Wan2.7-Image

Wan2.7-Image

Provider: Alibaba Cloud
Category: Image Generation
Endpoint: POST /v1/images/generations
Context window:
Served from: Singapore

Image generation and editing companion model: text-to-image, bounding-box edits, and cohesive image sets, with up to 4K output on Pro.

At a glance

FieldValue
Model idwan2-7-image
Input modalitiestext
Output modalitiesimage
Context window
RegionSingapore
Featuresimage_editing, 4k
NewNo
Native inferenceNo

Pricing

ChargeSpecRate
Standardper image$0.030
Proper image$0.075

Example request

$curl https://api.empiriolabs.ai/v1/images/generations \
> -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
> -H 'Content-Type: application/json' \
> -d '{"model": "wan2-7-image", "prompt": "a misty forest at dawn", "size": "1024x1024"}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringyesText prompt. For Image Set mode, describe each image in sequence (e.g. ‘First image: … Second image: …’).
modelenumno"wan2.7-image-pro"Pro: 4K + Thinking Mode + higher quality. Standard: faster, cheaper. · Allowed: wan2.7-image-pro, wan2.7-image
aspect_ratioenumnoOptional. If omitted, text-to-image defaults to 16:9; image-edit matches the last input image’s native ratio. · Allowed: 16:9, 1:1, 9:16, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5
resolutionenumno"2K"Quality tier. 1K ~1MP, 2K ~4MP, 4K ~16MP (Pro text-to-image only). · Allowed: 1K, 2K, 4K
use_custom_sizebooleannofalseOverride aspect_ratio + resolution with explicit pixel dimensions.
custom_widthnumbernoPixels (768–2048; Pro text-to-image up to 4096). Only when use_custom_size=true. Aspect must be in [1:8, 8:1]. · Range: 768 – 4096
custom_heightnumbernoPixels (768–2048; Pro text-to-image up to 4096). Only when use_custom_size=true. · Range: 768 – 4096
enable_sequentialbooleannofalseImage Set Mode. Generate up to 12 cohesive related images. Disables thinking_mode and color_palette.
num_imagesnumberno1Standard mode only. Number of images to generate. Each is billed separately. · Range: 1 – 4
num_images_setnumberno1Image Set Mode only. Maximum images in the set. The model decides the actual count; you’re billed only for images generated. · Range: 1 – 12
thinking_modebooleannotruePro only. Enhanced inference for higher quality at the cost of latency. Auto-ignored when input images are attached or sequential mode is on.
imagearraynoUp to 9 input image URLs for editing. Triggers image-edit mode automatically.
color_palettestringnoOptional JSON array of 3–10 {hex, ratio} objects (ratios sum to 100%). Standard mode only. Example: [{“hex”:“#C2D1E6”,“ratio”:“60.00%”},{“hex”:“#636574”,“ratio”:“40.00%”}]
bbox_liststringnoInteractive editing. JSON array, one entry per input image. [] for no box, [[x1,y1,x2,y2]] for one box (max 2 per image). Absolute pixels, top-left origin.
seednumbernoReproducibility seed. Leave empty for random. · Range: 0 – 2147483647
watermarkbooleannofalseAdd an EmpirioLabs watermark to the output.
response_formatenumno"url"Allowed: url, b64_json

Live machine-readable schema is also available at GET https://api.empiriolabs.ai/v1/models/wan2-7-image.