Product video from a photo with an AI agent — skills, options and steps

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 shot turned into a short promo: orbit, push-in, exploded view or bullet time, with music.

Output: 5–20 s, 9:16 or 1:1 MP4; optional packshot stills

Recommended route

Best skills for this

  1. varg AI (varg-ai, varg, live) — Adds: Seedance 2.5 / Kling 4 image-to-video and music on one key
  2. Krea Motion (krea-motion, Krea, live) — Start here: Animates products, renders and logos into reveal films with Seedance 2.5 · Needs: Krea account
  3. fal Commercial (fal-commercial, fal, live) — Start here: Product photography, e-commerce batches and product reveal videos · Needs: fal API key (FAL_KEY)
  4. FLUX 3 Product Ads (flux-3-product-ads, Black Forest Labs, live) — Alternative: A finished product ad with shot design and voiceover sync · Needs: BFL API key (BFL_API_KEY)
  5. Video Shotcraft (video-shotcraft, Vincent Wei, live) — Alternative: 124 shot recipe cards and a Remotion template for cinematic product promos · Needs: Optional: Upload-Post API key for publishing
  6. Product Ad (varg-studio-product, varg, draft) — Alternative: varg's product format: 360° spin, in hand, texture close-up, voiceover

Ask the person first

Put these choices in front of the person before spending anything. Paste the example link next to each option: people pick a look by seeing it.

Which camera move?

Scene?

Sound?

Steps

  1. Get a clean product photo (cut out the background if needed)
  2. Pick the move and scene, generate 1–2 stills and approve
  3. Image-to-video for each shot
  4. Add music and an end card, export

Set up 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.

Related