Turn product photos into an AI ASMR unboxing video — guide skill for product videos

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.

Hands-only ASMR unboxing from a box and a product photo: timed VISUAL / ACTION / SOUND blocks on Seedance 2.5 with native sound, no music.

What it does

Two photos in (the closed packaging and the product), a 5-15 s hands-only unboxing out: taps on the lid, the lid lifting off, the product lifted from its tray and switched on, with native ASMR sound and no music. The prompt is written in timed VISUAL / ACTION / SOUND blocks with the box and the product as Seedance 2.5 references (@image1, @image2); the skill makes a box image from the product photo when there is none. Unboxing has the highest winner rate of any Meta ad format in Motion's 2026 benchmark (9.8%) while only 2.1% of ads use it. Tested: 10 s at 720p with audio, 385 credits.

Example repo for ecommerce agents: https://github.com/vargHQ/ecommerce-ai-video-skills

Use when

Not for

Install

Models it drives: seedance_2_5, nano_banana_2_1

Example output

https://s3.varg.ai/files/194b94d0-58ff-4e8b-91de-4f1959d04013/file_942e9a6efa1c.mp4 — example (credit: varg)

More product videos skills