This guide will introduce you to the basic concepts of Pose ControlNet, and demonstrate how to generate large-sized images in ComfyUI using a two-pass generation approach
Workflows
-> Open (ctrl+o)
.
This image already includes download links for the corresponding models, and dragging it into ComfyUI will automatically prompt for downloads.Load Checkpoint
can load majicmixRealistic_v7.safetensorsLoad VAE
can load vae-ft-mse-840000-ema-pruned.safetensorsLoad ControlNet Model
can load control_v11p_sd15_openpose_fp16.safetensorsLoad Image
node to upload the pose input image provided earlier, or use your own OpenPose skeleton mapLoad Checkpoint
can load japaneseStyleRealistic_v20.safetensorsQueue
button or use the shortcut Ctrl(cmd) + Enter
to execute the image generationLoad Checkpoint
nodeLoad ControlNet Model
nodeApply ControlNet
node and combined with positive and negative prompt conditionsKSampler
node (typically using 20-30 steps) generates a basic character pose imageVAE Decode
Upscale latent
nodeLoad Checkpoint
loads the japaneseStyleRealistic_v20 model, which focuses on details and styleKSampler
node uses a lower denoise
strength (typically 0.4-0.6) for refinement, preserving the basic structure from the first phaseVAE Decode
and Save Image
nodes