Qwen

Qwen Image

Name: Qwen Image
Author: Qwen

Qwen Image is the Qwen series' image foundation model, built for complex text rendering, with custom sizes up to 2048px. Best for images with lots of text.

Try

A surreal studio still life of a severed humanoid hand sculpted in a muted green, zombie-like tone, positioned upright a

Remix

A cinematic portrait of a woman astronaut standing on the rocky surface of a distant planet, beneath a pale sky tinted w

Remix

Dynamic low-angle fashion portrait of a confident young man standing outdoors under a bright blue sky with scattered clo

Remix

Text prompt: Input
19: Presets
2048 pixels: Max edge
Guidance, steps, negative prompt, seed: Controls

Overview

About Qwen Image

Qwen Image is an image generation foundation model in the Qwen series, which Masonry runs through fal. fal describes it as achieving significant advances in complex text rendering and precise image editing. In Masonry this model is text-to-image: you describe the image, choose one of nineteen presets or a custom size, and can tune guidance, inference steps, a negative prompt, and a seed. Editing runs on the separate Qwen Image Edit Plus model.

Complex text rendering is the reason to pick it. Posters, menus, infographics, signage, and social graphics with several lines of copy depend on the words coming out right, and that is the strength fal highlights. Masonry's presets cover feed, story, portrait, landscape, and ultrawide shapes, and custom sizes go up to 2048 pixels on the long edge and about four megapixels in total, with ratios up to 4:1. As with any image model, proofread every word before an image ships.

Real prompts

Prompts behind these Qwen Image images

Actual prompts from Qwen Image renders by the Masonry community. Copy any prompt, then remix it into your own creation.

A close-up portrait of a young woman on an outdoor basketball court, bathed in warm natural sunlight. She has dewy, glowing skin with soft freckles, light makeup, and slightly parted lips. Her hair is tied back neatly, with a few loose strands framing her face. A basketball is positioned close to her cheek, dominating part of the foreground and adding texture contrast to her smooth skin. The lighting creates gentle shadows and highlights across her face, emphasizing her natural features and sporty confidence. Shot with a shallow depth of field and cinematic color grading for a modern, lifestyle aesthetic.
Remix

A steaming bowl of freshly prepared Maggi noodles with curly, golden-yellow strands glistening under warm ambient light. The noodles are lightly coated in a glossy, savory sauce with hints of spice, their texture appearing soft yet springy. Small bits of finely chopped vegetables — green chilies, onions, and tomatoes — add pops of color and freshness throughout. The dish is garnished with freshly chopped coriander leaves, a drizzle of soy sauce, and a few drops of chili oil for visual contrast. The bowl, rustic and ceramic with earthy tones, rests on a neatly folded beige linen napkin placed over a weathered wooden table, enhancing the homely, organic atmosphere. Wisps of steam rise gracefully from the noodles, subtly twisting upward into the air, suggesting heat and freshness. Around the bowl, scattered sprigs of herbs, a few slices of crusty bread, and a wooden spoon add authenticity and warmth. Soft, diffused lighting from the side casts gentle highlights on the noodles and delicate shadows on the table, evoking the golden glow of late afternoon. The overall mood is cozy, inviting, and nostalgic — a comforting homemade meal captured in perfect detail, ideal for illustrating home-cooked comfort food, Indian-style quick meals, or cozy kitchen moments.
Remix

a person taking a mirror selfie in what appears to be a gym locker room. They are wearing a black athletic outfit consisting of a cropped sports top and fitted shorts. The person is holding a pink smartphone in front of their face, partially obscuring their features. They have several visible tattoos on their arms, torso, and leg, and a small belly button piercing. Their light brown hair is styled straight and loose, and they are wearing a white seashell choker necklace. The background includes lockers, a bench, and neutral-colored walls, all well-lit with overhead fluorescent lighting, giving the scene a clean and modern gym atmosphere.
Remix

a stylish person posing confidently against a muted green studio backdrop. They are dressed in a sharp, tailored gray pinstripe suit with a double-breasted blazer and matching wide-leg trousers. Underneath, they wear a light blue dress shirt with the collar slightly open and a colorful striped tie worn loosely for a relaxed, modern look. The person accessorizes with dark sunglasses, black leather loafers, and a large textured black leather duffel bag held in one hand. Their wavy, shoulder-length dark hair and neutral expression add to the composed, fashion-forward aesthetic. The lighting is soft and even, emphasizing the outfit’s structure and texture, giving the overall scene a refined, editorial feel that blends classic menswear-inspired tailoring with contemporary minimalism.
Remix

a man outdoors in a cold, mountainous environment, dressed in technical winter gear. He is wearing a dark gray waterproof jacket with taped seams, multiple zippers, and orange accent details, giving it a sleek, high-performance look. A dark knit beanie covers his head, and he has a neatly groomed beard. The jacket includes reinforced sleeves and pockets, and he is carrying a backpack with visible shoulder straps, suggesting he’s prepared for outdoor activity such as hiking or mountaineering. The background features blurred rocky terrain with patches of snow, emphasizing the cold and rugged setting. The lighting is soft and natural, highlighting the texture of his clothing and the moisture on its surface. The overall atmosphere conveys resilience, focus, and adventure in a harsh winter landscape.
Remix

