MODELS · IMAGE · ALIBABA

Wan2.7 Image.

Alibaba's unified image generator and editor — avatar customization, 9 reference images, and text in 12 languages

Text to imageImage to imageImage editing

Free to start · 100+ models on one account · cancel anytime

About Wan2.7 Image

Wan 2.7 Image is Alibaba's unified image model, combining generation and interactive editing in one shared latent space instead of treating them as separate tools. It accepts up to 9 reference images per generation, virtual avatar face customization with fine bone-structure and eye-shape control, a color-palette system for extracting and reapplying consistent color schemes, and region-based selection editing for pixel-level control over specific areas. Text rendering supports up to 3,000 tokens across 12 languages, useful for posters, signage, or other text-heavy compositions. Output runs from 768 to 2048 pixels per side, and compositional generation can combine up to 12 images in a single output. This is the image entry point to Wan 2.7 — Alibaba's separate Wan 2.7 model handles video.

  • Text to image
  • Image to image
  • Image editing

How to use Wan2.7 Image on getvivix

STEP 1
Sign in & open Studio

Create a free getvivix account — no card required.

STEP 2
Pick Wan2.7 Image

Choose Wan2.7 Image from the model list and set your options.

STEP 3
Generate & download

Enter your prompt or upload your input, hit generate, then download in full quality.

Wan2.7 Image — frequently asked

What is Wan2.7 Image?

Wan2.7 Image is one of 100+ AI models available on getvivix. Wan 2.7 Image is Alibaba's unified image model, combining generation and interactive editing in one shared latent space instead of treating them as separate tools. It accepts up to 9 reference images per generation, virtual avatar face customization with fine bone-structure and eye-shape control, a color-palette system for extracting and reapplying consistent color schemes, and region-based selection editing for pixel-level control over specific areas. Text rendering supports up to 3,000 tokens across 12 languages, useful for posters, signage, or other text-heavy compositions. Output runs from 768 to 2048 pixels per side, and compositional generation can combine up to 12 images in a single output. This is the image entry point to Wan 2.7 — Alibaba's separate Wan 2.7 model handles video.

How do I use Wan2.7 Image on getvivix?

Sign in to getvivix and open the Studio, pick Wan2.7 Image from the model list, enter your prompt (or upload your input), and generate — then download the result in full quality.

Is Wan2.7 Image free to try?

Yes — getvivix has a free tier, so you can try Wan2.7 Image without a card. Sign up and start generating right away, alongside 100+ other AI models on one account.

What can Wan2.7 Image do?

Wan2.7 Image supports text to image, image to image, image editing. It runs on getvivix alongside 100+ other frontier AI models, all from one account.

More image models

Browse all 100+ models