Gallery
Ttio Wan21 Text2video 13b
general0 nodes0 custom nodes0 models
comfyui-videohelpersuitediffusion_modelstext_encodersvaevideo
Pull the image
Pre-built and pushed to Docker Hub. No local build needed.
docker pull timpietruskyrunpod/comfyui-wizard:ttio-wan21_text2video_13b
Dockerfile
# clean base image containing only comfyui, comfy-cli and comfyui-manager
FROM runpod/worker-comfyui:5.8.4-base
# install custom nodes into comfyui
RUN comfy node install --exit-on-fail comfyui-videohelpersuite --mode remote
# download models into comfyui
RUN comfy model download --url https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/diffusion_models/wan2.1_t2v_1.3B_bf16.safetensors --relative-path models/diffusion_models --filename wan2.1_t2v_1.3B_bf16.safetensors
RUN comfy model download --url https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors --relative-path models/vae --filename wan_2.1_vae.safetensors
RUN comfy model download --url https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors --relative-path models/text_encoders --filename umt5_xxl_fp8_e4m3fn_scaled.safetensors
Run Instructions
Build
docker build -t comfyui-ttio-wan21_text2video_13b .
Run
docker run --gpus all -p 8188:8188 timpietruskyrunpod/comfyui-wizard:ttio-wan21_text2video_13b
RunPod Serverless
Use the Dockerfile as a RunPod Serverless worker template