Qwen Image 3.0 Edit
[Core Function] Qwen Image 3.0 Edit is the standard image-to-image editing model for instruction-based edits and multi-image fusion. [Strengths] It accepts 1-3 reference images plus an edit instruction, optional negative prompts, free-form output size (widthheight), intelligent prompt rewrite (direct mode), and 1-6 outputs while preserving subject identity. [Best For] Background replacement, outfit or style changes, multi-image fusion, and iterative retouching when Pro-tier quality is not required. [Limitations] Do NOT use this for pure text-to-image with no reference images (use Qwen Image 3.0 instead). Keep output total pixels within 512512 to 2048*2048. prompt_extend_mode only supports direct (agent is T2I-only). [Routing] Route here when the user provides reference image(s) and wants balanced Qwen 3.0 edit quality. Prefer Qwen Image 3.0 Pro Edit for higher quality edits.
Authorizations
API Key authentication. Format: Bearer YOUR_API_KEY.
Body
Image editing instruction (positive prompt)
1 - 4500"Change the background to a beach scene"
Input image URL array, supports 1-3 images
1 - 3 elementsNegative prompt describing unwanted content
500Number of output images
1 <= x <= 6Output image resolution as widthheight (e.g. 10241024). Optional; when omitted the model auto-selects. Total pixels should stay within 512512 to 20482048.
^\d+\*\d+$"1024*1024"
Whether to enable intelligent prompt rewriting. Default true (recommended). When enabled, the model rewrites the positive prompt using the mode specified by prompt_extend_mode; most effective for short or simple prompts.
Prompt rewrite mode when prompt_extend is true. Default direct. direct: Direct Prompt Enhancement (DPE), suitable for most scenarios (supported for I2I). agent (Agent Prompt Enhancement / APE) is text-to-image only and is rejected for image editing.
direct "direct"
Random seed for reproducibility
0 <= x <= 2147483647