Image · Released Sep 2026
Alibaba Qwen Image 2.1
Alibaba Qwen's open 7B image model, running fully offline on your own machine. It generates from a prompt and edits images you attach, renders long passages of text inside the image from a far smaller model than the 20B original, and needs no API key or network once the weights are downloaded. Released under the Qwen Research License, which covers research and evaluation use only.
Alibaba's Qwen Image 2.1 is an open-weight image-generation model. It generates images from a text prompt. It runs entirely on your own hardware through GGML: no API key and no per-use fees.
Supported OS
macOSWindowsLinux
Minimum machine configuration
Local image generation · 32 GB+ RAM · 18 GB free disk · GPU strongly recommended
Download size · 14 GB
Specs
- Released
- this month (Sep 2026)
- Pricing
- Free, runs on your hardware
About the creator
Alibaba
Alibaba's Tongyi research group publishes the Wan video models and the Qwen family of language models.
www.alibabacloud.com ↗More from Alibaba
Wan 2.7
ImageCloud
High-quality diffusion model for detailed, prompt-faithful image generation.
Wan 2.7 Pro
ImageCloud
Alibaba's professional-grade Wan 2.7 image model for higher-fidelity, prompt-faithful generation and editing.
Qwen Image 3
ImageCloud
Alibaba Qwen's unified image generation and editing model, balancing visual quality, layout fidelity, and speed.
Qwen Image 3 Pro
ImageCloud
Alibaba Qwen's professional-grade image model for dense layouts, small-text rendering, and multilingual visual design.
HappyHorse 1.1
VideoCloud
Alibaba's video model with three modes — text-to-video, image animation, and reference-to-video from up to 9 images.
Wan 3.0
VideoCloud
Alibaba's all-in-one Wan 3.0 video model, generating clips of up to 30 seconds with native audio from text, frame images, or a deep bench of reference media.