--- title: "Qwen Image Prompts: 6 Tested Examples | Made" description: "Copy 6 tested Qwen Image prompts with the actual outputs they produced in Made, plus how to write your own: settings, strengths, and pitfalls." url: https://www.made.app/models/qwen-image/prompts --- [Models](https://www.made.app/models) / [Qwen Image](https://www.made.app/models/qwen-image) / Prompts # Qwen Image prompts that actually ran Every prompt below was generated with Qwen Image in Made, and the output next to it is what came back — not a curated stock image. Copy a prompt as a starting point, then use the guide underneath to adapt it. [Try Qwen Image](https://www.made.app/models/qwen-image) [Qwen Image pricing: 3 credits / image](https://www.made.app/price-sheet/qwen-image) Original results ## Qwen Image prompts and their outputs These examples use media produced for Made. Prompts are included when the production record allows them. ![neon-lit alley in the rain with a cyclist generated with Qwen Image in Made](https://www.made.app/images/models/qwen-image/rain-alley.jpg) ### Qwen Image: Rainy alley “Neon-lit alley in the rain, reflections on wet pavement, a lone cyclist with an umbrella passing through. 35mm film still, soft natural light, muted earth tones with one cyan accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.” ![noodle shop facade with a LATE NOODLE sign generated with Qwen Image in Made](https://www.made.app/images/models/qwen-image/noodle-shop.jpg) ### Qwen Image: Neon sign “Tiny noodle shop facade at night with a glowing sign reading exactly "LATE NOODLE" and red paper lanterns, steam from the doorway. Clean editorial design, muted earth tones with one red accent, subtle paper texture, sharp legible type, no other words or logos.” ![tea tins labeled Jasmine, Oolong and Sencha generated with Qwen Image in Made](https://www.made.app/images/models/qwen-image/tea-tins.jpg) ### Qwen Image: Tea tin labels “Three tea tins standing in a row on a wooden shelf against a plain wall, front view, each with a wide cream label printed with one word in large serif capitals: "JASMINE", "OOLONG" and "SENCHA". Clean editorial design, muted earth tones with one jade accent, subtle paper texture, sharp legible type, no other words or logos.” ![night market fruit stall under hanging bulbs generated with Qwen Image in Made](https://www.made.app/images/models/qwen-image/fruit-stall.jpg) ### Qwen Image: Night market “Night market fruit stall lit by hanging bulbs, piles of dragon fruit, lychee and mangosteen. 35mm film still, soft natural light, muted earth tones with one magenta accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.” ![calligraphy brushes and ink stone on a desk generated with Qwen Image in Made](https://www.made.app/images/models/qwen-image/calligraphy-desk.jpg) ### Qwen Image: Calligraphy desk “Calligraphy brushes, an ink stone and a blank sheet of rice paper with no characters or writing on a dark wooden desk in morning light. 35mm film still, soft natural light, muted earth tones with one vermilion accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.” ![bookshop window with a hand-painted sign generated with Qwen Image in Made](https://www.made.app/images/models/qwen-image/bookshop-window.jpg) ### Qwen Image: Bookshop window “Second-hand bookshop window with stacked books and a hand-painted sign reading exactly "USED BOOKS · OPEN LATE". Clean editorial design, muted earth tones with one bottle green accent, subtle paper texture, sharp legible type, no other words or logos.” ## How to write a Qwen Image prompt 1. **Lead with the subject** Describe the main subject, then add composition, materials, lighting, and style in concrete language. 2. **Quote exact display text** For posters, place the short requested wording in quotes and explicitly reject extra copy. 3. **Select the output shape** Choose the aspect ratio and output format that match the final placement. 4. **Review fine details** Inspect small text, hands, faces, and unintended marks before using the image. ## What Qwen Image responds well to ### Prompt for these jobs - Posters and graphics with a short headline - Structured product and interior compositions - Fast prompt-to-image concept exploration - Square, portrait, and landscape content in efficient WebP output ### Check the output for - It may invent small decorative copy or logo-like marks even when the main requested headline is correct. - Photorealistic faces and hands should be reviewed closely, especially in busy scenes or small crops. Iteration is cheap here: Qwen Image costs 3 credits / image, so rewriting a prompt and rerunning it is a normal part of the workflow, not a budget decision. See the [full Qwen Image pricing breakdown](https://www.made.app/price-sheet/qwen-image). Questions, answered ## Qwen Image prompts FAQ Need a specific answer? [Contact support](mailto:support@made.app) ### Why use Qwen Image in Made? It is a useful image-generation option when prompt structure and visible headline text matter, while still covering general product, portrait, interior, and illustration work. ### Is Qwen Image good at typography? It rendered the main benchmark headline correctly, but also introduced small decorative copy. Treat prominent text as a strength, not a guarantee of press-ready typesetting. ### Can Qwen Image use a source image? The verified provider contract includes an optional image input, and Made’s model configuration records that field for the production workflow. ### Which output format is the default? Made currently defaults to WebP and can expose JPG or PNG through the configured output-format control. ### Does it support portrait images? Yes. Made’s configured options include 3:4, 2:3, and 9:16 portrait ratios. ### When is another model preferable? Use Flux Kontext for precise source-image editing, or compare Flux 1.1 Pro when general photorealistic generation matters more than display text. More tested prompts across all models live in the [prompt library](https://www.made.app/prompts), and the full Qwen Image capability rundown is on the [model page](https://www.made.app/models/qwen-image). --- Markdown version of https://www.made.app/models/qwen-image/prompts. Every public Made page has one at its URL plus .md (https://www.made.app/models/qwen-image/prompts.md). Site summary for AI assistants: https://www.made.app/llms.txt