It is Wan AI’s current-generation video model, generating clips at up to 1080p with synchronized audio from text or a start image.

Does WAN 2.7 generate sound?

Yes. Audio is synchronized with the picture — describe the sound you want alongside the scene and motion.

How long can clips be?

Any length from 2 to 15 seconds — including a 2-second floor that suits very short cutaways.

Which resolutions are available?

720p and 1080p. Made defaults to 1080p, the tier it bills at provider cost; switch to 720p for cheaper drafts.

Can I set the aspect ratio?

No — Made does not expose an aspect-ratio control for this model. For image-to-video, the output follows your start frame, which is the practical way to steer composition.

When should I choose another model?

Choose WAN 3.0 or WAN 3.0 Prime for longer takes and newer-generation fidelity, or WAN 2.2 5B when you want flat-priced silent drafts.

WAN 2.7 prompts that actually ran

Every prompt below was generated with WAN 2.7 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 2.7 WAN 2.7 pricing: $0.10 / second

Original results

WAN 2.7 prompts and their outputs

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

Motion study

“Cinematic clip: wild horses gallop through shallow tide water under a storm sky, spray freezing in backlight”

Image-to-video

“The brush completes a sweeping character in one take, ink bleeding into the paper fibers, macro camera”

Creative scene

“Cinematic clip: a ramen chef torches chashu in a dark counter bar, flames flaring, smoke curling into the spotlight”

Calligrapher touching brush to paper, a still used as a WAN 2.7 start frame

Start-frame control

“Use this image as the opening composition.”

Scene brief

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

Composition brief

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

How to write a WAN 2.7 prompt

1
Write the shot and its sound
Describe the subject, motion, camera path, and the audio the clip should carry — sound is generated with the picture.
2
Add a start image if needed
Upload a still to animate; WAN 2.7 keeps its composition, which is also how you control framing.
3
Choose length and resolution
Pick any duration from 2 to 15 seconds and 720p or 1080p.
4
Review and refine
Check motion, audio, and continuity, then adjust one instruction at a time.

What WAN 2.7 responds well to

Prompt for these jobs

1080p masters with synchronized audio, no upscale pass needed
Flexible durations — any length from 2 to 15 seconds
Very short cutaways at the 2-second floor
Animating a still image at full resolution

Check the output for

No aspect-ratio control in Made — output uses the provider default, so steer composition with a start image when framing matters.
Made defaults to the 1080p tier it bills at provider cost; per-second pricing means long clips add up — drop to 720p for drafts.
Clips top out at 15 seconds; longer continuous takes need Seedance 2.5 or WAN 3.0 Prime.

Iteration is cheap here: WAN 2.7 costs $0.10 / second at the provider's wholesale rate, so rewriting a prompt and rerunning it is a normal part of the workflow, not a budget decision. See the full WAN 2.7 pricing breakdown.

Questions, answered

WAN 2.7 prompts FAQ

Need a specific answer? Contact support

: It is Wan AI’s current-generation video model, generating clips at up to 1080p with synchronized audio from text or a start image.

More tested prompts across all models live in the prompt library, and the full WAN 2.7 capability rundown is on the model page.