---
title: "Qwen-Image-2.1 ComfyUI Native Workflow Example"
description: "Run Qwen-Image-2.1 in ComfyUI: one model for image generation and editing, native 2K output, professional typography, and alpha channel support."
sidebarTitle: "Qwen-Image-2.1"
---

import UpdateReminder from '/snippets/tutorials/update-reminder.mdx'

**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**:
- [GitHub Repository](https://github.com/QwenLM/Qwen-Image)
- [Hugging Face (Comfy-Org/Qwen-Image-2.1)](https://huggingface.co/Comfy-Org/Qwen-Image-2.1)
- [Qwen Image 2.1 on Comfy](https://comfy.org/qwen-image-2.1/)

## Qwen-Image-2.1 workflow

<UpdateReminder />

### Qwen Image 2.1 Text to Image {#image_qwen_image_2_1_t2i}

Generate an image from a text prompt at the aspect ratio and megapixel target you select.

<img src="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/main/templates/image_qwen_image_2_1_t2i-1.webp" alt="Qwen-Image-2.1 text to image workflow preview" />

<CardGroup cols={2}>
  <Card title="Download Workflow" icon="download" href="https://github.com/Comfy-Org/workflow_templates/blob/main/templates/image_qwen_image_2_1_t2i.json">
    Download JSON or search "Qwen-Image-2.1" in Template Library
  </Card>
  <Card title="Run on Comfy Cloud" icon="cloud" href="https://cloud.comfy.org/?template=image_qwen_image_2_1_t2i&utm_source=docs&utm_medium=referral&utm_campaign=qwen-image-2-1">
    Run ComfyUI online with zero setup
  </Card>
</CardGroup>

**Example output**

![Qwen-Image-2.1 text to image example output](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/main/output/Qwen_image_2.1.png)

### Qwen Image 2.1 Image Edit {#image_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.

<img src="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/main/templates/image_qwen_image_2_1_image_edit-1.webp" alt="Qwen-Image-2.1 image edit workflow preview" />

<CardGroup cols={2}>
  <Card title="Download Workflow" icon="download" href="https://github.com/Comfy-Org/workflow_templates/blob/main/templates/image_qwen_image_2_1_image_edit.json">
    Download JSON or search "Qwen-Image-2.1" in Template Library
  </Card>
  <Card title="Run on Comfy Cloud" icon="cloud" href="https://cloud.comfy.org/?template=image_qwen_image_2_1_image_edit&utm_source=docs&utm_medium=referral&utm_campaign=qwen-image-2-1">
    Run ComfyUI online with zero setup
  </Card>
</CardGroup>

**Input materials**

Upload these files to the matching `LoadImage` nodes:

<CardGroup cols={2}>
  <Card title="portrait_model_denim.png" icon="image" href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/main/input/portrait_model_denim.png">
    `LoadImage` node 470 · `portrait_model_denim.png`
  </Card>
  <Card title="clothing_light_blue_denim_shirt.png" icon="image" href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/main/input/clothing_light_blue_denim_shirt.png">
    `LoadImage` node 475 · `clothing_light_blue_denim_shirt.png`
  </Card>
</CardGroup>

**Example output**

<div style={{display: 'grid', gridTemplateColumns: 'repeat(2, minmax(0, 1fr))', gap: '1rem', alignItems: 'start'}}>
  <img src="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/main/input/portrait_model_denim.png" alt="Input image" style={{width: '100%', height: 'auto', objectFit: 'contain'}} />
  <img src="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/main/output/image_qwen_image_2_1_image_edit.png" alt="Qwen-Image-2.1 image edit example output" style={{width: '100%', height: 'auto', objectFit: 'contain'}} />
</div>

### Remove Background: Qwen Image 2.1 {#image_qwen_image_2_1_background_removal}

Remove the background from a photo with an edit instruction. The workflow reuses the image edit subgraph with the prompt `Remove the background, and output a PNG image`, then compares the result with the original.

<img src="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/main/templates/image_qwen_image_2_1_background_removal-1.webp" alt="Qwen-Image-2.1 background removal workflow preview" />

<CardGroup cols={2}>
  <Card title="Download Workflow" icon="download" href="https://github.com/Comfy-Org/workflow_templates/blob/main/templates/image_qwen_image_2_1_background_removal.json">
    Download JSON or search "Qwen-Image-2.1" in Template Library
  </Card>
  <Card title="Run on Comfy Cloud" icon="cloud" href="https://cloud.comfy.org/?template=image_qwen_image_2_1_background_removal&utm_source=docs&utm_medium=referral&utm_campaign=qwen-image-2-1">
    Run ComfyUI online with zero setup
  </Card>
</CardGroup>

**Input materials**

Upload this file to the matching `LoadImage` node:

<Card title="angry_broccoli.png" icon="image" href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/main/input/angry_broccoli.png">
  `LoadImage` node 470 · `angry_broccoli.png`
</Card>

## Model links

The three workflows load the same files. All of them use the int8 versions of the diffusion model and the text encoder by default.

**text_encoders**

- [qwen3vl_8b_int8_convrot.safetensors](https://huggingface.co/Comfy-Org/Qwen-Image-2.1/blob/main/text_encoders/qwen3vl_8b_int8_convrot.safetensors) (loaded by the templates, lower memory)
- [qwen3vl_8b_bf16.safetensors](https://huggingface.co/Comfy-Org/Qwen-Image-2.1/blob/main/text_encoders/qwen3vl_8b_bf16.safetensors) (full precision, needs more memory)

**diffusion_models**

- [qwen_image_2.1_int8_convrot.safetensors](https://huggingface.co/Comfy-Org/Qwen-Image-2.1/blob/main/diffusion_models/qwen_image_2.1_int8_convrot.safetensors) (loaded by the templates, lower memory)
- [qwen_image_2.1_bf16.safetensors](https://huggingface.co/Comfy-Org/Qwen-Image-2.1/blob/main/diffusion_models/qwen_image_2.1_bf16.safetensors) (full precision, needs more memory)

**vae**

- [qwen_image_2.1_vae_bf16.safetensors](https://huggingface.co/Comfy-Org/Qwen-Image-2.1/blob/main/vae/qwen_image_2.1_vae_bf16.safetensors)

**Model Storage Location**

```
📂 ComfyUI/
├── 📂 models/
│   ├── 📂 text_encoders/
│   │      ├── qwen3vl_8b_int8_convrot.safetensors
│   │      └── 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

All three workflows sample with `steps` 25, `cfg` 1, the `euler` sampler, and the `simple` scheduler.

### Resolution

**Text to image**: the **Resolution Selector** node sets the aspect ratio and a megapixel target, where 1.0 MP is about 1024x1024. Qwen-Image-2.1 generates natively at 2K, so set the target to about 4.0 MP for a 2048x2048 square output.

**Image edit**: the output follows the first reference image's aspect ratio, scaled to about `resolution` x `resolution` pixels (default 1024). Set `resolution` to 0 to keep each reference image at its own size. Turn on `custom_size` to use the **Resolution Selector** canvas instead, and keep it close to the resized reference 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:

```
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 edit workflows include the **Qwen Image 2.1 Cache** node, which keeps the cached text and reference prefix in memory between sampling steps. The template defaults work for most setups.