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
Specifications
FamilyQwen Image
Released2025-08-31
Parameters20B
Architecturemmdit
Specializationimage-generation
LicenseApache 2.0