Qwen-Image 2.1 in Locally Uncensored

Qwen-Image 2.1 is the image model Alibaba Qwen published on 20 September 2026, and the first in its series where one set of weights both generates a picture from a prompt and edits a reference image. Locally Uncensored 3.0.1 carries it on Windows and Linux as a Model Manager bundle called Qwen-Image 2.1 (Generate and Edit): three files, 16.1 GB, straight into the right ComfyUI folders. After that it is an entry in the Image lane picker and the Edit lane picker, like any other local image model.

It needs ComfyUI 0.37.0 or newer. If the node is missing, the app says so in one sentence and points at the update button.

Three ways in

How to Run Qwen-Image 2.1 Locally

The step by step version: the three files and their sizes, the memory guide, the ComfyUI version check, the Image lane, the maskless Edit lane, and what this release does not do.

TutorialSeptember 22, 2026

Qwen-Image 2.1 Explained

7B where the first Qwen-Image had 20B, a VAE with an alpha channel, ten reference images in a pass, no separate edit model, and a license that is no longer Apache 2.0.

Model GuideSeptember 22, 2026

Handbook: Qwen-Image 2.1 in the Create chapter

The short reference version, in the chapter that covers every lane: where the bundle is, which picker it appears in, what the Edit lane takes, and the message you get on an older ComfyUI.

Handbook

The license, before you download 16 GB

Research and evaluation, not commercial use

Qwen-Image 2.1 is published under the Qwen Research License, not Apache 2.0. It allows research and evaluation, and commercial use needs a separate license from Alibaba Qwen. The Model Manager names this in the bundle description before the download starts. If you need Apache 2.0 terms, Qwen-Image 2512 and Qwen-Image-Edit 2511 remain under Apache 2.0.

What this release does and does not do

It generates from a prompt with a negative prompt, at the defaults from the official template: 25 steps, CFG 1, euler, simple, 1024x1024, with the usual Advanced settings for Steps, CFG, Width, Height, Seed and Batch. It edits from one reference image plus a prompt, with no mask, and the output follows that reference image.

Not in this release: several reference images at once, RGBA output, masks with this model, a prompt enhancer and the KV cache node. There is also no Lightning or Turbo LoRA for 2.1, and the older ones do not fit the new architecture.

Locally Uncensored is free and AGPL-3.0, Windows and Linux. New here? The handbook takes you from installer to first image.