Skip to main content

Qwen Image Edit 2509 LoRA edits and combines one to three source images with Alibaba's 20B Qwen-Image-Edit-2509 and up to three of your own LoRAs at strengths from 0 to 4. Faces stay consistent across sources, nine aspect ratios are optional, one flat price per image and no content filter.

From $0.03/image

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.

  • booth-strip-duoOutput
    booth-strip-duo

    Two studio portraits and a 9:21 frame. The prompt asked for four frames and the model drew three; both faces held in each one.

    • 91
    • 9:21
  • loft-next-sceneOutput
    loft-next-scene

    The next-scene LoRA at 1 with a prompt that starts with "Next Scene:" and names the new camera position.

    • 103
  • booth-animeOutput
    booth-anime

    A photo-to-anime LoRA at 1. Writing "a mature woman in her thirties with a grown-up face" kept the drawing true to the adult in the photo.

    • 113
  • darkroom-relightOutput
    darkroom-relight

    A relighting LoRA made for the original Qwen-Image-Edit, loaded on 2509 at 1: red safelight and a new prop, with his face and shirt kept.

    • 121

This example starts at $0.03 per image. The Playground updates the estimate when you change the settings.