Gallery

Ttio Qwen Image Tech Practice

general0 nodes0 custom nodes0 models
diffusion_modelstext_encodersvae

Pull the image

Pre-built and pushed to Docker Hub. No local build needed.

docker pull timpietruskyrunpod/comfyui-wizard:ttio-qwen_image_tech_practice
Dockerfile
# clean base image containing only comfyui, comfy-cli and comfyui-manager
FROM runpod/worker-comfyui:5.8.4-base

# download models into comfyui
RUN comfy model download --url https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/vae/qwen_image_vae.safetensors --relative-path models/vae --filename qwen_image_vae.safetensors
RUN comfy model download --url https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors --relative-path models/text_encoders --filename qwen_2.5_vl_7b_fp8_scaled.safetensors
RUN comfy model download --url https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_fp8_e4m3fn.safetensors --relative-path models/diffusion_models --filename qwen_image_fp8_e4m3fn.safetensors

Run Instructions

Build
docker build -t comfyui-ttio-qwen_image_tech_practice .
Run
docker run --gpus all -p 8188:8188 timpietruskyrunpod/comfyui-wizard:ttio-qwen_image_tech_practice
RunPod Serverless

Use the Dockerfile as a RunPod Serverless worker template