Exploded-View Product Reveal — trending format for product videos

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.

A product or dish floats apart into labeled layers, then snaps back together: a 3D-ad look from one photo.

What it does

A product (or a taco) separates into its parts along a clean axis, labeled with thin leader lines and weights, then magnetically reassembles: the kind of shot that used to need a CAD model and a 3D artist. The recipe is to generate an exploded-view still and an assembled still with matching light, animate between them with first/last-frame video, and reverse it. An agent asks for one product photo, writes the parts list, renders both keyframes with Nano Banana 2.1, interpolates with Kling v3 or Veo 3.1, and adds the labels in HTML so the text stays sharp.

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/Strength04_X/status/2006031630268522943

How an agent would make it: Product photo → parts list → exploded keyframe + assembled keyframe with matching light (Nano Banana 2.1) → first/last-frame interpolation (Kling v3 / Veo 3.1) → reverse → HTML labels

Models it drives: nano_banana_2_1, kling_v3, veo_3_1

Example output

https://skills.varg.ai/previews/want-exploded-view-reveal.mp4 — A floating taco separates into five ingredients stacked top to bottom with thin leader lines and gram labels, then reassembles (0.8–8.8 s of 8.8 s; Nano Banana Pro + Kling) (credit: M-studioAi (@Strength04_X), https://x.com/Strength04_X/status/2006031630268522943)

Used for

More product videos 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.