NodeTool Cloud is in alpha — run workflows in the browser, on your own keys.NodeTool Cloud is in alpha. Try it →
Product Video Generator
Pitch a campaign brief and one product photo, and the agent returns a cinematic 16:9 spot on an editable timeline. No agency, no export hops, one canvas you re-run for every new product.
How it works
Four nodes do the work. Inputs become a prompt, the prompt becomes a shot, the shot becomes a video.
01Feed in the campaign
Three text inputs hold the brief, the target audience, and the key features. A product photo goes in alongside them as the hero shot.
Aurora Trail smart fitness watch · active millennials who hike · GPS, heart-rate, adaptive coaching, water resistance
02Assemble the prompt
A Prompt node templates those inputs into a precise, rule-based request: one camera move, one subject action, lighting, color anchors, and hard constraints.
No on-screen text, no logos, no watermarks, no distorted anatomy
03Direct the shot
An agent turns the request into a concrete, cinematic prompt with framing, lens, and motion cues, the part most people get wrong by hand.
Gemini 3.1 Pro · 50mm macro push over the watch on a wet river rock at dawn
04Render the video
A text-to-video model animates the product photo from the agent's prompt into a finished, ready-to-post clip.
Veo 3.1 · 16:9 · 720p · 8 seconds · rendered in ~44s
One photo in, a product clip out
The whole pipeline runs from a single product render. Same graph, any product.
Direct it yourself
Nothing here is locked. Swap models, shift the tone, re-roll a shot, or point the whole thing at a different product.
Swap the video model
Veo, Seedance, Kling, Runway. Change one node, the rest of the graph stays exactly the same.
Retune the agent
Rewrite the system prompt for a luxury, playful, or hyper-technical tone without touching the pipeline.
Change the format
Aspect ratio, resolution, and duration all live on the video node. Go vertical for social in one click.
Reuse for any product
Drop in a new photo and brief, run it again. The workflow is the reusable part, not the output.
Models in this workflow
Called with your own keys. The bill comes from the provider, not from us — no token markups — and you can switch any of them for a better model the day it ships.
Frequently asked questions
- How do you make a product video from a single photo?
- Give the workflow a brief, an audience, the key features, and one product photo. A Prompt node turns them into a rule-based request, an agent writes the cinematic shot direction, and a video model animates the photo into a finished 16:9 clip.
- Which models does this workflow use?
- Gemini 3.1 Pro Preview writes the video prompt and Veo 3.1 Preview renders the clip from the product photo. Both are called with your own keys at provider prices.
- How long is the finished clip?
- The shipped setup renders an 8-second 16:9 clip at 720p, which took about 44 seconds in the run shown on this page. Change the video node and you change the length, resolution, and model.
- Can I run it for a whole product line?
- Yes. The workflow is the reusable part: swap the photo and the brief and run it again for the next product, with the same prompt rules and the same look.
Build your product video
Download the open-source studio for macOS, Windows, and Linux, open this workflow, and ship your first spot today.