EO VAE

--- license: apache-2.0 library_name: diffusers pipeline_tag: image-to-image base_model: nilsleh/eo-vae language: - en tags: - remote-sensing - earth-observation - vae - tokenizer - multi-spectral --- # EO-VAE Earth Observation Variational Autoencoder. Self-contained, no external eo-vae package—uses only `torch`, `safetensors`, and `huggingface_hub`. ## Usage ```python from huggingface_hub import snapshot_download import sys import torch model_dir = snapshot_download("BiliSakura/EO-VAE") sys.path.insert(0, model_dir) from eo_vae import EOVAEModel, WAVELENGTHS vae = EOVAEModel.from_pretrained(model_dir, torch_dtype=torch.float32, device="cpu") x = torch.randn(1, 3, 256, 256) wvs = torch.tensor(WAVELENGTHS["S2RGB"], dtype=torch.float32) with torch.no_grad(): recon = vae.reconstruct(x, wvs) z = vae.encode_spatial_normalized(x, wvs) # [1, 32, 32, 32] ``` ## Model | Property | Value | |----------|-------| | Architecture | Flux-style VAE with wavelength-conditioned dynamic convolutions | | Input | [B, C, 256, 256] + wavelengths [C] | | Latent | [B, 32, 32, 32] (spatial) or [B, 128, 16, 16] (packed) | | Modalities | S2RGB, S2L2A, S1RTC, S1GRD | ## Wavelengths (µm) | Modality | Values | |----------|--------| | S2RGB | 0.665, 0.56, 0.49 | | S1RTC | 5.4, 5.6 | | S2L2A | 0.443, 0.490, 0.560, 0.665, 0.705, 0.740, 0.783, 0.842, 0.865, 1.610, 2.190, 0.945 | | S2L1C | 0.443, 0.490, 0.560, 0.665, 0.705, 0.740, 0.783, 0.842, 0.865, 0.945, 1.375, 1.610, 2.190 | ## Citation ```bibtex @article{eo-vae, title={EO-VAE: Towards A Multi-sensor Tokenizer for Earth Observation Data}, author={Lehmann, Nils and Wang, Yi and Xiong, Zhitong and Zhu, Xiaoxiang}, journal={arXiv preprint arXiv:2602.12177}, year={2026} } ```

Source context: 41 downloads · 0 likes · Pipeline image-to-image · Library diffusers · Repo BiliSakura/EO-VAE

Source context: 16 downloads · 0 likes · Pipeline image-to-image · Library diffusers · Repo BiliSakura/EO-VAE