720p & 1080p · Text to Video · Image to Video · Reference to Video · Video Edit

Wan 2.7 AI Video Generator

Create 720p or 1080p AI videos from text, images, and references, or edit existing footage with natural-language instructions.

To compare this generation with the newest release, explore the Wan 3.0 AI video generator.

Generate with Wan 2.7 See Wan 2.7 Examples ↓

Driving audio (Optional) · Up to 5 · 15 sec total · 15 MB each

0/5 · 0s/15s

Click to upload audioUp to 5 · 15 sec total · 15 MB each · 5 remaining

Prompt*

0/20,000

Output settings

Per-second pricing varies by model

Resolution*

Default 720P

Aspect ratio*

Duration*

2–15 sec

Mode guide

Choose the Right Wan 2.7 Mode

Not sure which mode to use? Start with what you already have.

Your Goal	Use This Mode	Input	Output Limit
Turn an idea into a video	Text to Video	Prompt / supported audio workflow	2–15s
Animate a product or character image	Image to Video	Image + prompt	2–15s
Guide identity, motion, or style	Reference to Video	References + prompt	2–10s
Change existing footage	Video Edit	Video + instruction	2–10s
Control how a clip begins and ends	First + Last Frame I2V	Start frame + end frame + prompt	Within I2V limits

Turn an idea into a video

Text to Video

Input: Prompt / supported audio workflow
Output limit: 2–15s

Animate a product or character image

Image to Video

Input: Image + prompt
Output limit: 2–15s

Guide identity, motion, or style

Reference to Video

Input: References + prompt
Output limit: 2–10s

Change existing footage

Video Edit

Input: Video + instruction
Output limit: 2–10s

Control how a clip begins and ends

First + Last Frame I2V

Input: Start frame + end frame + prompt
Output limit: Within I2V limits

Overview

What Is Wan 2.7?

Wan 2.7 is an AI video model for creating and editing short videos from text, images, references, and existing footage. It supports 720p and 1080p output, with duration limits that depend on the generation mode.

You can use Wan 2.7 for text-to-video ideas, image animation, character-led reference workflows, first- and last-frame control, video continuation, and instruction-based editing.

It is designed for creators, marketers, e-commerce teams, designers, and other users who need short-form visual content without building a traditional production pipeline for every variation.

If your workflow is built around an earlier model, review Wan 2.6 before moving to Wan 2.7.

Video Examples

See What Wan 2.7 Can Actually Create

Explore four video examples created with Wan 2.7.

“A woman walks through a narrow Tokyo side street after rain, subtle handheld camera movement, warm shop lights reflecting on wet pavement, natural walking motion.”

“A premium wireless speaker rotates slowly on a matte studio table as soft directional light moves across the surface. Slow camera push-in, clean commercial framing.”

“A cyclist rides along a coastal road at sunrise. Side tracking shot, gentle ocean haze, long shadows, natural wheel movement, realistic road texture.”

“Two characters talk inside a quiet diner booth. Keep each character visually distinct, use restrained facial movement, stable medium shots, and warm evening lighting.”

Create Your Wan 2.7 Video

Capabilities

What Changed in Wan 2.7?

Wan 2.7 expands beyond a single generation upgrade. It improves video quality, motion, stylization, audio workflows, and subject consistency while adding more ways to control or edit a result.

Better Visual, Motion, and Subject Consistency

Wan 2.7 improves visual detail, motion smoothness, physical plausibility, and continuity across a clip. This is particularly useful with people, moving subjects, camera changes, or transitions where visual drift is easy to notice.

First- and Last-Frame Control

Define how a video begins and ends instead of giving the model only one starting image. This gives image-to-video workflows more direction for a planned transition, camera move, or visual endpoint.

9-Grid Image-to-Video

Wan 2.7 can use structured 3x3 image input in supported workflows to provide richer visual context for composition and scene direction when one reference image is not enough.

Subject and Voice References

Reference-based workflows can guide subject appearance and voice direction while additional video references help establish motion and scene style for recurring characters and repeatable concepts.

Instruction-Based Video Editing

Modify existing footage with natural-language instructions that describe a change to the background, lighting, styling, subject details, or other scene elements.

Video Recreation

Use an existing clip as structural guidance while changing the subject, visual treatment, or context for campaign variations, creative adaptations, and iterative production.

Try Wan 2.7

Workflows

Built for Real Video Workflows

Content Creators

Turn ideas, photos, or character references into short-form videos for TikTok, Instagram, YouTube, personal vlogs, music visuals, narrative clips, and creator-led campaigns. Use image-to-video for a strong visual and reference workflows when recurring identity matters.

Marketing & Ad Teams

Create campaign concepts, product reveals, social ads, promotional clips, branded characters, and creative variations without reshooting every idea. Use instruction-based editing to test settings, lighting, styles, or campaign versions.

E-Commerce & Brands

Animate product photography for product demos, launch teasers, lifestyle concepts, landing-page visuals, Shopify campaigns, and social ads. Describe product movement, camera angle, scene, lighting, and brand mood.

Enterprise & Industry

Use short AI-generated video for visual concepts, presentations, internal communication, training materials, process demonstrations, product visualization, or early-stage creative planning.

Model comparison

Wan 2.7 vs Wan 3.0

Wan 2.7 is not the newest Wan model. Wan 3.0 is a newer generation and supports longer single-generation video workflows.

