Image model · free · no sign-up

Qwen-Image
prompt generator.

Qwen-Image handles long, detailed natural-language prompts and supports a separate negative prompt, which makes it easy to steer away from unwanted artifacts.

The generator writes a subject-first description followed by scene and lighting, and outputs your negatives as their own field.

Example outputNeon cyberpunk night
Cinematic film still, cyberpunk, photorealistic. Waist-up medium shot, horizontal 16:9 frame. The subject is an original fictional adult man, 30s in appearance. Wearing a leather jacket outfit. Set in a city street, night, rainy, wet reflections, mood mysterious, edgy. Neon colored lighting, color temperature mixed warm and cool, volumetric light rays, reflections on surfaces. Shot on a cinema camera (ARRI Alexa), 35mm lens. Dominant palette of teal, neon purple, black, teal and orange cinematic grade.
75 wordsaspect_ratio: 16:9+ negative prompt

How to write better Qwen-Image prompts.

01

Order: subject → scene → light

Describing the subject first, then the setting, then lighting and camera keeps the result coherent.

02

Use the negative field

Add realism-related negatives such as “plastic skin” or “CGI” for photographic results; the generator suggests them automatically.

03

Edits need Qwen-Image-Edit

For changing an existing photo, use the edit model and describe only the change you want.

Qwen-Image examples.

All examples →

Qwen-Image FAQ.

Can Qwen-Image render text in images?+

Qwen-Image is known for strong text rendering. Add the exact text in the notes field and describe where it should appear.

JSON or text for Qwen?+

Plain text is the default; you can switch to JSON in the builder if your workflow prefers it.