Skip to content

Docker Image Version

WAN 2.x inference with ComfyUI

Select number frames, size , prompt and offload

A streamlined and automated environment for running ComfyUI with WAN 2.x video models, optimized for use on RunPod

🔧 Features

  • Automatic model and LoRA provisioning via environment variables.
  • Included workflows for video generation and enhancement using pre-installed custom nodes.
  • Compatible with high-performance NVIDIA GPUs (CUDA 12.8).
  • Compiled attentions and GPU accelerations.
  • Latent preview enabled for samplers.
  • Lora manager

🔧 Built-in authentication

  • ComfyUI
  • Code Server
  • Hugging Face API
  • CivitAI API

📦 Deployment on runpod

Pod running on L40S

Pod running on L40S native comfyUI

Pod running on A40

Pod running on A40 comfyUI wanwrapper