Image-to-image on Z-Image Base, Alibaba Tongyi-MAI's 6-billion-parameter model, with up to three of your own LoRAs and a strength control. One source image in, the same aspect ratio out at a 1k or 1.5k long side, and no filter on prompts, weights or results.
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.
Outputarchery-forest-to-ink A photo in, an illustration LoRA at 1 and strength 0.6: the bow, the draw and the light through the pines stay where they were, redrawn in the LoRA style.
- 632
- 0.6
- 1k
Outputslot-canyon-to-ink A wide 16:9 photo at the 1.5k tier and strength 0.65: the couple, the curve of the rock and the shaft of light are kept, redrawn in ink and colour.
- 621
- 0.65
- 1.5k
Outputcourtyard-noon-to-ink The same LoRA at 0.6 on a 4:3 portrait. The pose, the fountain and the leaf shadows carry over; skin and wall take the illustrated look.
- 612
- 0.6
- 1k
This example starts at $0.014 per image. The Playground updates the estimate when you change the settings.