Qwen Basic ControlNet Workflow in ComfyUI

About This Workflow

Qwen ControlNet Workflow in ComfyUI

The Qwen Basic ControlNet workflow in ComfyUI is a simple and effective setup that allows you to generate AI images using a ControlNet reference image along with a text prompt. This workflow is designed for users who want better control over image structure and composition instead of relying only on random text-to-image generations.

Without ControlNet, AI generation can be unpredictable. Even with the same prompt, the results may change every time.

This workflow helps you achieve:

More accurate composition Better pose control Improved layout consistency Faster workflow for controlled generations

It is a great choice for both beginners and advanced users who want clean and predictable output.

Required Models

Model links

You can find all the models on Huggingface or Modelscope

Diffusion model

• qwen_image_fp8_e4m3fn.safetensors

ControlNet

• Qwen-Image-InstantX-ControlNet-Union.safetensors

LoRA

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

Text encoder

• qwen_2.5_vl_7b_fp8_scaled.safetensors

VAE

• qwen_image_vae.safetensors

Model Storage Location

📂 ComfyUI/
├── 📂 models/
│   ├── 📂 diffusion_models/
│   │   ├── qwen_image_fp8_e4m3fn.safetensors
│   │   └── qwen_image_distill_full_fp8_e4m3fn.safetensors
│   ├── 📂 loras/
│   │   └── Qwen-Image-Lightning-8steps-V1.0.safetensors
│   ├── 📂 controlnet/ 
│   │   └── Qwen-Image-InstantX-ControlNet-Union.safetensors
│   ├── 📂 vae/
│   │   └── qwen_image_vae.safetensors
│   └── 📂 text_encoders/
│       └── qwen_2.5_vl_7b_fp8_scaled.safetensors

Workflow Graph