Qwen Image 2.1 text-to-image is Alibaba's open-weight model: a 5,000-character prompt becomes one image at 1k, 1.5k or 2k in fifteen aspect ratios, as JPEG, PNG or WebP. Transparent backgrounds are available, and there is no content filter.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
Outputsilk-robe-doorway One figure, one light source, a lot of fabric: late-morning sun rakes across ivory silk, and the hand held high on the doorframe has to come out with five fingers in the right places. The prompt names her age, the pose, the light and the film look, and leaves the rest to the model.
- 1k
- 3:4
Outputkitchen-dawn-couple Two people touching is where image models usually slip: arms merge, hands multiply, faces drift apart. Here her arms rest around his neck and their foreheads meet while both of them laugh, under two lights of different colour: cool dawn from the window and one warm stove lamp.
- 2k
- 3:2
Outputlace-and-lamplight One hard lamp from the left and nothing else, at 4:5 on the 1.5k tier. Most of the frame drops to near black; what survives is the fabric texture where the lamp catches it. Low-key work is where a model either holds its texture at the edge of exposure or turns the shadow into mush.
- 1.5k
- 4:5
This example starts at $0.024 per image. The Playground updates the estimate when you change the settings.