a woman posing against a plain light background, styled in an elegant and minimal fashion. She is wearing a black, deep V-neck top with slightly puffed shoulders, giving her outfit a sophisticated silhouette. Her dark, straight hair is parted in the middle and tucked neatly behind her ears, complementing her polished appearance. The main focus is on her accessories with layered gold necklaces featuring small pendants and hoops earrings that match in tone. Her makeup is natural and refined, emphasising a smooth complexion, neutral lips, and well-groomed brows. The lighting is soft and even, highlighting her features with a gentle glow. The overall mood is poised, confident, and modern — fitting for a beauty, fashion, or jewellery editorial portrait.
Remix

A surreal cinematic scene set inside a vast, abandoned gothic cathedral with towering stone arches, cracked walls, and tall stained-glass windows diffusing cold, misty daylight. Suspended in mid-air at the center of the nave is a bright orange sports car, lifted by heavy chains and a metal hoist frame attached to the vaulted ceiling. The car hangs perfectly horizontal, emphasizing tension and impossibility. Moss, vines, and creeping vegetation reclaim the ancient stone interior, while puddles on the cracked stone floor reflect the cathedral’s architecture and the floating vehicle above. The contrast between the modern, glossy supercar and the decaying medieval environment creates a striking visual juxtaposition. Lighting is soft but dramatic, with volumetric light rays cutting through dust and fog, evoking a mood of mystery, surrealism, and post-apocalyptic elegance. Highly detailed, cinematic realism with a dark, contemplative atmosphere.
Remix

A striking close-up portrait of a vividly colored lizard perched on a textured rock, captured at eye level with shallow depth of field. The reptile features an extraordinary gradient of saturated hues—electric blue scales along the body, fiery orange and red tones on the head and limbs, and subtle purple transitions across the neck and torso. Fine scale textures are sharply detailed, with glossy highlights catching the light. One large, reflective eye is in crisp focus, conveying alertness and curiosity. The background fades into a dark, softly blurred gradient, isolating the subject and enhancing contrast. Lighting is dramatic yet controlled, emphasizing color vibrancy and surface detail. The overall mood is bold, exotic, and visually arresting, ideal for wildlife art, fantasy realism, or high-end digital illustration.
Remix

a realistic Vogue magazine cover–style fashion portrait using the uploaded face as the original face reference (100% face identity preservation). A young elegant woman posing confidently, maintaining her original facial features and natural beauty. She is winking with her left eye and making a playful duck-face expression. Both hands are raised, forming a love/heart gesture near her face. She is surrounded by multiple DSLR cameras and smartphones held around her, as if paparazzi and photographers are capturing her from all directions. Some phones show her live image on their screens. Appearance & styling: flawless glowing skin, natural makeup with glossy pink lips, soft blush, subtle highlights. Light brown hair styled in a low, neat updo with a few loose strands. Outfit & accessories: elegant minimalist beige-white strapless evening dress, Louis Vuitton necklace, diamond ring, luxury fashion jewelry. Photography style: close-up to half-body fashion portrait, Vogue editorial aesthetic, cinematic professional studio lighting, soft HDR background, shallow depth of field, realistic skin texture, ultra-detailed, 8K quality. Camera & lens look: professional DSLR look, 85mm lens feel, f/1.8 aperture, crisp focus with smooth background bokeh. Composition: Vogue magazine layout with large bold logo at the top, editorial fashion cover framing, clean and elegant design. Mood & vibe: playful yet luxurious, high-fashion beauty editorial, realistic, not AI-looking, photographed by a professional fashion photographer.
Remix

A close-up wildlife portrait of a majestic stag standing still in a snowy forest during active snowfall. The deer faces the camera directly, with large symmetrical antlers coated in fresh snow, creating a striking and powerful composition. Its fur is a rich warm brown, lightly dusted with snowflakes, contrasting against the soft white foreground and cool gray-blue background. The background features blurred winter trees with shallow depth of field, producing a dreamy, atmospheric bokeh effect. Lighting is soft and diffused, typical of overcast winter conditions, emphasizing fine details in the fur, antlers, and snow texture. The mood is calm, serene, and slightly dramatic, evoking wilderness, nature, and seasonal beauty. Shot at eye level with a centered composition, high realism, no text, ideal for commercial wildlife, winter, or holiday-themed stock imagery.
Remix

a visually striking arrangement of luxury makeup products with brand name Kylie Cosmetics displayed against a warm, monochromatic background in shades of peach, coral, and rose gold. The setup includes lipsticks, foundation or serum bottles, a compact blush, and cream containers — all housed in sleek black and metallic coral packaging. The products are artfully placed among geometric blocks and curved shapes in matching tones, creating a modern, sculptural composition. Soft, diffused lighting enhances the smooth textures and rich colors, producing a polished, high-end aesthetic. The overall mood is elegant and contemporary, evoking themes of beauty, sophistication, and design harmony

beauty catalog

Remix

Browse the full gallery

Why teams choose Qwen Image

Choose Qwen Image when the image has to carry a lot of text, since complex text rendering is its documented strength. Its custom sizes reach 2048 pixels and ratios up to 4:1. For editing, use Qwen Image Edit Plus. For text-heavy designs that need larger output or reference images, compare GPT Image 2.5 Sunburst or Ideogram.

