Alibaba: qwen-image-edit-max-2026-01-16 API
qwen-image-edit-max-2026-01-16 is the latest flagship snapshot of the Tongyi Wanxiang image editing series. Building on a 20B-parameter diffusion architecture, this model introduces the newest "Visual Consistency Enhancement" algorithms, significantly improving ID preservation in complex editing tasks. It supports multi-image fusion, allowing for the precise migration of specific elements from reference images (e.g., human faces, specific products) into target scenes. This version features specialized optimizations for understanding physical laws, automatically generating matching environmental shadows and reflections when adding or removing objects. Furthermore, it maintains industry-leading capabilities in bilingual (Chinese/English) text modification and erasure, supporting ultra-clear outputs ranging from 1024px to 2048px.
- Context window: 2,048 tokens
- Input: text, image
- Output: image
- File input: Supported
- Released: 2026-01-15
- Knowledge cutoff: 2025-11-30
Frequently Asked Questions
What is the context window of qwen-image-edit-max-2026-01-16?
qwen-image-edit-max-2026-01-16 supports a context window of up to 2,048 tokens.
What is the knowledge cutoff of qwen-image-edit-max-2026-01-16?
The knowledge cutoff of qwen-image-edit-max-2026-01-16 is 2025-11-30.