LLM ReferenceLLM Reference

Qwen Image

qwen-image

Open SourceMultimodal

About

Qwen Image by Alibaba. A 20B Multimodal Diffusion Transformer (MMDiT) for text-to-image generation, achieving commercial-grade Chinese and English text rendering. Open source under Apache 2.0 on HuggingFace (Qwen/Qwen-Image). Part of Alibaba's Qwen/Tongyi AI ecosystem. Available via Fal API (fal-ai/qwen-image).

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode ExecutionPrompt CachingBatch APIAudioFine-tuning

Rankings

Specifications

Released2025-08-31
Parameters20B
Architecturemmdit
Specializationimage-generation
LicenseApache 2.0

Created by

AI research institute of Alibaba Group.

Hangzhou, Zhejiang, China
Founded 2017
Website