Qwen-Image 2.1

Repackaged model files for ComfyUI.

Original model repositories:

Prompt Enhancer

The qwen3.5_9b_qwen_image_2.1_pe models are for prompt enhancement, to be used with the Generate Text node.

Original model repositories:

Turbo

For faster inference, use either the full Turbo model, or the Turbo LoRA extracted from the base model. Use 8 steps and cfg 1.

Place the files in the following folders:

📂 ComfyUI/
└── 📂 models/
    ├── 📂 diffusion_models/
    │   ├── qwen_image_2.1_bf16.safetensors
    │   ├── qwen_image_2.1_int8_convrot.safetensors
    │   ├── qwen_image_2.1_turbo_bf16.safetensors
    │   └── qwen_image_2.1_turbo_int8_convrot.safetensors
    ├── 📂 model_patches/
    │   ├── qwen_image_2.1_fun_controlnet_union_bf16.safetensors
    │   └── qwen_image_2.1_fun_controlnet_union_int8_convrot.safetensors
    ├── 📂 text_encoders/
    │   ├── qwen3vl_8b_bf16.safetensors
    │   ├── qwen3vl_8b_int8_convrot.safetensors
    │   ├── qwen3vl_8b_w4a8.safetensors
    │   ├── qwen3.5_9b_qwen_image_2.1_pe_i2i.int8_convrot.safetensors
    │   ├── qwen3.5_9b_qwen_image_2.1_pe_i2i_w4a8.safetensors
    │   ├── qwen3.5_9b_qwen_image_2.1_pe_t2i.int8_convrot.safetensors
    │   └── qwen3.5_9b_qwen_image_2.1_pe_t2i_w4a8.safetensors
    └── 📂 vae/
        └── qwen_image_2.1_vae_bf16.safetensors
    └── 📂 loras/
        └── qwen_image_2.1_turbo_lora_avg_rank_178_bf16.safetensors