Qwen Image 3.0 Pro image editing edits or merges one to three reference images under a written instruction, including retyping a cover line without redrawing the picture. Output is one image at 1k or 2k in eight aspect ratios.
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.
Outputwardrobe-and-set Two references with an explicit role for each: the first supplies face, hair and pose, the second the room and its light, while the kimono is described in the prompt. You provide both images; nothing here is fetched from a sample library.
- 2k
Outputretype-the-tagline This one starts from the advertising frame the same model produced and changes exactly one thing, the line of type. The instruction spends more words on what must not move - pose, suspended mist, lighting, grain - than on the new wording, because that is the whole demonstration: retyping a headline in place rather than regenerating a picture that merely looks similar. Set the two frames side by side and everything outside the type block should be unchanged.
- 2k
- 3:4
Outputcover-line-swap A single-reference text edit with both strings quoted and the masthead explicitly protected. Supply your own cover frame — the image_urls value is a placeholder, not a hosted sample.
- 2k
- 3:4
Outputwatch-into-print-ad The instruction protects the product completely — watch, ice, stone and light named untouchable — and only adds two quoted lines of type: a serif headline in the empty sky, small caps along the bottom. `aspect_ratio` is 3:4 and `resolution` 1k, a vertical frame that already leaves room above the watch.
- 1k
- 3:4
This example starts at $0.04 per image. The Playground updates the estimate when you change the settings.