Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,150 @@
----
-license: cc-by-nc-sa-4.0
----
+---
+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
+  - controlnet
+  - image-generation
+  - synthetic-data
+  - ship-detection
+  - earth-observation
+  - sentinel-1
+---
+
+# SAR ControlNet
+
+## Overview
+
+**ControlNet** for spatially controlled synthesis of **Sentinel-1 SAR** images.  
+Published alongside the paper **"Diffusion-Based SAR Training Data Synthesis Controlled by Spatial Annotations"** (GCPR 2026).
+
+This model must be used together with the corresponding Stable Diffusion backbone:  
+[`sylviaHoch/SAR-StableDiffusion`](https://huggingface.co/sylviaHoch/SAR-StableDiffusion)
+
+Spatial control is provided via three-channel one-hot masks (water / ship / land), enabling precise placement of ships in the generated SAR images.
+
+---
+
+## Database
+The ControlNet was trained on the training set of **OpenSARShip Ship Detection Dataset (OSSDD)** [[dataset]](https://huggingface.co/datasets/sylviaHoch/OpenSARShip-Ship-Detection-Dataset), a Sentinel-1 dataset with 15,161 patches (700 × 700 px) and 64,640 ships, providing rotated bounding boxes (RBBs) and land–water masks. Text captions used during ControlNet training depend on land coverage: open-water patches are captioned *"An aerial view of ships on open water."*, patches with land (> 5 % of pixels) *"An aerial view of a coastal area with ships on the water."* During training, 512 × 512 crops are extracted, amplitude values converted to dB and linearly mapped to `[-1, 1]`.
+
+## Architecture
+
+| Component | Details |
+|---|---|
+| Type | ControlNet (based on SD 1.5 UNet) |
+| Control input — ship + land | Three-channel one-hot mask `(3, H, W)` — ch0: background, ch1: ship, ch2: land |
+| Required backbone | [`sylviaHoch/SAR-StableDiffusion`](https://huggingface.co/sylviaHoch/SAR-StableDiffusion) |
+
+---
+
+## Repository Structure
+
+```text
+SAR-ControlNet/
+├── config.json
+└── diffusion_pytorch_model.safetensors
+```
+
+---
+
+## Usage
+
+This model can be used directly with the 🤗 [diffusers](https://github.com/huggingface/diffusers) ControlNet pipeline. It requires the corresponding Stable Diffusion backbone ([`sylviaHoch/SAR-StableDiffusion`](https://huggingface.co/sylviaHoch/SAR-StableDiffusion)).
+
+**Requirements:**
+- `torch`
+- `diffusers`
+- `peft`
+
+**Control input:** The control image must be a three-channel, one-hot encoded mask of size **512 × 512**, i.e. a tensor of shape `(3, 512, 512)` with values in `{0, 1}`. Each pixel is assigned to exactly one class across the three channels:
+
+- **Channel 0:** water
+- **Channel 1:** ship (represented as rotated bounding box/ minimal enclosing rectangle)
+- **Channel 2:** land
+
+**Output:** `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`, single-channel SAR amplitude), and `H` and `W` the native model resolution.
+
+```python
+import torch
+from diffusers import ControlNetModel, StableDiffusionControlNetPipeline, UniPCMultistepScheduler
+from peft import PeftModel
+
+SD_MODEL_ID = "sylviaHoch/SAR-StableDiffusion"
+CN_MODEL_ID = "sylviaHoch/SAR-ControlNet"
+
+# control_image: torch.Tensor of shape (3, 512, 512), one-hot encoded
+#   channel 0: water, channel 1: ship, channel 2: land
+
+controlnet = ControlNetModel.from_pretrained(CN_MODEL_ID, torch_dtype=torch.float16)
+
+pipeline = StableDiffusionControlNetPipeline.from_pretrained(
+    SD_MODEL_ID,
+    controlnet=controlnet,
+    torch_dtype=torch.float16
+).to("cuda")
+
+# Load LoRA text-encoder adapter
+pipeline.text_encoder = PeftModel.from_pretrained(
+    pipeline.text_encoder,
+    SD_MODEL_ID,
+    subfolder="adapter_text_encoder"
+)
+
+pipeline.scheduler = UniPCMultistepScheduler.from_config(pipeline.scheduler.config)
+
+# Generate
+image = pipeline(
+    "An aerial view of ships on open water.",
+    control_image,
+    num_inference_steps=50,
+    guidance_scale=7.5,
+    controlnet_conditioning_scale=1.0,
+    output_type="pt"
+).images
+```
+
+---
+
+## Intended Use
+
+- Spatially controlled synthesis of Sentinel-1 SAR training data.
+- Ship placement guided by spatial annotations.
+- Training data generation or data augmentation for ship detection models.
+
+## Limitations
+
+- Tuned specifically to **Sentinel-1** sensor characteristics (in particular Sentinel-1 GRD products in VH polarization).
+- Training scenes are limited to harbour, coastal, and open water scenes.
+- 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.
+```

config.json

@@ -0,0 +1,51 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.36.0.dev0",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "class_embed_type": null,
+  "conditioning_channels": 3,
+  "conditioning_embedding_out_channels": [
+    16,
+    32,
+    96,
+    256
+  ],
+  "controlnet_conditioning_channel_order": "rgb",
+  "cross_attention_dim": 768,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "global_pool_conditions": false,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_time_scale_shift": "default",
+  "transformer_layers_per_block": 1,
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e89f9a3711fdde52116811a065d1b9a0e17bacf10aa6ca3d0ce3e573f227c72
+size 1445157120