Qwen Image 2.1 LoRA text-to-image renders a prompt of up to 5,000 characters with up to three of your own LoRA weights, each at a strength from 0 to 4. Choose 1k, 1.5k or 2k in fifteen aspect ratios, with no review of the weights.
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.
Outputwindow-seat-sweater-lora A storybook-anime LoRA pointed at a cosy scene: a grown woman on a rainy window seat in an oversized sweater. The prompt spells out mature features (a long face, defined cheekbones, a calm gaze) because anime LoRAs drift young unless you say otherwise.
- 1k
- 3:4
Outputwatercolor-lace-lora A watercolour-anime LoRA at 4:5, 2k. Transparent washes and pale paper texture come out of the weights rather than a post-process, and the single warm lamp leaves most of the figure in deep wash.
- 2k
- 4:5
Outputtwo-weights-stacked Two LoRAs in one request: watercolour at 0.9 and storybook at 0.45. Each weight keeps its own strength rather than being averaged, which is what stacking is for — the dominant style sets the medium and the second one shifts the drawing underneath it.
- 2k
- 3:4
This example starts at $0.03 per image. The Playground updates the estimate when you change the settings.