API docs / Image models

Wan 2.7 Image API

Generate and edit images using Alibaba's Wan 2.7 model with support for text-to-image generation, image editing, style transfer, and multi-image fusion. Supports resolutions up to 2K (2048×2048) with flexible aspect ratios including 1280×720, 2048×1152, 1024×768, and custom dimensions. Takes up to 9 input images for editing, style transfer, or multi-reference generation, allowing you to apply styles, swap elements between images, and blend multiple references into a single output. Features image set mode for generating coherent sets of related images from a single prompt, creating up to 12 images that maintain consistency across scenes. Includes thinking mode for enhanced reasoning and improved image quality in text-to-image generation.

Model id
wan-video/wan-2.7-image
Provider
wan-video
Output
Image
Price
From 11 credits per run, the same as on voor.ai. Options such as length or resolution can change it.

Request

POST https://voor.ai/v1/generations with "model": "wan-video/wan-2.7-image". Poll GET /v1/tasks/{id} or receive the signed webhook. See the overview for keys, idempotency, webhooks and errors.

curl https://voor.ai/v1/generations \
  -H "Authorization: Bearer $VOOR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "wan-video/wan-2.7-image",
  "input": {
    "prompt": "A red fox standing in fresh snow at golden hour, soft light"
  },
  "callback_url": "https://example.com/webhooks/voor"
}'

# Then poll the task (or wait for the webhook):
curl https://voor.ai/v1/tasks/TASK_ID \
  -H "Authorization: Bearer $VOOR_API_KEY"

Input parameters

NameTypeDetails
promptrequiredstring

Text prompt for image generation or editing

reference_imagesarray of URLs

Input images for editing, style transfer, or multi-reference generation (up to 9 images, jpg/png/bmp/webp). When provided, the model operates in image editing mode.

Default: []

Up to 10 files · Accepts image/*

output_countnumber

Number of images to generate (1-4 for standard mode, 1-12 for image set mode)

Default: 1

Min 1 · Max 4

sizestring

Default: 2K

One of: 1K, 2K, 1024*1024, 2048*2048, 1280*720, 720*1280, 2048*1152, 1152*2048, 1024*768, 768*1024, 2048*1536, 1536*2048

seednumber

Random seed for reproducible generation. Range: 0-2147483647

image_set_modeboolean

Generate a coherent set of related images from a single prompt (e.g. a character across seasons). When enabled, num_outputs can be up to 12.

Default: false

thinking_modeboolean

Enable enhanced reasoning for improved image quality. Only applies to text-to-image (no input images, no image set mode). Increases generation time.

Default: true