qwen-image-2.0

Specs & limits

• Accelerated version of qwen-image-2.0-pro balancing quality and speed
• API-only (no open-weights release on the official Qwen Hugging Face org)

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.

qwen-image-2.0

Model returned 1024×1024 latency 6 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 qwen-image-2.0 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="qwen-image-2.0",
    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: "qwen-image-2.0",
  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": "qwen-image-2.0",
    "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:  "qwen-image-2.0",
		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("qwen-image-2.0")
        .prompt("a watercolor lighthouse at dawn")
        .size("1024x1024")
        .build());
System.out.println(resp.data().orElseThrow().get(0).b64Json().orElseThrow().substring(0, 80));

About qwen-image-2.0

• Versus the original Qwen-Image, the official announcement highlights a lighter architecture with faster inference, native 2K-resolution output, and markedly stronger typography: it follows instructions up to 1k tokens to generate professional infographics such as PPT slides, posters, and comics directly.
• Custom width and height are supported within the documented pixel range, from 512x512 up to a 2048x2048 default, across presets for 1:1, 16:9, 9:16, 4:3 and 3:4, with one to six images per request, negative prompts up to 500 characters, an optional watermark, and prompt expansion on by default.
• Editing runs through the same model id rather than a separate endpoint: supply one to three reference images and the documented operations cover precise edits to text inside an image, adding, removing or moving objects, changing a subject's pose, transferring style, and enhancing detail.
• Two API facts are worth planning around.
• This model is synchronous only, returning results in a single request with no async task flow and no streaming, and the difference from the Pro tier is stated as quality rather than capability: identical limits, with this variant balancing quality against response speed.
• Synthorai offers it for image generation through its OpenAI-compatible endpoint.

FAQ

Related models

Compare