Marigold depth estimation in ComfyUI

By kijaiView on GitHub →

This is a wrapper node for Marigold depth estimation: [https://github.com/prs-eth/Marigold](https://github.com/kijai/ComfyUI-Marigold). Currently using the same diffusers pipeline as in the original implementation, so in addition to the custom node, you need the model in diffusers format. NOTE: See details in repo to install.

How much VRAM does Marigold depth estimation in ComfyUI require?

Direct Answer: The ComfyUI node Marigold depth estimation in ComfyUI requires a minimum base VRAM of 128MB and is optimized for GPUs with at least 4GB of VRAM. Low VRAM mode is fully supported for resource-constrained setups.

High (2-4GB)
Base VRAM:
128MB (0.1GB)
Recommended GPU:
4GB+ VRAM
Low VRAM Mode:
✓ Supported
Estimation Confidence:
MEDIUM

Interactive VRAM Compatibility Estimator

Estimated Total VRAM: 3.00 GBTarget: 8 GB
✅ Comfortable Fit

Your GPU has plenty of headroom. You can run this node safely with your active configurations!

Deploy on High-Performance GPUs

Need more VRAM to run ComfyUI with this node? Rent low-cost, high-performance GPUs on Vast.ai instantly.

🚀 Deploy on Vast.ai

Deploy on Cloud GPUs

Need more VRAM to run ComfyUI with this node? Rent low-cost, high-performance cloud GPUs on RunPod instantly.

🚀 Deploy on RunPod

What Python packages are required for Marigold depth estimation in ComfyUI?

Direct Answer: Running Marigold depth estimation in ComfyUI requires installing the following Python package dependencies: accelerate>=0.22.0, diffusers>=0.33.0, huggingface-hub, matplotlib, scipy, torch>=2.0.1, transformers>=4.32.1. This node specifically requires PyTorch version 2.0.1 or newer.

requirements.txt
accelerate>=0.22.0
diffusers>=0.33.0
huggingface-hub
matplotlib
scipy
torch>=2.0.1
transformers>=4.32.1

Interactive Setup & Dependency Resolver

Operating System:
Environment Type:
Run this terminal command in your ComfyUI root folder:
# Loading command...

Special Environment Requirements:

Requires PyTorch version 2.0.1+.

To update PyTorch for your selected setup, run:
# Loading PyTorch command...

Related Custom Nodes

The following custom nodes run in the same PyTorch / CUDA environment and share similar categories or workflows:

ComfyUI DreamLight Node
by APZmedia128MB VRAM
ComfyUI Level Pixel
by LevelPixel128MB VRAM
ComfyUI Level Pixel Advanced
by LevelPixel128MB VRAM
VLM_nodes
by gokayfem256MB VRAM
Yuan-ManX/ComfyUI-AudioX
by Yuan-ManX1.5GB VRAM

Frequently Asked Questions

How much VRAM does Marigold depth estimation in ComfyUI require?

Marigold depth estimation in ComfyUI requires a minimum of 128MB (0.1GB) of VRAM for base operation. For optimal performance, a GPU with at least 4GB of VRAM is recommended. This node supports low VRAM mode for resource-constrained setups.

Can I run Marigold depth estimation in ComfyUI on an RTX 3060, RTX 4070, or RTX 4090?

✅ RTX 3060 (12GB): Yes, fully compatible with 10.7GB headroom. ✅ RTX 4070 (12GB): Yes, fully compatible with 10.7GB headroom. ✅ RTX 4070 Ti (16GB): Yes, fully compatible with 14.3GB headroom. ✅ RTX 4090 (24GB): Yes, fully compatible with 21.5GB headroom

What PyTorch version does Marigold depth estimation in ComfyUI need?

Marigold depth estimation in ComfyUI requires the following PyTorch-related packages: torch>=2.0.1. Ensure your ComfyUI environment has these installed. Ensure your PyTorch installation matches your CUDA version (use torch.version.cuda to check).

What Python packages are required for Marigold depth estimation in ComfyUI?

To run Marigold depth estimation in ComfyUI, you need to install: accelerate>=0.22.0, diffusers>=0.33.0, huggingface-hub, matplotlib, scipy, torch>=2.0.1, transformers>=4.32.1. You can install these using pip or add them to your requirements.txt file.

How can I reduce VRAM usage when running Marigold depth estimation in ComfyUI?

Marigold depth estimation in ComfyUI supports low VRAM mode. To reduce memory usage: (1) Enable --lowvram or --medvram flags in ComfyUI, (2) Reduce batch size to 1, (3) Use fp16 or fp8 precision if supported, (4) Close other GPU applications.

How do I install Marigold depth estimation in ComfyUI in ComfyUI?

To install Marigold depth estimation in ComfyUI: (1) Navigate to your ComfyUI/custom_nodes directory, (2) Clone the repository: git clone https://github.com/kijai/ComfyUI-Marigold, (3) Install dependencies: pip install -r requirements.txt (if present), (4) Restart ComfyUI. Alternatively, use ComfyUI Manager for one-click installation.