Qwen Image ComfyUI Workflow: Generate High-Quality Images Locally

About This Workflow

Generate high-quality, detailed images from text prompts, including realistic people, fashion shots, fantasy scenes, and cinematic concepts.

Control image style and quality by adjusting CFG, steps, resolution, and workflow parameters directly inside ComfyUI.

Create sharp textures and fine details (fabric, skin, lighting, atmosphere), making it suitable for professional-looking visuals.

Run everything locally on your own GPU, giving you full privacy, no usage limits, and faster experimentation.

Easily integrate Qwen Image into custom ComfyUI workflows for batch generation, prompt testing, or creative pipelines.

Required Models

Model links

You can find all the models on Huggingface or Modelscope

diffusion model

• qwen_image_fp8_e4m3fn.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
│   ├── 📂 vae/
│   │   └── qwen_image_vae.safetensors
│   └── 📂 text_encoders/
│       └── qwen_2.5_vl_7b_fp8_scaled.safetensors

Workflow Graph