---
title: "WAN 3.0 Prompts: 6 Tested Examples | Made"
description: "Copy 6 tested WAN 3.0 prompts with the actual outputs they produced in Made, plus how to write your own: settings, strengths, and pitfalls."
url: https://www.made.app/models/wan-3-0/prompts
---

[Models](https://www.made.app/models) / [WAN 3.0](https://www.made.app/models/wan-3-0) / Prompts

# WAN 3.0 prompts that actually ran

Every prompt below was generated with WAN 3.0 in Made, and the output next to it is what came back — not a curated stock image. Copy a prompt as a starting point, then use the guide underneath to adapt it.

[Try WAN 3.0](https://www.made.app/models/wan-3-0) [WAN 3.0 pricing: from 0.5 credits / second](https://www.made.app/price-sheet/wan-3-0)

Original results

## WAN 3.0 prompts and their outputs

These examples use media produced for Made. Prompts are included when the production record allows them.

### Motion study

“A glassblower turns molten glass at the furnace mouth, heat shimmer rising, the camera arcing slowly from the flame to their focused face.”

### Image-to-video

“Animate the scene: the glass glows and turns, sparks drift, furnace roar fills the room, the camera holds a slow arc.”

### Creative scene

“Hot air balloons lift off over terraced fields at dawn, burners firing in turn, a slow aerial drift among the envelopes as mist burns off below.”

![Glassblowing workshop still used as a WAN 3.0 start frame](https://www.made.app/images/models/wan-3-0/still-01.jpg)

### Start-frame control

“Use this image as the opening composition.”

![Balloons over terraced fields, a WAN 3.0 scene brief](https://www.made.app/images/models/wan-3-0/still-02.jpg)

### Scene brief

“Set the scene as a still before describing its motion.”

![Terracotta rooftops in evening light, a composition brief for WAN 3.0](https://www.made.app/images/models/wan-3-0/still-03.jpg)

### Composition brief

“Plan the shot as a still, then hand the motion to the model.”

## How to write a WAN 3.0 prompt

1. **Choose text or image input**
   Write a prompt on its own, or add a start image — and optionally an end frame — to anchor the clip.
2. **Use the long-take ceiling**
   Durations run from 2 to 30 seconds; describe how the shot evolves over longer takes.
3. **Set the format**
   Pick a fixed aspect ratio, or adaptive to follow the input image’s shape.
4. **Review and refine**
   Check motion stability across the take, then adjust one instruction at a time.

## What WAN 3.0 responds well to

### Prompt for these jobs

- Long takes — up to 30 seconds in one pass
- 1080p output for about 30% less per second than Prime
- Start-to-end frame transitions
- An adaptive aspect ratio that follows the input image

### Check the output for

- Slower than WAN 3.0 Prime: a 5-second 720p clip took 143 seconds in our test, against 83 on Prime.
- Made starts at 480p, the cheapest tier; 720p and 1080p cost more per second.

Iteration is cheap here: WAN 3.0 costs from 0.5 credits / second, so rewriting a prompt and rerunning it is a normal part of the workflow, not a budget decision. See the [full WAN 3.0 pricing breakdown](https://www.made.app/price-sheet/wan-3-0).

Questions, answered

## WAN 3.0 prompts FAQ

Need a specific answer? [Contact support](mailto:support@made.app)

### What is WAN 3.0?

It is Alibaba’s WAN 3.0 video model at its standard speed and price, with the same inputs and 30-second ceiling as WAN 3.0 Prime.

### How does it differ from WAN 3.0 Prime?

Speed and price. Prime costs about 40% more per second and, in our test, finished 5-second clips 1.7x faster at 720p and 1.3x faster at 1080p. Standard is the better buy when nobody is waiting on the clip.

### Which resolution does Made use?

Made starts at 480p, the cheapest tier; you can pick 720p or 1080p at their own rates.

### How long can clips be?

From 2 to 30 seconds — one of the longest single-pass ranges in the library.

### Does it generate sound?

Yes, audio is on by default in the provider contract and included in the billed rate.

### When should I choose another model?

Choose WAN 3.0 Prime when turnaround matters, Happy Horse 1.1 for lip-synced dialogue, or Seedance 2.5 for flagship 30-second takes.

More tested prompts across all models live in the [prompt library](https://www.made.app/prompts), and the full WAN 3.0 capability rundown is on the [model page](https://www.made.app/models/wan-3-0).

---

Markdown version of https://www.made.app/models/wan-3-0/prompts. Every public Made page has one at its URL plus .md (https://www.made.app/models/wan-3-0/prompts.md). Site summary for AI assistants: https://www.made.app/llms.txt
