AlibabaWan 3.0 Prime Prompt Guide
How to write Wan 3.0 Prime prompts: a structure that works, 4 example prompts for text to video, image to video and reference to video, the settings that change the result and how to reference your own media. Copy any prompt into the Studio to try it.
- Example prompts
- 4
- 3 tasks
- Resolution
- 1080p
- 480p · 720p · 1080p
- Clip length
- 2–30 s
- audio included
- Per try from
- $0.0566/s
- 480p
Structure
A Wan 3.0 Prime prompt, piece by piece
Write in this order and keep each part concrete. Physical detail works better than mood words.
01
Subject
Who or what is on screen, with the details that must stay consistent: age, clothing, materials, colours.
02
Action
One clear action in the present tense. For clips up to 30 s, describe a short sequence of beats.
03
Camera
Shot size and movement: close-up, wide, dolly-in, orbit, handheld, drone.
04
Scene and light
Location, time of day, and where the light comes from.
05
Style
Lens, film look, colour grade or animation style.
06
Sound
Wan 3.0 Prime generates synchronized audio with the clip, so name the ambience, effects or lines of dialogue you want.
07
References
Say what each reference controls, e.g. @Image1, @Video1, @Audio1: “@Image1 is the main character”.
Examples
Wan 3.0 Prime prompt examples
Prompts written for this model, grouped by task. Open one in the Studio, then change one part at a time.
- Text to Video16:9
Luxury watch macro: the second hand sweeps as light glides across sapphire glass
Try in Studio - Text to Video
A street-food vendor in Bangkok flips noodles in a flaming wok, night market bokeh, handheld
Try in Studio - Image to Video
Gentle wind moves the curtains; the camera slowly pulls back to reveal the room
Try in Studio - Reference to Video
The woman in @Image1 walks through the café from @Image2 and orders a coffee, moving like @Video1
Try in Studio
By task
Prompting each Wan 3.0 Prime task
Text to Video
Everything comes from the text, so describe subject, action and camera explicitly. Put the most important element first.
Image to Video
The image is the first frame: describe what moves and how the camera moves, not what the picture already shows.
Reference to Video
Attach references and mention them in the prompt by name, saying what each one should control — character, product, style or camera move.
Referencing your own media
| Input | In the prompt | Limits and rules |
|---|---|---|
| Reference images Reference to Video · up to 4 | @Image1, @Image2… | Up to 4 images for characters, products, style or scene. Refer to them in the prompt as @Image1, @Image2… |
| Reference videos Reference to Video · up to 5 | @Video1, @Video2… | Up to 5 MP4/MOV clips for motion, camera moves or effects (1–15 s each, 15 s in total, ≤ 100 MB each). Refer to them as @Video1, @Video2… Reference-video seconds are billed like output seconds; reference + output must be 30 s or less. |
| Reference audio Reference to Video · up to 5 | @Audio1, @Audio2… | Up to 5 MP3/WAV clips for voice, music or sound (1–15 s each, 15 s in total, ≤ 15 MB each). Refer to them as @Audio1, @Audio2… |
Settings
Settings that change the result
Set these next to the prompt — in the Studio or as API parameters.
| Setting | Options | Effect |
|---|---|---|
| Aspect ratio aspect_ratio | 16:9 · 9:16 · 1:1 · 4:3 · 3:4 default 16:9 | Output frame shape. |
| Resolution resolution | 480p · 720p · 1080p default 720p | Output resolution. Higher resolutions cost more per second. Price: 480p $0.0566/s · 720p $0.1132/s · 1080p $0.2263/s |
| Duration duration | 2–30s default 5 | Length of the generated clip in seconds (2–30s). You pay per second. |
| Generate audio generate_audio | on / off default true | Generate synchronized sound, ambience and dialogue. No extra cost. |
| Negative prompt negative_prompt | — | Things to avoid in the output. |
| Seed seed | — | Use the same seed and settings to reproduce a result. Leave empty for random. |
FAQ