Depth ControlNet

Video Lecture

Section	Video Links
Depth ControlNet

Video Timings

Description

The Depth ControlNet will prioritise 3D depth information in the image more than shapes and outlines detected when using Canny.

It can produce much more creative styles since it is only interested in the 3D shape, and not any patterns or lines detected on the surfaces.

Since it is 3D aware, it can also produce better lighting, shadows and perspective.

The Depth ControlNet is most often used in architectural and interior design image generation.

Drag this image that contains a work flow into ComfyUI and generate.

"ultra modern house in the forest, swimming pool, garden, sunset"

"modern kitchen, open plan, view of garden, sunset"

Generate A Depth Image

There is no inbuilt node that can create a depth image in ComfyUI, so we can install the comfyui_controlnet_aux addon using the Custom Nodes Manager, or with your command/terminal prompt,

1. Navigate to your ComfyUI/custom_nodes folder.

2. Run,

git clone https://github.com/Fannovel16/comfyui_controlnet_aux/

1. Restart ComfyUI

Depth ControlNet Models

Base	ControlNet Model (Depth)
SD1.5	control_v11f1p_sd15_depth_fp16.safetensors
SDXL	control-lora-depth-rank256.safetensors
Flux	flux-depth-controlnet-v3.safetensors

Optional Extra Checkpoints

SD1.5 Based

architecturerealmix_v11.safetensors
interiordesignsuperm_v2.safetensors