Marigold V2

Marigold V2 estimates depth, surface normals or intrinsic albedo with task-specific diffusion adapters.

Tasks: depth, surface normals, albedo
Sizes: b at 1024 px
Install: pip install "libreyolo[marigold]"
Support tier: Inference only, since v1.6.0. Predict, validate and export only. Training features do not apply.
Licenses: Code MIT, weights Apache-2.0. Commercial use

Install

bash

pip install "libreyolo[marigold]"

The default four-bit runtime requires CUDA.

Predict

Python

from libreyolo import LibreYOLO, SAMPLE_IMAGE # Requires CUDA for default four-bit inference.model = LibreYOLO("LibreMarigoldV2b-depth.pt", device="cuda")result = model(SAMPLE_IMAGE)print(result)

The adapter downloads a separately pinned base model. Default quantization="4bit" requires CUDA; the snippet requires that runtime. quantization="none" selects the CPU-capable path. The default seed is 2025. Albedo results hold linear RGB and convert to sRGB for display. Training and export are not supported.

Validate

Python

from libreyolo import LibreYOLO, SAMPLE_IMAGE # Requires CUDA for default four-bit inference.model = LibreYOLO("LibreMarigoldV2b-depth.pt", device="cuda")# Depth dataset YAML: images/val plus same-stem maps in depths/val.metrics = model.val(data="path/to/your/depth.yaml", workers=0)print(metrics)

Use the dataset format for this task. Validation explains the dataset requirements and returned metrics.

Checkpoints

File	Weights license
Depth
LibreMarigoldV2b-depth.pt	apache-2.0
LibreMarigoldV2b-depth-log-stage1.pt	apache-2.0
LibreMarigoldV2b-depth-log-layered.pt	apache-2.0
LibreMarigoldV2b-depth-uniform-base.pt	apache-2.0
LibreMarigoldV2b-depth-uniform-layered.pt	apache-2.0
LibreMarigoldV2b-depth-disparity-base.pt	apache-2.0
LibreMarigoldV2b-depth-disparity-layered.pt	apache-2.0
Surface normals
LibreMarigoldV2b-normal.pt	apache-2.0
Albedo
LibreMarigoldV2b-albedo.pt	apache-2.0

Every file above exists in the LibreYOLO org today and downloads on first use.

Licensing

Check the license on the Hugging Face repository of the specific weights you download. Every checkpoint in the LibreYOLO org carries one, and they are not always the same across a family. That repository is the authoritative source; the summary below describes what applied when this page was last verified.

This is a description of the licenses involved, not legal advice. If the answer matters commercially, read the licenses yourself and take your own counsel.

Original work: Marigold V2, Huawei Bayer Lab
Upstream license: Apache-2.0
Upstream source: github.com/huawei-bayerlab/marigold-v2
LibreYOLO code: MIT
Weights: Apache-2.0, republished at huggingface.co/LibreYOLO
Interpretation: The adapters and separately acquired Qwen image base declare Apache-2.0.