Gallery

Hyper SDXL 1step Unified LoRA Workflow

fast-generation0 nodes0 custom nodes0 models
checkpointscomfyui-tcdloralorassdxl

Pull the image

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

docker pull timpietruskyrunpod/comfyui-wizard:aim-comfyui_hyper-sdxl-1step-unified-lora-workflow
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-tcd --mode remote

# download models into comfyui
RUN comfy model download --url https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_base_1.0.safetensors --relative-path models/checkpoints --filename sd_xl_base_1.0.safetensors
RUN comfy model download --url https://huggingface.co/ByteDance/Hyper-SD/resolve/main/Hyper-SDXL-1step-lora.safetensors --relative-path models/loras --filename Hyper-SDXL-1step-lora.safetensors

Run Instructions

Build
docker build -t comfyui-aim-comfyui_hyper-sdxl-1step-unified-lora-workflow .
Run
docker run --gpus all -p 8188:8188 timpietruskyrunpod/comfyui-wizard:aim-comfyui_hyper-sdxl-1step-unified-lora-workflow
RunPod Serverless

Use the Dockerfile as a RunPod Serverless worker template