Wan 2.7 AI Video Generator

Use Wan 2.7 for text-to-video or reference-to-video creation. Start with a prompt, or add a first frame and up to five reference images or videos to guide subjects, motion, and style; pair voice clips with referenced subjects when needed.

Try It

Create AI Videos with Wan 2.7

Set your parameters and start generating AI videos with the workflows and inputs currently supported on this page, including text, images, video clips, or audio where supported.

+

Describe the video you want to generate...

Wan 2.7Custom

Visual media illustrates the creative workflows described on this page and is not a benchmark or a guarantee of model-specific output.

What's New

What's New in Wan 2.7

Create AI video from text or direct subjects, motion, and voice with references. Wan 2.7 brings 720p/1080p output, five aspect ratios, and flexible short-form durations to Vofy.

Wan 2.7 Text-to-Video Workflow

Wan 2.7 Text-to-Video and Reference-to-Video

Use text-to-video when you want Wan 2.7 to interpret a complete scene description. Choose reference-to-video when you need to guide a subject, opening composition, motion cue, or visual style with uploaded assets.

Wan 2.7 Reference-to-Video Workflow

Guide Subjects and Voices With Up to Five References

Add up to five total reference images or videos to guide subject appearance, movement, and scene direction. You can also anchor the opening composition with a first frame and pair optional voice clips with referenced subjects for voice consistency.

Wan 2.7 1080p Short-Form Video Output

Generate 720p or 1080p Video Up to 15 Seconds

Choose 16:9, 9:16, 1:1, 4:3, or 3:4 output. Text-to-video and image-reference workflows support 2-to-15-second clips, while workflows that include a reference video support 2 to 10 seconds.

Videos Generated with Wan 2.7

See how Wan 2.7 fits cinematic text-to-video, reference-to-video character scenes, product marketing, and vertical social content.

Wan 2.7 - Cinematic Text-to-Video Scene

Getting Started

How to Create AI Videos with Wan 2.7

1

Choose a Creation Mode

Begin with text-to-video for an open-ended concept or reference-to-video when you need tighter control over subjects, motion, or visual direction.

2

Describe and Direct the Scene

Write the action, camera movement, setting, style, and pacing. For reference-to-video, add image or video references, an optional first frame, and any voice clips that should be paired with referenced subjects.

3

Set the Delivery Format

Choose the aspect ratio, resolution, and duration for the destination, then generate and refine the prompt or references as needed.

Specifications

Wan 2.7 Technical Specs

Creation ModesText-to-video and reference-to-video
Reference InputsFirst frame, up to 5 total reference images or videos, and paired voice clips
Resolution720p or 1080p
Duration2 to 15 seconds; up to 10 seconds with a reference video
Aspect Ratios16:9, 9:16, 1:1, 4:3, and 3:4

Use Cases

What You Can Create with Wan 2.7

From social content to professional workflows, see how creators and teams are using AI video generation across industries.

Cinematic Text-to-Video Concepts

Turn a written scene into a short cinematic draft for story development, pitch films, mood exploration, and previsualization before production.

Reference-to-Video Character Scenes

Combine a prompt with visual references to guide character appearance, movement, and scene direction, then pair voice clips with referenced subjects when voice consistency matters.

AI Product Videos for Marketing

Create product reveals, lifestyle scenes, campaign drafts, and ecommerce motion concepts in landscape, square, or vertical formats.

Short-Form Social Content

Generate short clips for social ads, creator content, music visuals, event promos, and rapid A/B testing across landscape, square, and vertical formats.

Frequently Asked Questions

Everything you need to know about Wan 2.7.

What is Wan 2.7?
Wan 2.7 is Alibaba's AI video model for text-to-video and reference-to-video creation. In Vofy, it supports prompt-only generation and reference workflows guided by images, videos, a first frame, and paired voice clips.
Can Wan 2.7 generate video from text alone?
Yes. Choose text-to-video, write the scene and motion you want, and select the output format without adding a reference asset.
Does Wan 2.7 support reference-to-video generation?
Yes. In Vofy, Wan 2.7 can use up to five total reference images or videos alongside a prompt. You can also add a first frame and pair optional voice clips with referenced subjects.
How long can Wan 2.7 videos be?
Text-to-video and image-reference workflows support 2-to-15-second clips. If you include a reference video, the available duration is 2 to 10 seconds. Output is available at 720p or 1080p in 16:9, 9:16, 1:1, 4:3, or 3:4.
Can Wan 2.7 use voice references?
Yes. In Vofy's reference-to-video workflow, an optional voice clip can be paired with a reference image or video. Voice references are tied to referenced subjects rather than used as a standalone general audio or rhythm input.

Visual media illustrates the creative workflows described on this page and is not a benchmark or a guarantee of model-specific output.