Qwen-Image-2.1 ComfyUI Native Workflow Example

Qwen-Image-2.1 is the latest open-weight release in the Qwen-Image series from Alibaba’s Qwen team. A single model covers both text-to-image generation and instruction-based image editing, with native 2K output, professional typography, and an alpha channel for transparent backgrounds. Key Features:

Generation and editing in one model: the same weights serve text-to-image prompts and editing instructions, so a workflow does not need to swap checkpoints
Native 2K output: generate at up to 2048x2048 directly instead of upscaling a smaller result
Professional typography: dense small text and complex layouts hold up, for infographics, slides, UI mockups, posters, and packaging designs
Alpha channel support: the VAE carries four channels, so transparent-background images can be generated and edited directly instead of being cut out afterwards
Multi-image editing: reference images are spliced into the text encoder in slot order. The node exposes image_1 through image_16 slots, and the prompt addresses them by index, for example image_1 is written as <image1>
Localized edits: describe the object or region to change and the rest of the image is preserved

Related Links:

Qwen-Image-2.1 workflow

Local users
Cloud users

Make sure your ComfyUI is updated.

Workflows in this guide can be found in the Workflow Templates. If you can’t find them in the template, your ComfyUI may be outdated.If nodes are missing when loading a workflow, possible reasons:

You are not using the latest ComfyUI version (Nightly version)
Some nodes failed to import at startup

Qwen Image 2.1 Text to Image

Generate an image from a text prompt at the aspect ratio and megapixel target you select. Qwen-Image-2.1 text to image workflow preview

Download Workflow

Download JSON or search “Qwen-Image-2.1” in Template Library

Run on Comfy Cloud

Run ComfyUI online with zero setup

Example output Qwen-Image-2.1 text to image example output

Qwen Image 2.1 Image Edit

Edit an image with an instruction. Add reference images when the edit needs content that is not in the source image, such as putting a garment from a second photo onto the person in the first. Qwen-Image-2.1 image edit workflow preview

Download Workflow

Download JSON or search “Qwen-Image-2.1” in Template Library

Run on Comfy Cloud

Run ComfyUI online with zero setup

Input materials Upload these files to the matching LoadImage nodes:

portrait_model_denim.png

LoadImage node 470 · portrait_model_denim.png

clothing_light_blue_denim_shirt.png

LoadImage node 475 · clothing_light_blue_denim_shirt.png

Example output

Model links

The two workflows load the same files. Both templates use the int8 version of the diffusion model by default. text_encoders

qwen3vl_8b_bf16.safetensors

diffusion_models

qwen_image_2.1_int8_convrot.safetensors (loaded by the templates, lower memory)
qwen_image_2.1_bf16.safetensors (full precision, needs more memory)

vae

qwen_image_2.1_vae_bf16.safetensors

Model Storage Location

📂 ComfyUI/
├── 📂 models/
│   ├── 📂 text_encoders/
│   │      └── qwen3vl_8b_bf16.safetensors
│   ├── 📂 diffusion_models/
│   │      ├── qwen_image_2.1_int8_convrot.safetensors
│   │      └── qwen_image_2.1_bf16.safetensors
│   └── 📂 vae/
│          └── qwen_image_2.1_vae_bf16.safetensors

Workflow settings

Sampler settings

Both templates sample with steps 25, cfg 1, the euler sampler, and the simple scheduler. The text to image workflow keeps the seed fixed, and the image edit workflow randomizes it.

Resolution

Text to image: the Resolution Selector node sets the aspect ratio (1:1, 16:9, 9:16, 3:2, 2:3, 4:3, 3:4, 21:9) and a megapixel target, where 1.0 MP is about 1024x1024. The template defaults to 1:1 at 1 MP. Qwen-Image-2.1 generates natively at 2K, so set the target to about 4.0 MP for a 2048x2048 square output. Image edit: with custom_size off, which is the template default, the output follows image_1’s aspect ratio, scaled to about resolution x resolution pixels (default 1024, rounded to multiples of 32). That is not the original pixel size of image_1. Set resolution to 0 to keep each reference image at its own size, rounded to a multiple of 32. Turn custom_size on to use the Resolution Selector canvas instead, and keep it close to the resized image_1 size, otherwise the edit can shift.

Prompting for image edit

Reference images are spliced into the text encoder in slot order, and the prompt addresses each one by index. The template prompt is a good example of the pattern:

Keep the character and pose in <image1> unchanged, put this light blue denim shirt from <image2> on the character, preserve the original facial features, hair, body shape and pose

KV cache

The image edit workflow includes the Qwen Image 2.1 Cache node, which sets where the cached text and reference prefix lives:

Setting	Values	Effect
`device`	`auto` (default), `gpu`, `cpu`, `off`	`auto` uses spare VRAM, then RAM. `cpu` is prefetched behind compute and costs little speed. `off` recomputes the prefix every step, which is slower but rules the cache out when debugging
`dtype`	`default` (default), `int8`, `int4`	Storage precision. `default` is lossless, `int8` halves the cache at about bf16 accuracy, `int4` quarters it but roughly doubles the per-step error

Get Started

Agent Tools

Basic Concepts

Interface Guide

Tutorials

Comfy Cloud Nodes

Partner Nodes

Qwen-Image-2.1 ComfyUI Native Workflow Example