Marigold V2

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

Task: depth, surface normals, albedo
Ukuran: b at 1024 px
Instalasi: pip install "libreyolo[marigold]"
Tier dukungan: Hanya inferensi, sejak v1.6.0. Hanya prediksi, validasi, dan ekspor. Fitur pelatihan tidak berlaku.
Lisensi: Kode MIT, bobot Apache-2.0. Penggunaan komersial

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

Berkas	Lisensi bobot
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

Setiap berkas di atas saat ini tersedia di organisasi LibreYOLO dan diunduh saat pertama kali digunakan.

Licensing

Periksa lisensi di repositori Hugging Face untuk bobot tertentu yang diunduh. Setiap checkpoint di organisasi LibreYOLO memiliki lisensi, dan lisensinya tidak selalu sama dalam satu family. Repositori tersebut adalah sumber resmi. Ringkasan di bawah menjelaskan ketentuan yang berlaku saat halaman ini terakhir diverifikasi.

Ini adalah deskripsi lisensi yang terlibat, bukan nasihat hukum. Jika jawabannya penting secara komersial, baca sendiri lisensinya dan mintalah nasihat dari penasihat hukum Anda.

Karya asli: Marigold V2, Huawei Bayer Lab
Lisensi upstream: Apache-2.0
Sumber upstream: github.com/huawei-bayerlab/marigold-v2
Kode LibreYOLO: MIT
Bobot: Apache-2.0, dipublikasikan ulang di huggingface.co/LibreYOLO
Interpretasi: The adapters and separately acquired Qwen image base declare Apache-2.0.