Jib Mix Qwen LoRA text-to-image runs J1B's photoreal merge of Alibaba's 20B Qwen-Image with up to three of your own LoRAs for Qwen-Image or Qwen-Image-2512 at strengths from 0 to 4. Nine aspect ratios at up to 1536 pixels on the long side, 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.
Outputbilliards-portrait-lora A portrait LoRA at its intended scale of 1 with a lighting brief: one green-shaded lamp, haze, key light on the face, rim light along the shoulder.
- 501
- 2:3
Outputcar-wash-flash A phone-camera LoRA at 1, with "amateur phone photo with on-camera flash" written into the prompt to match it.
- 515
- 3:4
Outputice-rink-two-loras Two LoRAs stacked: the camera look at 0.8 and the portrait finish at 0.6. Lower the second one if skin starts to look retouched.
- 529
- 4:3
Outputbowling-alley-flash A darker flash-photo LoRA at 1 on a night interior; the hard flash on the face and the falloff into the lanes come from the prompt and the weights together.
- 539
- 9:16
This example starts at $0.03 per image. The Playground updates the estimate when you change the settings.