#324 · Primary category： Computer Vision
ComfyUI-Marigold
Marigold depth estimation in ComfyUI
Project last updated：05/16/25
GitHub Stars
569
Forks
24
Contributors
5
License
GPL-3.0
Why we included this project
This custom node brings Marigold's diffusion-based depth estimator into ComfyUI. It exposes the settings that matter for quality and speed: denoise steps, ensemble repeats, and batch size, so you can trade processing time for accuracy depending on your GPU. The author also added a remap node to stretch the depth range for viewing and an OpenEXR output node that preserves the full 16-bit range, which is handy when you're handing depth maps to VFX or 3D tools. Since it uses the same diffusers pipeline as the original Marigold, the model auto-downloads on first run, and fp16 support roughly halves VRAM usage. It's a solid option for depth-aware workflows in ComfyUI, whether you're doing ControlNet conditioning, relighting, or 3D reconstruction.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)