MODEL LINEAGE
中文
All families

FAMILY / ALIBABA CLOUD

Qwen-Image

Qwen’s image line focused on Chinese text, complex layouts, editing, and realistic detail.

First model
2025
Models
6
Latest dated version
Qwen-Image-2.1-Turbo

01 / RELEASE SEQUENCE

Family release sequence

Compare versions →
  1. 2025-08-04Qwen-ImageImage generation
  2. 2025-08-18Qwen-Image-EditImage generation
  3. 2026-02-10Qwen-Image 2.0Image generation · Multimodal
  4. 2026-07-21Qwen-Image 3.0Image generation · Multimodal
  5. 2026-10-02Qwen-Image-2.1-ProImage generation · Multimodal
  6. 2026-10-09Qwen-Image-2.1-TurboImage generation · Multimodal
6 versions
What changed ↓

02 / GENERATIONS

What changed

01

Qwen-Image

A 20B MMDiT image foundation model focused on complex Chinese/English text rendering.

02

Qwen-Image-Edit

An image-editing extension of 20B Qwen-Image for semantic, appearance, and bilingual text changes.

03

Qwen-Image 2.0

Unified generation and editing with 1K-token complex prompts, native 2K, and more realistic detail.

04

Qwen-Image 3.0

Targets directly usable visual content with 4.5K-token prompts, 10px text, multilingual rendering, and complex layouts.

05

Qwen-Image-2.1-Pro

An image-generation and editing API model listed by QwenCloud on October 2, 2026. Its visual generation component is described as a 7B, 32-layer single-stream DiT, with native transparency and up to 10 reference images.

06

Qwen-Image-2.1-Turbo

It adds a distinct fast-generation checkpoint to Qwen-Image 2.1 and makes its weights public, expanding deployment choices for the image line rather than merely adding a serving-speed tier.