| ---
|
| license: cc-by-nc-sa-4.0
|
| language:
|
| - en
|
| library_name: diffusers
|
| pipeline_tag: text-to-image
|
| tags:
|
| - sar
|
| - synthetic-aperture-radar
|
| - remote-sensing
|
| - stable-diffusion
|
| - image-generation
|
| - synthetic-data
|
| - ship-detection
|
| - earth-observation
|
| - sentinel-1
|
| ---
|
|
|
| # SAR Stable Diffusion
|
|
|
| ## Overview
|
|
|
| Fine-tuned **Stable Diffusion 1.5** backbone for generating synthetic **Sentinel-1 SAR** amplitude images from text prompts.
|
| Published alongside the upcoming paper **"Diffusion-Based SAR Training Data Synthesis Controlled by Spatial Annotations"** (Hochstuhl et al., 2026; accepted for GCPR conference 2026).
|
|
|
| The model generates single-channel SAR amplitude images for specific land cover types similar to Sentinel-1 GRD image products (in VH polarization).
|
|
|
| > For spatially controlled generation via ship/land masks, use this model together with
|
| > [`sylviaHoch/SAR-ControlNet`](https://huggingface.co/sylviaHoch/SAR-ControlNet).
|
|
|
| ---
|
|
|
| ## Database
|
| The model was fine-tuned on Sentinel-1 acquisitions from the [`SEN12MS dataset`](https://github.com/schmitt-muc/SEN12MS) dataset. The corresponding text prompts were derived from the dataset's land cover maps, using the dominant land cover class within each image patch. Possible land cover classes are:
|
| - Evergreen Needleleaf Forest
|
| - Evergreen Broadleaf Forest
|
| - Deciduous Needleleaf Forest
|
| - Deciduous Broadleaf Forest
|
| - Mixed Forest
|
| - Closed Shrublands
|
| - Open Shrublands
|
| - Woody Savannas
|
| - Savannas
|
| - Grasslands
|
| - Permanent Wetlands
|
| - Croplands
|
| - Urban and Built-up
|
| - Cropland/Natural Vegetation Mosaic
|
| - Snow and Ice
|
| - Barren or Sparsely Vegetated
|
| - Water Bodies
|
|
|
| ---
|
|
|
| ## Architecture
|
|
|
| | Component | Details |
|
| |---|---|
|
| | Base model | Stable Diffusion 1.5 |
|
| | VAE decoder | Adapted to **single-channel** output |
|
| | Text encoder | Fine-tuned with a **LoRA adapter** (`adapter_text_encoder/`) |
|
| | Output | Single-channel float32 SAR amplitude image |
|
| ---
|
|
|
| ## Repository Structure
|
|
|
| ```text
|
| SAR-StableDiffusion/
|
| ├── model_index.json
|
| ├── unet/
|
| ├── vae/ # Modified: single-channel conv_out
|
| ├── text_encoder/
|
| ├── tokenizer/
|
| ├── scheduler/
|
| ├── feature_extractor/
|
| └── adapter_text_encoder/ # LoRA adapter for text encoder
|
| ├── adapter_config.json
|
| └── adapter_model.safetensors
|
| ```
|
|
|
| ---
|
|
|
| ## Usage
|
| This model can be used directly with the 🤗 [diffusers](https://github.com/huggingface/diffusers) pipeline.
|
| The LoRA adapter for the text encoder is included in this repository and must be loaded manually after initialising the pipeline.
|
|
|
| **Requirements:**
|
| - `torch` (CUDA recommended)
|
| - `diffusers`
|
| - `peft`
|
|
|
| ### Text-to-Image Generation
|
|
|
| ```python
|
| import torch
|
| from diffusers import StableDiffusionPipeline
|
| from peft import PeftModel
|
|
|
| MODEL_ID = "sylviaHoch/SAR-StableDiffusion"
|
|
|
| # Load pipeline
|
| pipeline = StableDiffusionPipeline.from_pretrained(
|
| MODEL_ID,
|
| torch_dtype=torch.float16
|
| ).to("cuda")
|
|
|
| # Load LoRA text-encoder adapter
|
| pipeline.text_encoder = PeftModel.from_pretrained(
|
| pipeline.text_encoder,
|
| MODEL_ID,
|
| subfolder="adapter_text_encoder"
|
| )
|
|
|
| # Generate
|
| image = pipeline(
|
| "Woody Savannas.",
|
| num_inference_steps=50,
|
| guidance_scale=3.0,
|
| output_type="pt"
|
| ).images
|
|
|
| ```
|
|
|
| >image is a torch.Tensor of shape (N, C, H, W) with values in the range [0, 1] and dtype float32, where N is the batch size (here 1), C the number of channels (here 1, grayscale), and H and W the native model resolution (512 x 512).
|
| ---
|
|
|
| ## Intended Use
|
|
|
| - Synthetic SAR data generation for given land cover types.
|
| - Research on generative models for remote sensing.
|
|
|
| ## Limitations
|
|
|
| - Tuned specifically to **Sentinel-1** sensor characteristics based on GRD products in VH polarization; transferability to other sensors and imaging properties is very limited.
|
| - Generated images are synthetic and may not fully capture all real SAR image properties.
|
|
|
| ---
|
|
|
| <!-- ## Citation
|
|
|
| If you use this model, please cite:
|
|
|
| ```bibtex
|
| @inproceedings{sar_diffusion_gcpr2026,
|
| title = {Diffusion-Based SAR Training Data Synthesis Controlled by Spatial Annotations},
|
| booktitle = {German Conference on Pattern Recognition (GCPR)},
|
| year = {2026},
|
| note = {accepted, to be published},
|
| authors = {}
|
| }
|
| ```
|
|
|
| --- -->
|
|
|
| ## License
|
|
|
| This model is released under **CC BY-NC-SA 4.0**.
|
| Commercial use is not permitted. Derivatives must be shared under the same license.
|
| See [LICENSE](https://creativecommons.org/licenses/by-nc-sa/4.0/) for details.
|
|
|
