This ComfyUI workflow is used to test and pick which preprocessors/controlnets will work best for your images. Simply add a image (or single frame) and analyze the results. It uses the auxiliary controlnets, marigold...
Runtime profile
Source description
This ComfyUI workflow is used to test and pick which preprocessors/controlnets will work best for your images. Simply add a image (or single frame) and analyze the results. It uses the auxiliary controlnets, marigold depth, SoftEdgePlus, and threw in a automask node.
*When running the workflow for the first time, It will auto download the models it needs. Currently there is a bad link for the "Zoe_Depth_Anything" model. If you get a giant error. Download the model from HuggingFace here and put it in:
...\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts\LiheYoung\Depth-Anything\checkpoints_metric_depth\depth_anything_metric_depth_indoor.pt
Estimated VRAM requirement
0 GB estimated
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Use this ComfyUI workflow to test and choose which preprocessors and ControlNets work best for an image or single frame by analyzing the resulting outputs.
It uses auxiliary ControlNets, Marigold depth, SoftEdgePlus, and an automask node to analyze the input.
Input: add an image or a single frame.
Output: analyzed results for choosing preprocessors or ControlNets for the input.
On its first run, it automatically downloads the models it needs.
If the Zoe_Depth_Anything link causes a giant error, download depth_anything_metric_depth_indoor.pt from Hugging Face and place it under ...\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts\LiheYoung\Depth-Anything\checkpoints_metric_depth\.
Named workflow nodes include AIO_Preprocessor, ColorizeDepthmap, GrowMaskWithBlur, Image Dragan Photography Filter, Image High Pass Filter, and LoadImage.
Other named workflow nodes are MarigoldDepthEstimation, MaskToImage, PreviewImage, RemapDepth, and Robust Video Matting.
The listed base model is SD 1.5, and the workflow version is v1.0.
No usage license is listed for this workflow, so verify the terms before reuse.
Suggestion · not verified
Before setup, verify which node pack provides MaskToImage, LoadImage, and PreviewImage.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 816 downloads · Type Workflows · Base model SD 1.5
Requirements
11 requirementsNode pack · Unknown
Node pack · Unknown
Node pack · Unknown
Node pack · Unknown
Node pack · Unknown
LoadImage
PossibleNode pack · Unknown
Node pack · Unknown
MaskToImage
PossibleNode pack · Unknown
PreviewImage
PossibleNode pack · Unknown
Node pack · Unknown
Node pack · Unknown