Wan 2.2 Image

What is Wan 2.2 Image?#

Wan 2.2 Image is the text-to-image model in Alibaba's Wan 2.2 line. It is the smallest possible parameter surface for a Wan image call: prompt, aspect ratio, optional negative prompt, optional seed. No reference images, no editing mode, no thinking mode. Output runs at five aspect ratios (1:1, 3:4, 4:3, 9:16, 16:9). The 500-character prompt cap and tight controls make it a good fit for high-volume backends and integrations that do not need editing.

Key features of Wan 2.2 Image#

Four features cover what the model actually exposes.

Five aspect ratios in one model

1:1, 3:4, 4:3, 9:16, and 16:9 cover square feed posts, portrait, landscape, vertical reels, and standard hero banners.

Text-to-image only

No reference image input, no inpainting, no editing mode. Useful for backends where the smaller surface keeps the contract stable.

Negative prompts for brand-safe output

Suppress unwanted content with `negative_prompt`. Useful for guarding against logos, faces, and other content categories that have to stay out.

Seed control for reproducibility

Pass an integer seed and the same prompt returns the same image. Useful for regression checks and A/B copy variants.

Best for#

API examples#

Call Wan 2.2 Image from any language by POSTing to /v1/tasks. Full parameter docs live at docs.unifically.com/models/image/alibaba/wan-2.2-image.

curl -X POST https://api.unifically.com/v1/tasks \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "alibaba/wan-2.2-image",
    "input": {
      "prompt": "Aurora borealis over a snowy chapel, soft light",
      "aspect_ratio": "16:9"
    }
  }'

Successful submission returns a task_id. Poll GET /v1/tasks/<task_id> or set a callback_url on the request to receive the finished result.