Wan 2.7 — AI video generator
Alibaba Wan 2.7 image-to-video, from a single still
Wan 2.7 is Alibaba's image-to-video model: upload a still and describe the motion you want out of it. Like HappyHorse it requires an image, and it takes a negative prompt, which is the practical lever for keeping unwanted movement out of a shot.
What Wan 2.7 is good at
- Animates any uploaded still, with the prompt describing motion only
- Negative prompt support for suppressing unwanted movement
- 1080p delivery
- Seed control for reproducible results
What people use it for
- Turning a catalog photograph into a short looping clip
- Adding camera movement to flat artwork
- Reviving archive stills for social
Wan 2.7 specifications
- Duration
- 3–15s
- Resolution
- 720p, 1080p
- Audio
- Not supported
- Reference image
- Required
- Seed control
- Supported
- Negative prompt
- Supported
Plan limits apply on top of these — see pricing.
Example prompts for Wan 2.7
Written for this model in particular. Open one in the composer and edit it from there.
“Slow push in on the subject, background falling out of focus, everything else held still”
Try this prompt“Wind moving through the trees behind the subject while the subject stays motionless”
Try this prompt“The camera cranes up and back to reveal the wider room”
Try this promptWan 2.7 FAQ
- What is Wan 2.7?
- Wan 2.7 is an AI video model from Alibaba, available on Vixlens. Wan 2.7 is Alibaba's image-to-video model: upload a still and describe the motion you want out of it. Like HappyHorse it requires an image, and it takes a negative prompt, which is the practical lever for keeping unwanted movement out of a shot.
- How long can a Wan 2.7 clip be?
- Wan 2.7 generates clips of 3–15s.
- What resolution does Wan 2.7 output?
- Wan 2.7 outputs at 720p, 1080p on Vixlens.
- Does Wan 2.7 generate audio?
- No — Wan 2.7 generates picture only. Several other video models on Vixlens do generate native audio.
- How much does Wan 2.7 cost?
- Generating needs a plan — there is no free tier. Starter is $10/month for 1,000 credits (launch offer: $6/month for the first 20 Starter subscribers, locked in while they stay subscribed). Credits are spent per generation based on the model, resolution and duration, and the exact cost is shown before you generate.
Other video models on Vixlens
Seedance 2.5
Long-form AI video with reference control and native audio
ByteDanceSeedance 2.0
1080p AI video with multi-subject references and motion from a clip
ByteDanceSeedance 2.0 Mini
The cheapest way to test a video idea before committing credits
GoogleVeo 3.1
Google's flagship video model, with synchronized audio at up to 4K
GoogleVeo 3.1 Fast
Veo 3.1 quality at lower latency, for iterating on a shot
Black Forest LabsFlux 3 Video
Black Forest Labs' first video model, with a fast draft mode
Start generating with Wan 2.7
Every model on one credit balance — pick a plan and start creating.