# Hermoso: Wan 3.0 on Hermoso: 3–30s, 1080p/720p/480p, native sound

> Machine-readable twin of https://hermoso.ai/models/wan-3-0/. Generated from the shipped page. Do not edit by hand.
> Full agent guide: https://hermoso.ai/llms.txt · MCP: https://app.hermoso.ai/mcp

[Models](https://hermoso.ai/models/) › [Video models](https://hermoso.ai/models/video/)

# Wan 3.0

Alibaba’s Wan 3.0: up to 30s in one take with sound, 1080p, up to 10 reference images, for less than Prime

Alibaba · video model

[Try Wan 3.0 →](https://app.hermoso.ai/tools/model/wan-3?src=site-model-wan-3-0)

**3–30s** clip length

**1080p** best resolution of 3

**Native sound** speech and world audio in the render

**up to 10** reference images

Wan 3.0 is one of 38 video models Hermoso can render a video ad, product sizzle or UGC clip with. Name it, or leave the model out and the router picks a sound default. The same catalog is available from the app, the [API](https://hermoso.ai/docs/api/), the [MCP server](https://hermoso.ai/mcp/) and the CLI, on one account and one credit balance; the exact price of every render is shown in the app before it runs.

## What people make with it

- [UGC testimonials and talking creators](https://hermoso.ai/recipes/testimonial-video/)
- [Product sizzles and packshot spins](https://hermoso.ai/recipes/orbit-360/)
- [Cinematic brand films](https://hermoso.ai/recipes/cinematic/)
- [Faceless product demos and explainers](https://hermoso.ai/recipes/explainer/)

The linked formats are [creative recipes](https://hermoso.ai/recipes/) Hermoso plans and renders for your brand.

## Use cases

- [Wan 3.0 for TikTok ads](https://hermoso.ai/models/wan-3-0/tiktok-ads/)
- [Wan 3.0 for product videos](https://hermoso.ai/models/wan-3-0/product-videos/)
- [Wan 3.0 for UGC ads](https://hermoso.ai/models/wan-3-0/ugc-ads/)

## About Alibaba

Alibaba makes the Wan video models and the Qwen family, open-weight and quick to improve.

## Made with Wan 3.0

Real renders from the Hermoso Studio, shown exactly as they came out, with no edits.

Wan 3.0 sample: a woman tastes cold brew in her kitchen and says it is really good, 5 seconds with sound

## Specs

Lengths 3s 4s 5s 6s 8s 10s 12s 15s 20s 30s

Longest single take 30s in one unbroken shot

Resolutions 1080p 720p 480p

Aspect ratios 9:16 16:9 1:1 4:3 3:4

Sound Native audio (can be switched off per render)

Modes text to video, image to video, reference to video

Reference images up to 10 per render in Hermoso (our fidelity cap, measured on paid renders; the model itself accepts more), addressed in the prompt as @Image1, @Image2…

Reference videos up to 5

Reference audio up to 5

Edit an existing video No

Model id `wan-3`

## Where it fits

Each aspect ratio Wan 3.0 renders maps to a placement:

- **9:16** for Reels, TikTok, Shorts and Stories
- **16:9** for YouTube, in-stream and display
- **1:1** for Feed posts and carousels
- **4:3** for Presentations and display
- **3:4** for Pinterest and tablet feed

## Wan 3.0 compared with other video models

Model Lengths Top resolution Sound Refs

**Wan 3.0** 3–30s 1080p Native up to 10

[HappyHorse 1.1](https://hermoso.ai/models/happyhorse-1-1/) 5–15s 1080p Native up to 1

[Wan 3.0 Prime](https://hermoso.ai/models/wan-3-0-prime/) 3–30s 1080p Native up to 10

[FLUX.3 Video](https://hermoso.ai/models/flux-3-video/) 5–20s 720p Native up to 1

[MiniMax H3 Max](https://hermoso.ai/models/minimax-h3-max/) 5–15s 1080p Native up to 1

[FLUX.3 Max Video](https://hermoso.ai/models/flux-3-max-video/) 5–20s 1080p Native up to 1

[HeyGen Video](https://hermoso.ai/models/heygen-video/) 5–15s 1080p Native up to 1

See [all 38 video models](https://hermoso.ai/models/video/) side by side.

