Pre-trained checkpoints

.gitattributes

@@ -0,0 +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

README.md

@@ -0,0 +1,53 @@
+---
+base_model:
+  - stabilityai/stable-diffusion-2
+pipeline_tag: image-to-image
+library_name: diffusers
+tags:
+  - reflection-removal
+  - reflection-separation
+  - image-restoration
+  - diffusion
+  - stable-diffusion
+  - cvpr2026
+---
+
+# Reflection Separation from a Single Image via Joint Latent Diffusion
+
+Pre-trained checkpoints for the CVPR 2026 paper. Given a single photo taken
+through glass, the model jointly generates the **transmission** and
+**reflection** layers.
+
+- 🌐 Project page: https://brian90709.github.io/diff-reflection-separation/
+- 💻 Code: https://github.com/Brian90709/diff-reflection-separation-code
+- 📄 Paper: arXiv (coming soon)
+
+[Zheng-Hui Huang](https://github.com/Brian90709), [Zhixiang Wang](https://lightchaserx.github.io), [Yu-Lun Liu](https://yulunalexliu.github.io), [Yung-Yu Chuang](https://www.csie.ntu.edu.tw/~cyy/)
+
+## Files
+
+| File | Size | Description |
+| --- | --- | --- |
+| `iter_016000/unet/diffusion_pytorch_model.bin` | ~3.5 GB | Trained layer-separation UNet. |
+| `fuse_blocks.bin` | ~264 MB | CFW refiner for the VAE decoder. |
+| `lrm/iter_008000/aux_net.bin` | ~1.3 MB | Latent composition module (LRM), used by `--optimization`. |
+
+## Usage
+
+Download the weights into `./checkpoints`, then follow the
+[code repository](https://github.com/Brian90709/diff-reflection-separation-code):
+
+```bash
+huggingface-cli download Brian9999/diff-reflection-separation --repo-type model --local-dir ./checkpoints
+```
+
+## Citation
+
+```bibtex
+@inproceedings{huang2026reflection,
+  title     = {Reflection Separation from a Single Image via Joint Latent Diffusion},
+  author    = {Huang, Zheng-Hui and Wang, Zhixiang and Liu, Yu-Lun and Chuang, Yung-Yu},
+  booktitle = {CVPR},
+  year      = {2026}
+}
+```

fuse_blocks.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec25a78ead2d6da001dee231a046a8f39ddc435e4fc5190dbb77005099db7286
+size 264297122

iter_016000/unet/config.json

@@ -0,0 +1,73 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.31.0.dev0",
+  "_name_or_path": "/home/hhh/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2/snapshots/1e128c8891e52218b74cde8f26dbfc701cb99d79/unet",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 1024,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 8,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "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,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 96,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": true
+}

iter_016000/unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b27f744b524588624b16ec7ced9b688b3518e9c74ef31eae8fd3c9b0d4910133
+size 3463944196

lrm/iter_008000/aux_net.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b1a5549aa62c130e25bd89cfc6bdede1a3507564f8e395a379d861f17ac91c1
+size 1289162