Marigold V2 Tiled Depth - Vathography
Tiled Marigold V2 depth map estimation from high-resolution photographs in ComfyUI
ComfyUI-Marigold-V2-Tiled-Depth-Vathography
The Vathography practice: a photograph is distilled to a single element: the volume of the scene, creating a unique artwork, composed at capture, focused and shaped in post by the artist.
- The volume: estimated by inferring the depth map from a single photograph, using the Marigold V2 model.
- The artwork: originally meant to be an intermediate post-process pass, the depth map is elevated to the final artwork, through a process that gives full creative control to the artist.
- The focus: no longer determined by the lens at capture. When remapping the depth values, it becomes a creative choice, placed at any distance, on one subject or across several at once, sitting at different depths.
- The expression: the depth map is then shaped by the artist using contrast or color, from the quiet haze of atmospheric perspective to the stark contrast of opposing tonal values.
- The photography: this post-process changes the process itself, giving a new approach to photography. At capture, a photograph is composed purposefully for Vathography, reading a scene by its depth and volume rather than its light and color.
Vathography tutorial: https://youtu.be/DVYgwRaTKkA
Vathography Blender add-on: https://vathography.gumroad.com/l/addon
Vathography website: https://vathography.com/
The node
Marigold V2 Tiled Depth - Vathography estimates the depth map of a high-resolution photograph by tiling it, keeping the photograph's full resolution.
Install: search Marigold V2 Tiled Depth Vathography in ComfyUI Manager, or clone into ComfyUI/custom_nodes/:
git clone https://github.com/vathography/ComfyUI-Marigold-V2-Tiled-Depth-Vathography
No extra Python packages required. Needs ComfyUI v0.36.0 or newer and the Marigold V2 depth models from Comfy-Org/marigold-v2-0 which can be installed following the official guide: https://docs.comfy.org/tutorials/utility/marigold-v2
Use: open the example workflow in example_workflows/, load a photograph, run.
GPU: tested on an RTX 5090. Estimated minimum requirements: 8 GB VRAM + 24 GB RAM.
License: AGPL-3.0-only. Free node; the depth maps it produces are free to use, for personal and commercial work. See LICENSE.
By Karim Joseph Nassar, developed with Claude Code.
Marigold V2
- Marigold V2 ComfyUI official guide: https://docs.comfy.org/tutorials/utility/marigold-v2
- The ComfyUI implementation — native Marigold V2 support by the ComfyUI team: models for ComfyUI
- The model — Marigold V2 by huawei-bayerlab, Apache-2.0: code · weights
Thank you to the Marigold V2 team: Igor Pavlovic, Thiemo Wandel, Anton Obukhov, Luca Bartolomei, Andrey Davydov, Fabio Tosi, Matteo Poggi, Sabine Süsstrunk, Dengxin Dai. https://huggingface.co/spaces/huawei-bayerlab/marigold-v2-web