wan2.7-image API

Use the exact model ID wan2.7-image. The model field must match this page exactly.

Sample outputwan2.7-imagePOST /v1/images/generations

Parameters: size=1536x1024n=1

Prompt: A long hotel corridor with a heavily patterned carpet, doors receding into the distance. A woman in a floor-length crimson satin coat has just taken one step forward. Behind her heel the carpet pattern has started to peel up off the floor, lifting away as loose ribbons of colour that keep the print exactly and curl into the air down the length of the hall. One hard green exit sign above, warm wall sconces along the corridor. Wide low camera on the floor line, deep perspective, real cloth weight, film grain, slight vignette, no text.

Request that produced this sample

{
  "model": "wan2.7-image",
  "prompt": "A long hotel corridor with a heavily patterned carpet, doors receding into the distance. A woman in a floor-length crimson satin coat has just taken one step forward. Behind her heel the carpet pattern has started to peel up off the floor, lifting away as loose ribbons of colour that keep the print exactly and curl into the air down the length of the hall. One hard green exit sign above, warm wall sconces along the corridor. Wide low camera on the floor line, deep perspective, real cloth weight, film grain, slight vignette, no text.",
  "n": 1,
  "size": "1536x1024"
}

Authentication and endpoint

Use a Modelflare API key with https://modelflare.dev/v1. The gateway entry point is POST /v1/images/generations.

HTTP

Authorization: Bearer YOUR_MODELFLARE_API_KEY

Generate an image

bash

curl https://modelflare.dev/v1/images/generations \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-image",
    "prompt": "A white cat runs through a neon-lit street in the rain",
    "size": "1024x1024", "n": 1
  }'

Request notes

OpenAI-compatible image models use prompt, n, size, and quality; use editing only when the official page documents it.

Request parameters

Wan2.7 Image / Pro uses the synchronous Images API. Use the flat OpenAI-compatible shape for simple calls; use input.messages plus parameters for multi-image, region editing, and sequential generation. Pro text-to-image supports up to 4K outside sequential mode; the standard model supports up to 2K.

Field	Required	Notes
model	Yes	wan2.7-image
prompt	Yes	Generation or editing instruction
image	No	Single image URL/Base64; use input.messages for up to 9 images
input.messages	No	Nested messages for multi-image, region editing, and sequential generation
size	No	1K / 2K; Pro non-sequential text-to-image also supports 4K
n	No	1–4 for ordinary generation; 1–12 for sequential generation; billed per successful image
thinking_mode	No	Thinking mode when no image is supplied
watermark	No	Whether to add a watermark
parameters.prompt_extend	No	Prompt expansion, default true;
parameters.bbox_list	No	Interactive editing region boxes
parameters.enable_sequential	No	Enable sequential generation
parameters.color_palette	No	3–10 HEX colors with percentages totaling 100%

Response and input limits

Use the flat shape for simple calls; use input.messages and parameters for multi-image, region editing, and sequential generation. Up to 9 input images are supported, each under 20 MB, 240–8,000 px per edge, with a 1:8 to 8:1 aspect ratio. Ordinary output count is 1–4 and sequential output count is 1–12; Pro text-to-image supports 4K outside sequential mode, while other combinations top out at 2K.

Documented workflow examples

Wan2.7 Image supports both a flat shape and the nested input.messages/parameters shape; use the nested shape for multi-image, region editing, and sequential generation.

Multi-image editing

bash

curl https://modelflare.dev/v1/images/generations \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-image",
    "input": {"messages": [{"role": "user", "content": [
      {"image": "https://example.com/person.png"},
      {"image": "https://example.com/background.png"},
      {"text": "将图 1 中的人物放入图 2 的场景中"}
    ]}], "parameters": {"size": "2K", "n": 1, "prompt_extend": true}}
  }'

Interactive region editing

bash

curl https://modelflare.dev/v1/images/generations \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-image", "input": {"messages": [{"role": "user", "content": [
      {"image": "https://example.com/room.png"},
      {"text": "将选中区域的花瓶替换成红玫瑰"}
    ]}], "parameters": {"size": "2K", "n": 1, "bbox_list": [[[420, 280, 760, 720]]]}}
  }'

Sequential image group

bash

curl https://modelflare.dev/v1/images/generations \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-image", "input": {"messages": [{"role": "user", "content": [{"text": "生成四张角色一致的季节分镜"}]}]},
    "parameters": {"size": "2K", "enable_sequential": true, "n": 4, "watermark": false}
  }'

Errors and failed tasks

Invalid model parameters return a 4xx with a request ID; use the response fields and error message defined by the selected model contract.

Supported scope

This page covers Modelflare model generation and editing calls. Search or map enrichment, voice management, and element-library management are resource APIs outside this public model-call surface and are not required request fields.

Pricing and billing

This model uses per-call billing. See the model pricing page for the current customer price, reference list price, and complete specification.

Note

This page documents Modelflare’s public interface; the fields and limits shown here are the current contract.

Variants

Model ID	Difference
wan2.7-image	The model documented on this page.