Spaces:

wavespeed
/

qwen-image

Running

App Files Files Community

qwen-image / index.html

chengzeyi

Add UTM attribution to outbound wavespeed.ai links

43198da 7 days ago

Raw

History Blame Contribute Delete

13.6 kB

	<!doctype html>
	<html lang="en">
	<head>
	<meta charset="utf-8" />
	<meta name="viewport" content="width=device-width, initial-scale=1" />
	<title>Qwen-Image — text-to-image foundation model</title>
	<meta name="description" content="Reference for Qwen-Image, Alibaba's open text-to-image foundation model, with emphasis on in-image text rendering. Includes diffusers and hosted API usage." />
	<link rel="canonical" href="https://wavespeed.ai/models/wavespeed-ai/qwen-image/text-to-image?utm_source=huggingface&utm_medium=space&utm_campaign=qwen_image" />

	<meta property="og:type" content="website" />
	<meta property="og:title" content="Qwen-Image — text-to-image foundation model" />
	<meta property="og:description" content="Reference for Qwen-Image, Alibaba's open text-to-image foundation model, with emphasis on in-image text rendering. Includes diffusers and hosted API usage." />
	<meta property="og:url" content="https://wavespeed.ai/models/wavespeed-ai/qwen-image/text-to-image" />
	<meta property="og:image" content="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/merge3.jpg" />
	<meta name="twitter:card" content="summary_large_image" />

	<link rel="stylesheet" href="style.css" />
	</head>
	<body>
	<header class="site-header">
	<div class="wrap">
	<a class="brand" href="https://wavespeed.ai?utm_source=huggingface&utm_medium=space&utm_campaign=qwen_image" target="_blank" rel="noopener">
	<span class="brand-mark" aria-hidden="true"></span>
	<span>WaveSpeed AI</span>
	</a>
	<nav class="header-nav">
	<a class="jump opt" href="#overview">Overview</a>
	<a class="jump opt" href="#strengths">What it does well</a>
	<a class="jump" href="#run">Run it</a>
	<a class="jump opt" href="#local">Local</a>
	<a class="jump" href="#resources">Resources</a>
	<a href="https://wavespeed.ai/models/wavespeed-ai/qwen-image/text-to-image?utm_source=huggingface&utm_medium=space&utm_campaign=qwen_image" target="_blank" rel="noopener">wavespeed.ai ↗</a>
	</nav>
	</div>
	</header>

	<main class="wrap">
	<div class="hero">
	<p class="eyebrow">Alibaba Cloud · Qwen Team</p>
	<h1>Qwen-Image</h1>
	<p class="lede">An open image generation foundation model in the Qwen series. Its distinguishing strength is rendering legible text inside the image — including Chinese — rather than the smeared glyphs most diffusion models produce.</p>
	<ul class="meta">
	<li><b>Developer</b> Alibaba Cloud Qwen Team</li>
	<li><b>Task</b> text-to-image</li>
	<li><b>License</b> Apache-2.0</li>
	<li><b>Weights</b> open</li>
	</ul>
	</div>

