Qwen-Image 2512

Name: Qwen-Image 2512
Author: Qwen

by Qwen

Image

Qwen-Image 2512 high-fidelity text-to-image with strong text rendering, served in-process by the Pendra (stable-diffusion.cpp) backend.

Publisher: Qwen

Model card on Hugging Face

Run Qwen-Image 2512

Install it on a Pendra worker, then call it through the OpenAI-compatible API with a pdr_sk_ key.

from pendra import Pendra
import base64, pathlib

client = Pendra(api_key="pdr_sk_...")

result = client.images.generations.create(
    model="qwen-image-2512",
    prompt="A misty Welsh valley at dawn",
    size="1024x1024",
)

pathlib.Path("out.png").write_bytes(base64.b64decode(result.data[0].b64_json))

import { Pendra } from "pendra";
import { writeFileSync } from "node:fs";

const client = new Pendra({ apiKey: "pdr_sk_..." });

const result = await client.images.generations.create({
  model: "qwen-image-2512",
  prompt: "A misty Welsh valley at dawn",
  size: "1024x1024",
});

writeFileSync("out.png", Buffer.from(result.data[0].b64_json, "base64"));

Run Qwen-Image 2512 on your own UK infrastructure

Deploy a worker, install Qwen-Image 2512, and start serving it through one sovereign API endpoint.

Get started free Read the quickstart