Model
Trends
.ai
Model
Trends
.ai
the best open source ai models

Load ControlNet Model node in ComfyUI

Load ControlNet Model reads a ControlNet (or T2I-Adapter / ControlNet Union) file from models/controlnet and outputs a CONTROL_NET object for Apply ControlNet.
Node pack: ComfyUI core
Category: ControlNet and guidance

What Load ControlNet Model does

ControlNets are side networks that steer the diffusion model with a guide image: an edge map, a depth map, a pose skeleton, a normal map or the picture itself (Tile). Load ControlNet Model loads one such file and must match the base model family: SD 1.5 ControlNets for SD 1.5 checkpoints, SDXL ControlNets (for example controlnet-union-sdxl-1.0, diffusers_xl_canny) for SDXL and Pony, Flux ControlNets (Shakker, InstantX, Union Pro) for Flux.
Union and Promax models bundle several control types in one file and switch mode through a companion node (SetUnionControlNetType) or by the preprocessor you feed them. T2I-Adapters load through the same node and are lighter but weaker. The DiffControlNetLoader variant takes the MODEL input for diff-ControlNets, which are rare today.

Inputs

Name
Type
What it is
control_net_name
COMBO
A file from models/controlnet.

Outputs

Name
Type
What it is
CONTROL_NET
CONTROL_NET
The loaded network; connect it to Apply ControlNet.
AD
Skip the setup: ComfyUI workflows preinstalled on the cloud
BitVector runs ready-made ComfyUI workflows on its own GPUs. No install, no missing nodes, no red boxes. Open it on your phone or laptop and generate in a minute.

How to use Load ControlNet Model

  1. Download a ControlNet for your model family into models/controlnet.
  2. Add Load ControlNet Model and pick the file.
  3. Connect CONTROL_NET to Apply ControlNet along with the preprocessed guide image.
  4. For a Union model add SetUnionControlNetType and choose canny, depth, openpose and so on.

Settings and tips

  • File names tell the family: "xl" or "sdxl" for SDXL, "v11p_sd15" for SD 1.5, "flux" for Flux.
  • fp16 versions (700 MB for SD 1.5, 2.5 GB for SDXL) are enough for generation.
  • One loaded ControlNet can be applied in several Apply ControlNet nodes with different images.
  • The ControlNet Aux pack provides the preprocessors (Canny, Depth Anything, DWPose) that create guide images.

Troubleshooting Load ControlNet Model

Error: ControlNet model type mismatch / shape mismatch

Why it happens
An SD 1.5 ControlNet with an SDXL checkpoint or the other way round.

How to fix it
Download the ControlNet for the right family and pick it here.

The ControlNet has no visible effect

Why it happens
A Union model without a type set, strength 0, or the guide image is black because the preprocessor failed.

How to fix it
Preview the guide image, set strength 0.6-1.0 and add SetUnionControlNetType for union files.

Dropdown is empty

Why it happens
No files in models/controlnet, or files in a nested folder with an unsupported extension.

How to fix it
Place .safetensors or .pth files directly in models/controlnet and press R.

AD
Run this workflow from your phone
Every workflow on this page is preinstalled on BitVector with the models and custom nodes already in place. Pick one, type a prompt, done. Zero setup, nothing to download.

Questions about Load ControlNet Model

Can I load a diffusers ControlNet folder?

Only single-file versions. Convert or download the .safetensors release.

Do ControlNets work with LoRAs?

Yes; ControlNets act on conditioning, LoRAs patch the model. They combine freely.

Related nodes

Apply ControlNet
ComfyUI core
Apply ControlNet attaches a guide image and a loaded ControlNet to the positive and negative CONDITIONING with strength and start/end percentages, so the sampler follows edges, depth or pose from the guide.
Load Checkpoint
ComfyUI core
Load Checkpoint (CheckpointLoaderSimple) opens a .safetensors or .ckpt model file and hands out the three parts every workflow needs: the diffusion MODEL, the CLIP text encoder and the VAE.
Load Image
ComfyUI core
Load Image reads a picture from the ComfyUI input folder (or an upload) and outputs an IMAGE tensor plus a MASK taken from the alpha channel, the starting point for img2img, inpainting, ControlNet and IP-Adapter graphs.
Ultimate SD Upscale
ComfyUI_UltimateSDUpscale
Ultimate SD Upscale enlarges a picture with an ESRGAN model, then re-samples it tile by tile through the diffusion model with your prompt at low denoise, adding real detail at 2x-4x without running out of VRAM.
AD
Tired of fixing nodes? Let the cloud do it
BitVector keeps hundreds of ComfyUI workflows installed, updated and tested on fast cloud GPUs. No Python, no CUDA errors, no VRAM limits. Works from any browser.

More ComfyUI nodes

CLIP Text Encode (Prompt)
ComfyUI core
CLIP Text Encode turns a text prompt into CONDITIONING using the model text encoder. One node holds the positive prompt, a second one the negative prompt.
ComfyUI Manager
ComfyUI-Manager
ComfyUI Manager is the extension that installs, updates and fixes custom node packs and models from inside the interface, resolves missing nodes in imported workflows and snapshots your setup.
KSampler
ComfyUI core
KSampler runs the denoising loop: it takes the model, prompts and a latent and produces the finished latent image, controlled by seed, steps, cfg, sampler, scheduler and denoise.
Save Image
ComfyUI core
Save Image writes the IMAGE tensor to ComfyUI/output as a PNG, with the whole workflow embedded in the file metadata so the picture can be dragged back into ComfyUI to restore the graph.
VAE Decode
ComfyUI core
VAE Decode converts the sampled LATENT into a pixel IMAGE with the VAE; VAE Decode (Tiled) does the same in tiles for very large images.
Empty Latent Image
ComfyUI core
Empty Latent Image creates the blank latent canvas (width, height, batch_size) that text-to-image sampling starts from; dimensions must be multiples of 8 and match the model family.