QuickStart - Deploying ComfyUI 2

Note

Recommended: Z-image Turbo model.

• z-image-bf16.safetensors
• qwen_3_4b.safetensors
• ae.safetensors

(When you select a workflow for a template, ComfyUI will guide you through the required models.)

1. Load Workflow in ComfyUI

   Select Template inside ComfyUI.

   

   Check the missing nodes in the modal.

   

   Don’t close this popup — you should click [Copy URL] next to each model.

   Via SSH, download the models with the commands below

   Note

   Download the desired models or components via wget / curl from your SSH session.

   

   1) Create the folder if it doesn’t exist:

   mkdir -p /workspace/models/vae
   wget -c -O /workspace/models/vae/ae.safetensors \
     "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/vae/ae.safetensors?download=true"
   
   mkdir -p /workspace/models/text_encoders
   wget -c -O /workspace/models/text_encoders/qwen_3_4b.safetensors \
     "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/text_encoders/qwen_3_4b.safetensors?download=true"

   2) Skip mkdir if the folder already exists:

   wget -c -O /workspace/models/diffusion_models/z_image_bf16.safetensors \
     "https://huggingface.co/Comfy-Org/z_image/resolve/main/split_files/diffusion_models/z_image_bf16.safetensors?download=true"

   Note

   Once executed, the download process will be visible inside your SSH terminal.

   

2. Generate Image or Video

   

Next Steps

• Write Prompt — input the positive and negative prompts. Z-image Turbo allows for high-quality generation even with simple descriptions.
• Modify Sampler Settings — adjust parameters such as steps, CFG scale, and seed to fine-tune the generation process.
• Apply LoRAs — connect LoRA nodes to apply specific styles or characters to your Z-image Turbo workflow.