	<section id="overview">
	<h2>Overview</h2>
	<p class="section-note">Qwen-Image is a general-purpose text-to-image model that also handles editing and several image-understanding tasks. The authors' benchmark summary is reproduced below.</p>
	<div class="figure-single">
	<figure>
	<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/merge3.jpg" alt="Grid of Qwen-Image sample outputs" loading="lazy" />
	<figcaption>Sample outputs from the official release.</figcaption>
	</figure>
	</div>
	</section>
	<section id="bench">
	<h2>Reported benchmarks</h2>
	<p class="section-note">Published by the Qwen team with the model release. These are the authors' own figures and have not been independently reproduced here.</p>
	<div class="figure-single">
	<figure>
	<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/bench.png" alt="Qwen-Image benchmark chart" loading="lazy" />
	<figcaption>Benchmark summary from the Qwen-Image model card.</figcaption>
	</figure>
	</div>
	</section>
	<section id="strengths">
	<h2>What it does well</h2>
	<div class="grid">
	<div class="card">
	<h3>Text inside the image</h3>
	<p>Typography is generated as part of the scene, holding layout and letterforms together for both alphabetic scripts and Chinese — the capability the model is built around.</p>
	</div>
	<div class="card">
	<h3>Style range</h3>
	<p>Photographic, painterly, anime and flat-design outputs all come from the same checkpoint, steered by prompt rather than by LoRA.</p>
	</div>
	<div class="card">
	<h3>Editing operations</h3>
	<p>Style transfer, object insertion and removal, detail enhancement and text replacement inside an existing image.</p>
	</div>
	<div class="card">
	<h3>Understanding tasks</h3>
	<p>Detection, segmentation, depth and edge estimation, novel view synthesis and super-resolution, framed as conditional generation.</p>
	</div>
	</div>
	</section>
	<section id="showcase">
	<h2>Showcase</h2>
	<div class="figure-grid">
	<figure>
	<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/s1.jpg" alt="Text rendering examples" loading="lazy" />
	<figcaption><b>Text rendering.</b> Signage and dense copy integrated into the scene.</figcaption>
	</figure>
	<figure>
	<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/s2.jpg" alt="Artistic style examples" loading="lazy" />
	<figcaption><b>Styles.</b> Photoreal through to illustrative, one checkpoint.</figcaption>
	</figure>
	<figure>
	<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/s3.jpg" alt="Image editing examples" loading="lazy" />
	<figcaption><b>Editing.</b> Insertion, removal and in-image text edits.</figcaption>
	</figure>
	<figure>
	<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/s4.jpg" alt="Image understanding examples" loading="lazy" />
	<figcaption><b>Understanding.</b> Depth, edges, segmentation and view synthesis.</figcaption>
	</figure>
	</div>
	</section>
	<section id="run">
	<h2>Run it</h2>
	<p class="section-note">The hosted endpoint runs the same weights without a local GPU.</p>
	<div class="code">
	<div class="code-tabs" role="tablist">
	<button type="button" role="tab" aria-selected="true" data-panel="run-0">cURL</button>
	<button type="button" role="tab" aria-selected="false" data-panel="run-1">Python</button>
	<button type="button" role="tab" aria-selected="false" data-panel="run-2">JavaScript</button>
	</div>
	<pre id="run-0" role="tabpanel"><code># 1. submit the job
	curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/qwen-image/text-to-image" \
	-H "Authorization: Bearer $WAVESPEED_API_KEY" \
	-H "Content-Type: application/json" \
	-d '{
	"prompt": "A chalkboard outside a coffee shop reading \"Qwen Coffee \u2014 $2 a cup\", warm morning light, shallow depth of field",
	"size": "1328*1328",
	"enable_sync_mode": false
	}'

	# -> {"code": 200, "data": {"id": "<request-id>", "status": "created", ...}}

	# 2. poll until status is "completed"
	curl "https://api.wavespeed.ai/api/v3/predictions/<request-id>/result" \
	-H "Authorization: Bearer $WAVESPEED_API_KEY"

	# -> {"code": 200, "data": {"status": "completed", "outputs": ["https://..."]}}</code></pre>
	<pre id="run-1" role="tabpanel" hidden><code>import os, time, requests

	API = "https://api.wavespeed.ai/api/v3"
	KEY = os.environ["WAVESPEED_API_KEY"]
	HEADERS = {"Authorization": f"Bearer {KEY}"}

	# submit
	res = requests.post(
	f"{API}/wavespeed-ai/qwen-image/text-to-image",
	headers={**HEADERS, "Content-Type": "application/json"},
	json={
	"prompt": "A chalkboard outside a coffee shop reading \"Qwen Coffee \u2014 $2 a cup\", warm morning light, shallow depth of field",
	"size": "1328*1328",
	"enable_sync_mode": false
	},
	timeout=30,
	)
	res.raise_for_status()
	request_id = res.json()["data"]["id"]

	# poll
	while True:
	data = requests.get(
	f"{API}/predictions/{request_id}/result",
	headers=HEADERS,
	timeout=30,
	).json()["data"]

	if data["status"] == "completed":
	print(data["outputs"][0])
	break
	if data["status"] == "failed":
	raise RuntimeError(data.get("error", "generation failed"))
	time.sleep(1.5)</code></pre>
	<pre id="run-2" role="tabpanel" hidden><code>const API = "https://api.wavespeed.ai/api/v3";
	const KEY = process.env.WAVESPEED_API_KEY;
	const headers = { Authorization: `Bearer ${KEY}` };

	// submit
	const submit = await fetch(`${API}/wavespeed-ai/qwen-image/text-to-image`, {
	method: "POST",
	headers: { ...headers, "Content-Type": "application/json" },
	body: JSON.stringify({
	"prompt": "A chalkboard outside a coffee shop reading \"Qwen Coffee \u2014 $2 a cup\", warm morning light, shallow depth of field",
	"size": "1328*1328",
	"enable_sync_mode": false
	}),
	});
	const { data: { id } } = await submit.json();

