shot AI video before paying: story, anchor sheets, a three.js grey-box previz, then a Seedance v2v pack.
- [Higgsfield Generate](https://skills.varg.ai/skills/higgsfield-generate.md): Generate images, video, 3D and audio across 30+ models, plus ad videos and virality scoring, from one CLI.
- [fal Recipes](https://skills.varg.ai/skills/fal-recipes.md): Follow proven multi-step fal pipelines for commercials, product shots, characters, lip-sync and try-on.
- [fal Fan Cam](https://skills.varg.ai/skills/fal-fan-cam.md): Put someone into a live sports broadcast: a realistic fan-cam cutaway with scoreboard and channel overlays.
- [Gemini Omni Flash](https://skills.varg.ai/skills/gemini-omni-flash-api.md): Generate and edit video with Gemini Omni 1.1 Flash: text-to-video, first/last frames, extensions, edits.
- [Melies](https://skills.varg.ai/skills/melies.md): Generate images, video, movie posters and thumbnails from the terminal with 148 AI actors and style flags.

## 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.

- 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`
- 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