wan2.7-image

Specs & limits

• Same feature set as wan2.7-image-pro with faster generation and lower max resolution
• no official open-weights release for Wan2.7

per Alibaba official docs ↗

One prompt, measured through the gateway

PROMPT A weathered enamel diner mug on a steel counter, the words "OPEN 24H" stencilled on the mug in worn paint, low winter sun raking in from the left, shallow depth of field.

wan2.7-image

Model returned 1024×1024 latency 18 s

One prompt, one request per model, no retries and no cherry-picking - the first result each model returned. Neither size nor duration was pinned: each model used its own default, because a request shaped to fit all of them would flatter none. Files here are re-encoded for the web, so judge composition and prompt adherence, not compression.

Use wan2.7-image in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/images/generations

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.images.generate(
    model="wan2.7-image",
    prompt="a watercolor lighthouse at dawn",
    size="1024x1024",
)
print(resp.data[0].b64_json[:80])

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://synthorai.io/v1",
  apiKey: "sk-syn-...",
});

const resp = await client.images.generate({
  model: "wan2.7-image",
  prompt: "a watercolor lighthouse at dawn",
  size: "1024x1024",
});
console.log(resp.data?.[0]?.b64_json?.slice(0, 80));

curl https://synthorai.io/v1/images/generations \
  -H "Authorization: Bearer sk-syn-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-image",
    "prompt": "a watercolor lighthouse at dawn",
    "size": "1024x1024"
  }'

package main

import (
	"context"
	"fmt"

	"github.com/openai/openai-go/v3"
	"github.com/openai/openai-go/v3/option"
)

func main() {
	client := openai.NewClient(
		option.WithBaseURL("https://synthorai.io/v1"),
		option.WithAPIKey("sk-syn-..."),
	)
	resp, _ := client.Images.Generate(context.TODO(), openai.ImageGenerateParams{
		Model:  "wan2.7-image",
		Prompt: "a watercolor lighthouse at dawn",
		Size:   "1024x1024",
	})
	fmt.Println(resp.Data[0].B64JSON[:80])
}

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.images.*;

OpenAIClient client = OpenAIOkHttpClient.builder()
    .baseUrl("https://synthorai.io/v1")
    .apiKey("sk-syn-...")
    .build();

ImagesResponse resp = client.images().generate(
    ImageGenerateParams.builder()
        .model("wan2.7-image")
        .prompt("a watercolor lighthouse at dawn")
        .size("1024x1024")
        .build());
System.out.println(resp.data().orElseThrow().get(0).b64Json().orElseThrow().substring(0, 80));

About wan2.7-image

• The official docs note support for up to 2K resolution in editing and image-set scenarios, and position this base variant as the faster-generation option in the 2.7 lineup.
• Where Pro reaches 4K, this model is capped at 2048x2048 in every scenario, which is the whole of the documented difference between them.
• The shared feature set is what makes the line distinctive against Alibaba's other image models: prompts up to 5,000 characters in Chinese or English, aspect ratios spanning 1:8 to 8:1, region-based interactive editing that takes bounding boxes instead of only free-text instructions, character-consistent sets of up to twelve images from a single call, and a brand-colour palette parameter accepting several hex values with proportions.
• Negative prompts are not supported here, unlike the Qwen-Image line.
• Reference images are accepted across a wide dimension range at up to 20 MB each.
• Both synchronous and asynchronous task-based calling are documented (create a task, then poll it to completion).
• Output arrives as PNG with generated URLs expiring after twenty-four hours, and only successfully generated images are billed.
• Synthorai makes Wan2.7-Image available to developers through its OpenAI-compatible endpoint.

FAQ

Related models

Compare