	// poll
	for (;;) {
	const res = await fetch(`${API}/predictions/${id}/result`, { headers });
	const { data } = await res.json();

	if (data.status === "completed") {
	console.log(data.outputs[0]);
	break;
	}
	if (data.status === "failed") throw new Error(data.error ?? "generation failed");
	await new Promise((r) => setTimeout(r, 1500));
	}</code></pre>
	</div>
	<div class="callout"><p>Requests are asynchronous: <code>POST</code> returns a request id, then you poll <code>/predictions/<id>/result</code> until <code>status</code> is <code>completed</code>. Set <code>enable_sync_mode: true</code> to have the call block and return outputs directly.</p><p>API keys are created in the <a href="https://wavespeed.ai/dashboard?utm_source=huggingface&utm_medium=space&utm_campaign=qwen_image" target="_blank" rel="noopener">WaveSpeed dashboard</a>.</p></div>
	<div class="btn-row">
	<a class="btn" href="https://wavespeed.ai/models/wavespeed-ai/qwen-image/text-to-image?utm_source=huggingface&utm_medium=space&utm_campaign=qwen_image" target="_blank" rel="noopener">Open on WaveSpeed</a>
	<a class="btn secondary" href="https://wavespeed.ai/docs?utm_source=huggingface&utm_medium=space&utm_campaign=qwen_image" target="_blank" rel="noopener">API reference</a>
	</div>
	</section>
	<section id="local">
	<h2>Running locally</h2>
	<p class="section-note">Weights are Apache-2.0 and load through <code>diffusers</code>.</p>
	<div class="code">
	<div class="code-tabs" role="tablist">
	<button type="button" role="tab" aria-selected="true" data-panel="local-0">Python</button>
	</div>
	<pre id="local-0" role="tabpanel"><code>import torch
	from diffusers import DiffusionPipeline

	pipe = DiffusionPipeline.from_pretrained(
	"Qwen/Qwen-Image",
	torch_dtype=torch.bfloat16,
	).to("cuda")

	# The Qwen team recommends appending a quality suffix to the prompt.
	magic = {"en": "Ultra HD, 4K, cinematic composition.", "zh": "超清，4K，电影级构图"}

	image = pipe(
	prompt='A chalkboard reading "Qwen Coffee — $2 a cup". ' + magic["en"],
	negative_prompt=" ",
	width=1664,
	height=928, # 1:1 1328x1328 · 16:9 1664x928 · 4:3 1472x1140
	num_inference_steps=50,
	true_cfg_scale=4.0,
	generator=torch.Generator(device="cuda").manual_seed(42),
	).images[0]

	image.save("out.png")</code></pre>
	</div>
	</section>
	<section id="resources">
	<h2>Resources</h2>
	<ul class="links">
	<li><a href="https://huggingface.co/Qwen/Qwen-Image" target="_blank" rel="noopener"><span>Qwen/Qwen-Image weights</span><span class="host">huggingface.co</span></a></li>
	<li><a href="https://github.com/QwenLM/Qwen-Image" target="_blank" rel="noopener"><span>Qwen-Image on GitHub</span><span class="host">github.com</span></a></li>
	<li><a href="https://wavespeed.ai/models/wavespeed-ai/qwen-image/text-to-image?utm_source=huggingface&utm_medium=space&utm_campaign=qwen_image" target="_blank" rel="noopener"><span>Hosted endpoint</span><span class="host">wavespeed.ai</span></a></li>
	<li><a href="https://huggingface.co/spaces/wavespeed/qwen-edit-image" target="_blank" rel="noopener"><span>Editing variant</span><span class="host">huggingface.co</span></a></li>
	</ul>
	</section>
	</main>

	<footer class="site-footer">
	<div class="wrap">
	<p>This page is a model reference maintained by WaveSpeed AI. The model itself is developed and released by its respective authors; trademarks belong to them. WaveSpeed AI provides hosted inference for it.</p>
	<div class="footer-links">
	<a href="https://wavespeed.ai?utm_source=huggingface&utm_medium=space&utm_campaign=qwen_image" target="_blank" rel="noopener">WaveSpeed AI</a>
	<a href="https://wavespeed.ai/docs?utm_source=huggingface&utm_medium=space&utm_campaign=qwen_image" target="_blank" rel="noopener">Docs</a>
	<a href="https://huggingface.co/wavespeed" target="_blank" rel="noopener">Hugging Face</a>
	</div>
	</div>
	</footer>

	<script src="tabs.js"></script>
	</body>
	</html>