## Just ask for it

In Claude, ChatGPT, Cursor or any assistant connected to Hermoso, name the model in plain English. Or pick it from the model menu in the app.

Make a 15 second UGC ad for our olive oil with Wan 3.0, kitchen at golden hour, 9:16.

Render the packshot spin on Wan 3.0 and post it to TikTok and Reels.

Redo yesterday's ad on Wan 3.0 with the new label.

## Getting the best out of Wan 3.0

- Describe one continuous camera move and where it ends. The model renders motion, not a shot list.
- Attach the real product photo as a reference and ask for it matched exactly. Never describe a lookalike.
- Name colours in words. A hex code turns into text on screen.
- Keep spoken lines short. Roughly two words per second is what a clip can carry cleanly.
- Ask for the placement's ratio up front (9:16 for Reels and TikTok) instead of cropping afterwards.

Make a video ad with Wan 3.0. Start free with the full studio and up to 5 posts a month.

[Try Wan 3.0 →](https://app.hermoso.ai/tools/model/wan-3?src=site-model-wan-3-0)

[See pricing](https://hermoso.ai/pricing)

## Frequently asked questions

### How long a video can Wan 3.0 make?

Wan 3.0 renders clips from 3 to 30 seconds, and up to 30 seconds in one unbroken take. Longer spots are built from several clips.

### Does Wan 3.0 make sound?

Yes. Wan 3.0 renders native audio with the picture, so a talking creator or a voiceover is part of the same take.

### Can Wan 3.0 use my product photos?

Yes. Attach up to 10 reference images of the product and Hermoso keeps the real product in the render.

### How much does Wan 3.0 cost?

The exact credit price is shown in the app before every render and settled at cost. See pricing for what a credit is worth.

## Related video models

Other Alibaba models first, then the video models listed nearest to Wan 3.0 in the catalog.

[HappyHorse 1.1 #1 on Video Arena · native audio + multilingual lip-sync · up to 15s 5–15s · 720p / 1080p · native sound](https://hermoso.ai/models/happyhorse-1-1/)[Wan 3.0 Prime Alibaba’s newest: 1080p, up to 30s in one take, sound, up to 10 reference images 3–30s · 1080p / 720p / 480p · native sound](https://hermoso.ai/models/wan-3-0-prime/)[FLUX.3 Video From a prompt or a starting image, 5 to 20 seconds, with sound 5–20s · 720p · native sound](https://hermoso.ai/models/flux-3-video/)[MiniMax H3 Max Tuned H3: follows prompts more closely and looks better; up to 768p and 15s; can go from a first to a last frame 5–15s · 720p / 480p / 1080p · native sound](https://hermoso.ai/models/minimax-h3-max/)[FLUX.3 Max Video Fast, low-cost video for drafts and quick clips. Sound, up to 1080p, 5 to 20 seconds 5–20s · 720p / 1080p · native sound](https://hermoso.ai/models/flux-3-max-video/)[HeyGen Video Very low cost per second, holds a face from a photo, sound included 5–15s · 720p / 480p / 1080p · native sound](https://hermoso.ai/models/heygen-video/)[Grok Imagine 1.5 From a prompt or a starting image, with sound and lip-sync 6–15s · 720p / 480p / 1080p · native sound](https://hermoso.ai/models/grok-imagine-1-5/)[MiniMax H3 MiniMax’s best: synced sound, 7 shapes, up to 15s, very cheap per second 5–15s · 1080p / 720p / 480p · native sound](https://hermoso.ai/models/minimax-h3/)

See [all 38 video models](https://hermoso.ai/models/video/) or [every model Hermoso offers](https://hermoso.ai/models/).
