Turn product photos into AI video that keeps the logo and shape — 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.

Stops logos, labels and shapes from warping in AI product video: lock sheet, multi-angle references, camera-risk ladder, drift check.

What it does

AI video models redraw the product in every frame, so long, soft or printed products drift: wedges turn into blocks and labels melt. This skill writes a lock sheet (fixed geometry, fixed surface, allowed motion), builds a 2-4 angle reference pack with one role per image for Seedance 2.5 or Kling 4, climbs a camera-risk ladder (locked → push-in → slide → small orbit), checks every clip against the lock sheet with varg video_analyze and reruns only the failed shot, then composites the real packshot back where text must be exact. Tested on a car seat gap filler that turned boxy from one photo: with a side-profile reference and the lock block it kept its shape (231 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, kling_v4, nano_banana_2_1

Example output

https://s3.varg.ai/files/194b94d0-58ff-4e8b-91de-4f1959d04013/file_332df2a110a0.mp4 — example (credit: varg)

More product videos skills