Qwen Image 1.0 LoRA text-to-image runs Alibaba's original 20B Qwen-Image with up to three of your own LoRAs at strengths from 0 to 4. Nine aspect ratios at up to 1536 pixels on the long side, legible lettering, one flat price per image and 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.
Outputferry-cabin-flat-color A flat-colour LoRA at 1 with its trigger words first. Without the LoRA, the same prompt and seed gave a photograph.
- 41
- 3:4
Outputstorm-keeper-room No LoRA: the base model alone, with the light written out as two sources, a caged bulb in warm amber against cold storm blue.
- 11
- 4:3
Outputferry-deck-1947 A vintage magazine LoRA at 0.9 with its trigger words first. The life-ring lettering came out exactly as quoted in the prompt.
- 22
- 2:3
Outputlighthouse-storm-pixel A pixel-art LoRA trained for Qwen-Image-2512, loaded on this base at 1. Start the prompt with "Pixel Art" to match the LoRA.
- 32
- 16:9
This example starts at $0.03 per image. The Playground updates the estimate when you change the settings.