Capability	Wan 2.7	Wan 3.0
Model generation	Previous generation	Newer generation
Core workflows	Text, image, reference, edit	Broader omni-generation workflows
Maximum duration	Up to 15s depending on mode	Up to 30s
Video editing	Supported	Supported
Reason to use	Established 2.7 generation, reference, and editing workflows	Longer and newer-generation workflows

Model generation

Wan 2.7: Previous generation
Wan 3.0: Newer generation

Core workflows

Wan 2.7: Text, image, reference, edit
Wan 3.0: Broader omni-generation workflows

Maximum duration

Wan 2.7: Up to 15s depending on mode
Wan 3.0: Up to 30s

Video editing

Wan 2.7: Supported
Wan 3.0: Supported

Reason to use

Wan 2.7: Established 2.7 generation, reference, and editing workflows
Wan 3.0: Longer and newer-generation workflows

If your current task fits Wan 2.7's generation and editing modes, continue using it here. If you need longer videos or want to evaluate the newer Wan generation, compare the two models first.

Compare Wan 3.0 and Wan 2.7 →

Looking for the latest generation? Explore the Wan 3.0 AI video generator for newer reference, editing, consistency, and audio-visual workflows. You can also compare Wan 2.7 with Wan 2.6 before choosing a model.

Quick start

How to Use Wan 2.7

Choose a Mode

Choose Text to Video for an idea, Image to Video for a photo or design, Reference to Video when identity or motion guidance matters, or Video Edit for existing footage.

Add Your Prompt or Media

Write a focused prompt and upload any required image, video, or reference media. Describe what should happen instead of relying only on visual adjectives.

Choose Resolution and Duration

Select 720p or 1080p. Text-to-video and image-to-video support 2–15 seconds; reference-to-video and video editing support 2–10 seconds.

Generate and Refine

Generate your clip, review motion and subject consistency, then adjust the prompt or references. Change one major variable at a time so you can see what improved.

Generate with Wan 2.7

Prompt guide

Wan 2.7 Prompt Recipes

You do not need a long prompt. Give the model clear information about the subject, action, environment, camera, lighting, and sound.

Cinematic Prompt

Template: Subject + action + location + camera movement + lighting + atmosphere + audio direction

“A lone traveler crosses a desert ridge at sunrise, slow tracking shot from behind, long shadows, light wind moving the clothing, quiet atmospheric ambience.”

Product Prompt

Template: Product + setting + product movement + camera movement + lighting + brand mood

“A black smartwatch rests on dark stone as the camera makes a slow half-circle around it, soft edge lighting, minimal premium commercial mood.”

Reference Prompt

Template: Reference subject + action + environment + camera + consistency instruction

“Keep the reference subject's appearance consistent while they walk through a bright modern gallery. Medium tracking shot, restrained body movement, soft daylight.”

Video Edit Instruction

Template: Change + preserve + visual target

“Change the outdoor background to an autumn park. Preserve the person, pose, camera movement, and timing of the original clip.”

For prompt formulas designed for the latest model, use the Wan 3.0 prompt guide.

Simple Pricing

Wan 2.7 Pricing

Choose a generation mode, duration, and resolution based on your project. Review the displayed credit cost and current terms before generating.

Starter

$9.9

100 credits · $0.099/credit

A lightweight one-time credit pack for trying the video generator.

Credit-based video generation
Credit cost shown before generation
One-time credit pack

Pro

$29.9

330 credits · $0.091/credit

A one-time credit pack with a lower per-credit price than Starter.

Credit-based video generation
Credit cost shown before generation
One-time credit pack

Scale

$49.9

600 credits · $0.083/credit

A larger one-time credit pack with a lower per-credit price.

Credit-based video generation
Credit cost shown before generation
One-time credit pack

Max

$99.9

1,250 credits · $0.080/credit

The largest one-time credit pack with the lowest listed per-credit price.

Credit-based video generation
Credit cost shown before generation
One-time credit pack

One-time credit packs. Any applicable taxes and credit-validity terms are shown at checkout or in the current service terms.

7-Day Refund

Stripe Checkout

Email Support

One-time purchaseCredit-based generationCurrent workflow accessEmail support

Compare current credit packs on the Wan 3.0 pricing page before starting a longer or higher-resolution job.

FAQ

Frequently Asked Questions

What is Wan 2.7?

Wan 2.7 is an AI video model for text-to-video, image-to-video, reference-based generation, and instruction-based video editing. It supports short-form 720p and 1080p video workflows.

How long can Wan 2.7 videos be?

The limit depends on the mode. Text-to-video and image-to-video support 2 to 15 seconds, while reference-to-video and video editing support 2 to 10 seconds.

Does Wan 2.7 support 1080p video?

Yes. Wan 2.7 supports both 720p and 1080p output across the video workflows covered on this page.

Can Wan 2.7 turn an image into a video?

Yes. Wan 2.7 supports image-to-video generation, including first-frame workflows and first- plus last-frame control for supported generation setups.

Can Wan 2.7 use reference videos?

Yes. Wan 2.7 supports reference-based video generation and can use multiple video references in supported workflows to guide subjects, motion, or scene direction.

Can Wan 2.7 edit an existing video?

Yes. Wan 2.7 supports instruction-based video editing. You can describe changes to elements such as background, lighting, styling, or scene details while working from existing footage.

How are Wan 2.7 credits calculated?

Wan 2.7 credit cost is calculated from the selected resolution and video duration. The current generator uses 2 credits per second for 720p and 4 credits per second for 1080p, and shows the total before generation.

Can I use Wan 2.7 videos commercially?

Yes. Videos generated through wan30.net can be used commercially, provided your use complies with the website's Terms of Service and other applicable policies.