Qwen-Image ComfyUI Native Workflow Example

• Excellent Multilingual Text Rendering: Supports high-precision text generation in multiple languages including English, Chinese, Korean, Japanese, maintaining font details and layout consistency
• Diverse Artistic Styles: From photorealistic scenes to impressionist paintings, from anime aesthetics to minimalist design, fluidly adapting to various creative prompts

• GitHub
• Hugging Face
• ModelScope

• Qwen-Image-DiffSynth-ControlNets/model_patches: Includes canny, depth, and inpaint models
• qwen_image_union_diffsynth_lora.safetensors: Image structure control LoRA supporting canny, depth, pose, lineart, softedge, normal, openpose
• InstantX ControlNet: To be updated

​

ComfyOrg Qwen-Image live stream

​

Qwen-Image Native Workflow Example

​

Qwen-Image: Text to Image

1. Qwen-Image original model fp8_e4m3fn
2. 8-step accelerated version: Qwen-Image original model fp8_e4m3fn with lightx2v 8-step LoRA
3. Distilled version: Qwen-Image distilled model fp8_e4m3fn

​

1. Workflow File

After updating ComfyUI, you can find the workflow file in the templates, or drag the workflow below into ComfyUI to load it.

​

2. Model Download

• Qwen-Image_bf16 (40.9 GB)
• Qwen-Image_fp8 (20.4 GB)
• Distilled versions (non-official, requires only 15 steps)

• qwen_image_fp8_e4m3fn.safetensors

• qwen_image_distill_full_fp8_e4m3fn.safetensors
• qwen_image_distill_full_bf16.safetensors

• Qwen-Image-Lightning-8steps-V1.0.safetensors

• qwen_2.5_vl_7b_fp8_scaled.safetensors

📂 ComfyUI/
├── 📂 models/
│   ├── 📂 diffusion_models/
│   │   ├── qwen_image_fp8_e4m3fn.safetensors
│   │   └── qwen_image_distill_full_fp8_e4m3fn.safetensors ## 蒸馏版
│   ├── 📂 loras/
│   │   └── Qwen-Image-Lightning-8steps-V1.0.safetensors   ## 8步加速 LoRA 模型
│   ├── 📂 vae/
│   │   └── qwen_image_vae.safetensors
│   └── 📂 text_encoders/
│       └── qwen_2.5_vl_7b_fp8_scaled.safetensors

​

3. Workflow Instructions

1. Make sure the Load Diffusion Model node has loaded qwen_image_fp8_e4m3fn.safetensors
2. Make sure the Load CLIP node has loaded qwen_2.5_vl_7b_fp8_scaled.safetensors
3. Make sure the Load VAE node has loaded qwen_image_vae.safetensors
4. Make sure the EmptySD3LatentImage node is set with the correct image dimensions
5. Set your prompt in the CLIP Text Encoder node; currently, it supports at least English, Chinese, Korean, Japanese, Italian, etc.
6. If you want to enable the 8-step acceleration LoRA by lightx2v, select the node and use Ctrl + B to enable it, and modify the Ksampler settings as described in step 8
7. Click the Queue button, or use the shortcut Ctrl(cmd) + Enter to run the workflow
8. For different model versions and workflows, adjust the KSampler parameters accordingly

​

Qwen Image InstantX ControlNet Workflow

​

Qwen-Image InstantX Union ControlNet

​

1. Workflow and Input Images

​

2. Model Links

1. InstantX Controlnet

2. Lotus Depth model

• lotus-depth-d-v1-1.safetensors

• vae-ft-mse-840000-ema-pruned.safetensors or any SD1.5 VAE

ComfyUI/
├── models/
│   ├── diffusion_models/
│   │   └─── lotus-depth-d-v1-1.safetensors
│   └── vae/
│       └──  lvae-ft-mse-840000-ema-pruned.safetensors

You can also use custom nodes like comfyui_controlnet_aux to generate depth map.

​

3. Workflow Instructions

1. Ensure that the Load ControlNet Model node correctly loads the Qwen-Image-InstantX-ControlNet-Union.safetensors model
2. Upload input image
3. This subgraph uses the Lotus Depth model. You can find it in the templates or edit the subgraph to learn more, make sure all the models are loaded correctly
4. Click the Run button, or use the shortcut Ctrl(cmd) + Enter to run the workflow

​

Qwen Image ControlNet DiffSynth-ControlNets Model Patches Workflow

​

Qwen-Image ControlNet Model Patch

​

1. Workflow and Input Images

​

2. Model Links

• qwen_image_canny_diffsynth_controlnet.safetensors
• qwen_image_depth_diffsynth_controlnet.safetensors
• qwen_image_inpaint_diffsynth_controlnet.safetensors

​

3. Workflow Usage Instructions

• Canny: Processed canny edge, line art contours
• Depth: Preprocessed depth map showing spatial relationships
• Inpaint: Requires using Mask to mark areas that need to be repainted

1. Ensure that qwen_image_canny_diffsynth_controlnet.safetensors is loaded
2. Upload input image for subsequent processing
3. The Canny node is a native preprocessing node that will preprocess the input image according to your set parameters to control generation
4. If needed, you can modify the strength in the QwenImageDiffsynthControlnet node to control the intensity of line art control
5. Click the Run button, or use the shortcut Ctrl(cmd) + Enter to run the workflow

For using qwen_image_depth_diffsynth_controlnet.safetensors, you need to preprocess the image into a depth map and replace the image processing part. For this usage, please refer to the InstantX processing method in this document. Other parts are similar to using the Canny model.

1. Ensure that ModelPatchLoader loads the qwen_image_inpaint_diffsynth_controlnet.safetensors model
2. Upload image and use the Mask Editor to draw a mask. You need to connect the mask output of the corresponding Load Image node to the mask input of QwenImageDiffsynthControlnet to ensure the corresponding mask is loaded
3. Use the Ctrl-B shortcut to set the original Canny in the workflow to bypass mode, making the corresponding Canny node processing ineffective
4. In CLIP Text Encoder, input what you want to change the masked area to
5. If needed, you can modify the strength in the QwenImageDiffsynthControlnet node to control the corresponding control intensity
6. Click the Run button, or use the shortcut Ctrl(cmd) + Enter to run the workflow

​

Qwen Image Union ControlNet LoRA Workflow

​

Qwen-Image Union Control

​

1. Workflow and Input Images

​

2. Model Links

• qwen_image_union_diffsynth_lora.safetensors: Image structure control LoRA supporting canny, depth, pose, lineart, softedge, normal, openpose

​

3. Workflow Instructions

1. Ensure that LoraLoaderModelOnly correctly loads the qwen_image_union_diffsynth_lora.safetensors model
2. Upload input image
3. If needed, you can adjust the Canny node parameters. Since different input images require different parameter settings to get better image preprocessing results, you can try adjusting the corresponding parameter values to get more/fewer details
4. Click the Run button, or use the shortcut Ctrl(cmd) + Enter to run the workflow

For other types of control, you also need to replace the image processing part.