Qwen-Image 2.1

Alibaba Qwen's downloadable picture model that makes and edits images, including transparent layers, cut-outs and edits marked with circles or masks, from up to 10 reference pictures. Unlike earlier Qwen-Image, its licence is research-only: no commercial use.

Go to Qwen-Image 2.1’s website

Free to try?Yes

Can I sell what I make?No

Open or closedDownloadable, with conditions

Skill neededTechnical

The facts, with sources

Open or closed: Downloadable, with conditions
You can download and run it, but the licence limits use
Weights downloadable; licence is not open source.
source · checked 7 Nov 2026 · checked on the maker's own page
Licence: Qwen Research License Agreement (Non-commercial only)
source · checked 7 Nov 2026 · checked on the maker's own page
Can I sell what I make?: No
s.2(b): no commercial use without a separate licence; 'Non-Commercial' means research or evaluation only. Outputs not explicitly addressed.
source · checked 7 Nov 2026 · checked on the maker's own page
Cost: Free option: Free to download for research; you pay for your own hardware
Plans below.
How you use it: On your own computer, In your browser
Diffusers, Draw Things, DiffusionBee; demo Space on Hugging Face; ModelScope.
source · checked 7 Nov 2026 · checked on the maker's own page
Skill needed: Technical
source · checked 7 Nov 2026 · checked, but the page was unclear or partial
Made by: Hangzhou Tongyi Laboratory Technology Co., Ltd. (Qwen) (CN)
Licensor named in the licence.
source · checked 7 Nov 2026 · checked on the maker's own page
Status: Available
Release date not stated on the card; found on Hugging Face in autumn 2026.
source · checked 7 Nov 2026 · checked, but the page was unclear or partial

What you can make with it

A picture, from a description (main use)
A picture, by changing a photo I have
A picture, remove a background
A picture, the same character or style across many images

text to imageimage to image

Transparent RGBA output and layer edits, subject extraction, up to 10 references, mask or annotation edits.

source · checked 7 Nov 2026 · checked on the maker's own page

Plans and prices

No paid plans listed.

source · checked 7 Nov 2026 · checked on the maker's own page

Where you can run it

Hugging Face

Other options for “A picture, from a description”

Adobe Express, Adobe Firefly, Adobe Photoshop, Akool, Artbreeder, Bria, Bria Fibo 2.0, Canva AI (Magic Studio), ChatGPT Images, Civitai, Clipdrop, ComfyUI, Creatify, DeeVid AI, DiffusionBee, DomoAI, Draw Things, Dreamina, Dzine, fal, Filmora, FlexClip, FLORA, FLUX 3

About this entry. Facts last checked 7 Nov 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.

Spot an error? Tell us, with a link to the source. How corrections work