Vofy

Wan 2.7 Image AI Generator and Editor

Generate new images, edit with up to nine references, or create a coherent image set from one request. Use 1K or 2K output in familiar square, portrait, landscape, and widescreen formats.

Try It

Create AI Images with Wan 2.7 Image

Set your parameters and start generating AI images with the workflows and inputs currently supported on this page.

+

Describe the image you want to generate...

Wan 2.7 ImageCustom

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 Image

Wan 2.7 Image combines text-to-image generation, reference-guided editing, and coherent image set creation. In Vofy, choose 1K or 2K output, use up to nine input images, and enable sequential generation for related images.

Illustrative source image for a reference-guided editBefore
Illustrative edited result based on a source imageAfter

Reference-Guided Image Edit

Generate or Edit With Up to Nine References

Start from a text prompt or upload as many as nine images for reference-guided generation and editing. The references can define subjects, products, palettes, materials, composition, or brand direction in one request.

Four-scene greenhouse restoration montage with a consistent character and environment

Cohesive Multi-Image Direction

Create Coherent Image Sets of Up to 12 Images

Enable sequential image generation when a project needs related images rather than independent variations. You can request up to 12 images for story beats, campaign series, product views, or visual development; the model determines the actual number returned.

Images Generated with Wan 2.7 Image

Explore cultural landscapes, cinematic festival scenes, and stylized architectural illustration across distinct visual directions.

Wan 2.7 Image - Colorful Cultural Landscape

Wan 2.7 Image - Colorful Cultural Landscape

Getting Started

How to Create AI Images with Wan 2.7 Image

1

Start From Text or References

Describe a new visual or upload references that define the subject, composition, colors, style, and edit direction.

2

Choose Standard or Image Set Output

Create up to four independent images in standard mode, or enable sequential generation and request up to 12 related images for a set or story.

3

Set the Canvas and Quantity

Choose 1K or 2K resolution, select the target aspect ratio, and generate the number of results needed for comparison or production.

Specifications

Wan 2.7 Image Technical Specs

Creation ModesText-to-image and image-to-image
Resolution1K or 2K
Input ImagesUp to 9 for reference-guided workflows
Output Images1-4 normally; up to 12 in image set mode
Image Set GenerationOptional coherent sets; actual count may vary
FormatsSquare, portrait, landscape, and widescreen presets
Best ForImage series, lifestyle content, and reference-guided edits

Use Cases

What You Can Create with Wan 2.7 Image

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

Lifestyle Product Campaigns

Lifestyle Product Campaigns

Create polished product imagery for seasonal launches, outdoor campaigns, social posts, and ecommerce concepts with consistent packaging and a natural lifestyle setting.

Multi-Reference Product Image Creation

Multi-Reference Product Image Creation

Combine product photos, material references, palettes, and composition ideas to generate a unified commercial visual without manual compositing.

Portrait Restyling and Scene Changes

Portrait Restyling and Scene Changes

Use a portrait as a visual anchor while changing the wardrobe, setting, lighting, and campaign mood for polished lifestyle and editorial variations.

Lifestyle Portraits and Everyday Moments

Lifestyle Portraits and Everyday Moments

Create polished portraits and natural lifestyle scenes for travel, celebrations, social posts, and personal storytelling. Reference images can guide the subject, wardrobe, location, and visual mood.

Frequently Asked Questions

Everything you need to know about Wan 2.7 Image.

What is Wan 2.7 Image?
Wan 2.7 Image is Alibaba's AI model for text-to-image generation, reference-guided image editing, and coherent image set creation. It supports up to nine input images and 1K or 2K output.
How many reference images can I use?
The reference-guided workflow in Vofy accepts up to nine input images for image generation or editing, making it suitable for multi-reference creative direction.
What is sequential image generation?
Sequential generation is Wan 2.7 Image's image set mode. It creates related, story-coherent images from one request instead of treating every result as an independent variation. You can request up to 12 images, but the model determines the actual number returned.
How many images can Wan 2.7 Image generate?
With image set mode disabled, Wan 2.7 Image generates one to four images per request. With sequential image generation enabled, you can request up to 12 images, and the model determines the final number returned.
Which aspect ratios does Wan 2.7 Image support?
Vofy provides common square, portrait, landscape, and widescreen presets for Wan 2.7 Image. The available choices are shown directly in Studio and focus on practical formats for social, personal, and commercial content.
How is Wan 2.7 Image different from Qwen Image 2.0?
Wan 2.7 Image supports larger reference packs and coherent image sets. Qwen Image 2.0 supports up to three input images and six outputs while emphasizing fast generation and text rendering; Qwen Image 2.0 Pro adds stronger text rendering, realistic textures, and semantic adherence.

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