Capabilities

What Qwen Image can do

The capabilities that set Qwen Image apart and earn its place in a brief

Complex Text Rendering

fal highlights significant advances in complex text rendering, the main reason to use Qwen Image for posters, menus, and graphics with real copy.

Nineteen Presets

Choose from presets including 1:1, 4:5, 3:4, 2:3, 9:16, 16:9, and wide 7:3 shapes.

Custom Sizes to 2048 Pixels

Set your own width and height in multiples of 16, up to 2048 pixels on the long edge, about four megapixels in total, and ratios up to 4:1.

Guidance and Steps Control

Adjust guidance scale and the number of inference steps to trade prompt adherence and detail against speed. fal's defaults are 2.5 guidance and 30 steps.

Negative Prompt and Seed

List what to avoid with a negative prompt, and set a seed to reproduce a result. The same seed and prompt return the same image on the same model version.

Separate Edit Model

This model is text-to-image only in Masonry. For edits and multi-image work, Qwen Image Edit Plus takes up to four input images.

Use cases

Where teams reach for Qwen Image

Posters and flyers with headlines and body copy
Menus, price boards, and signage mockups
Infographics and explainer graphics
Social graphics with several lines of text
Packaging and label concepts
Book, podcast, and event covers

Explore related categories

Browse adjacent categories and creative directions teams are exploring

FAQ

Frequently asked questions

What teams need to know about creating with Qwen Image in Masonry

What is Qwen Image?

Qwen Image is an image generation foundation model in the Qwen series. fal describes it as achieving significant advances in complex text rendering and precise image editing. Masonry runs it through fal as a text-to-image model.

Is Qwen Image good at text in images?

Complex text rendering is its headline strength according to fal. Quote every string in the prompt and proofread each result before it ships.

Can Qwen Image edit images in Masonry?

Not this model. Qwen Image is text-to-image only in Masonry. Use Qwen Image Edit Plus, which accepts up to four input images, for edits.

What sizes does Qwen Image support?

Nineteen presets, or custom sizes in multiples of 16 up to 2048 pixels on the long edge and about four megapixels, with ratios up to 4:1.

What do guidance scale and steps do in Qwen Image?

Guidance scale controls how closely the image follows the prompt, and inference steps trade detail against speed. fal's defaults are 2.5 and 30.

Can I reproduce a Qwen Image result?

Yes. Set a seed. The same seed and prompt on the same model version produce the same image.

How much does Qwen Image cost in Masonry?

Masonry bills in credits by output size, and the editor shows the exact cost before you generate.

Can Qwen Image output be used commercially?

fal marks the endpoint for commercial use. Review the current fal and Qwen terms for your project.

How does my team use Qwen Image in Masonry?

Open a Masonry canvas, pick Qwen Image from the model selector, and describe the image you need: a product shot, an ad creative, a social post. Masonry generates it, then you refine, edit, and combine Qwen Image with other models in one workspace.

Is Qwen Image free to try?

New Masonry accounts get 50 free credits to try GPT Image 2.5 Flare. Qwen Image is included in every paid plan, and the editor shows the exact credit cost before you generate.

How do I write good prompts for Qwen Image?

Put every exact string in quotation marks and say where it goes, from the headline down to small labels. Describe the layout as well as the content, for example "headline at the top, three rows of menu items below". Proofread each result, since any model can still miss a character. See the prompt gallery on this page for real Qwen Image prompts you can copy and adapt.

Who makes Qwen Image?

Qwen Image is built by Qwen. Inside Masonry it runs alongside 50+ image and video models, so your team can pick the right one for each brief without switching tools.

Can I see examples made with Qwen Image?

Yes, the prompt gallery on this page shows real images teams have generated with Qwen Image in Masonry, each paired with the exact prompt you can copy and adapt for your own brand.

Start creating with Qwen Image

Generate, edit, and compare across 50+ models in one workspace.

Create with Qwen Image

Guides for Qwen Image

Prompt walkthroughs and examples from the Masonry blog

Best AI Image Model for Text Rendering (2026): 7 Models Tested

Explore more AI models

Compare Qwen Image with other models teams run in Masonry

Qwen Image Edit PlusQwen · Image Bria Embed ProductBria · Image Bria Fibo 2.0Bria · Image Crystal UpscalerPhilz1337x · Image FLUX 1.1 ProBlack Forest Labs · Image FLUX 3 ImageBlack Forest Labs · Image