# Coffee pour AI video prompt

> Copy this coffee pour ai video template. Find source guidance, a simpler variation and motion checks for your video model.

Source: https://windflow.online/prompts/product-coffee-pour · Updated 2026-10-11 · Windflow Labs

Focus on one physically legible action with a stationary camera.

## Copyable prompt

```text
A thin stream of hot coffee pours from a small kettle into a white ceramic cup on a wooden table. A locked close-up camera frames the cup and pouring stream. Light steam rises naturally; warm side light reveals the surface movement. The cup stays stable, the stream follows one path and the background remains softly out of focus.
```

This is an editable starting template. The model, reference input and serving profile determine the output; evaluate the generated result before using it in a product.

## Choose the input

A cup and kettle positioned so the pouring path is visible without obstructing the cup rim.

Plan product reveals, material close-ups and controlled camera moves. Use a reference image when exact shape or identity matters, and inspect logos and geometry in the result.

## A simpler variation

Begin with the filled cup and generate only a small steam movement for a simpler loop.

## What to inspect

Inspect liquid boundaries, cup geometry and whether the pour connects to the cup plausibly.

Record the input, supported control, model profile and the visible result. Change one variable at a time to learn which instruction affects your scene.

## Models and next steps

- [Helios API and specifications](https://windflow.online/models/helios)
- [LongLive-2.0 API and specifications](https://windflow.online/models/longlive-2)

Browse [ai product video prompts](https://windflow.online/prompts/product-video-prompts), or assemble your own with the [prompt generator](https://windflow.online/tools/ai-video-prompt-generator).

## FAQ

### Can I copy and edit this video prompt?

Yes. Copy the template, replace the subject and scene details, and adapt it to your model's supported input. Start with the simpler variation if the output becomes unstable.

### Does this template guarantee the described result?

No. It expresses the intended scene or edit. Inspect the model's output for identity, motion and continuity before publishing or integrating it.

### How should I evaluate a change to the prompt?

Keep the source input and serving profile constant, change one instruction, and compare the visible result over several runs. Measure responsiveness separately from output quality.