Add files using upload-large-folder tool

README.md

@@ -0,0 +1,48 @@
+---
+license: mit
+language:
+  - en
+pipeline_tag: image-to-image
+library_name: pytorch
+tags:
+  - pix2pixhd
+  - image-translation
+  - cityscapes
+  - checkpoint
+---
+
+# BiliSakura/Pix2PixHD-ckpt
+
+Packaged Pix2PixHD checkpoint from `models/raw/Pix2PixHD`.
+
+## Variant
+
+| Model | Export format | Notes |
+| --- | --- | --- |
+| `cityscapes` | `generator/diffusion_pytorch_model.safetensors` | local-enhancer style generator checkpoint |
+
+## Repository layout
+
+```text
+Pix2PixHD-ckpt/
+  cityscapes/
+    generator/
+      config.json
+      diffusion_pytorch_model.safetensors
+```
+
+## Notes
+
+- A normalized safetensors export is included under `generator/`.
+- This checkpoint appears to be local-enhancer style (`model1_*` modules), so it is not a strict drop-in for the current `Pix2PixHDGenerator` wrapper.
+
+## Citation
+
+```bibtex
+@inproceedings{wang2018pix2pixHD,
+  title={High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs},
+  author={Wang, Ting-Chun and Liu, Ming-Yu and Zhu, Jun-Yan and Tao, Andrew and Kautz, Jan and Catanzaro, Bryan},
+  booktitle={CVPR},
+  year={2018}
+}
+```

cityscapes/generator/config.json

@@ -0,0 +1,10 @@
+{
+  "_class_name": "Pix2PixHDGenerator",
+  "input_nc": 36,
+  "output_nc": 3,
+  "ngf": 64,
+  "n_downsampling": 4,
+  "n_blocks": 9,
+  "norm": "instance",
+  "source_checkpoint": "latest_net_G.pth"
+}

cityscapes/generator/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f740477201464d0448df284c508d5d6cc2ef44969ff969171452a77b3c7a2de1
+size 731435388