Add DiffHDR model card

README.md

@@ -0,0 +1,180 @@
+---
+license: apache-2.0
+base_model: Wan-AI/Wan2.1-VACE-14B
+base_model_relation: adapter
+tags:
+  - lora
+  - safetensors
+  - diffsynth
+  - diffusion
+  - video-to-video
+  - image-to-image
+  - hdr
+  - ldr-to-hdr
+  - inverse-tone-mapping
+  - panorama
+  - wan2.1
+  - vace
+---
+
+# DiffHDR
+
+DiffHDR reconstructs high-dynamic-range (HDR) radiance from low-dynamic-range
+(LDR) videos and images using LoRA-finetuned
+[Wan2.1-VACE-14B](https://huggingface.co/Wan-AI/Wan2.1-VACE-14B). It formulates
+LDR-to-HDR conversion as generative radiance inpainting in Log-Gamma space and
+supports text- and reference-image-guided reconstruction.
+
+- **Paper:** [DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models](https://arxiv.org/abs/2604.06161)
+- **Code and full inference instructions:** [Eyeline-Labs/DiffHDR](https://github.com/Eyeline-Labs/DiffHDR)
+- **Base model:** [Wan-AI/Wan2.1-VACE-14B](https://huggingface.co/Wan-AI/Wan2.1-VACE-14B)
+
+## Model files
+
+This repository contains LoRA adapters, not a standalone model. Download the
+base model separately before running inference.
+
+| File | Intended inference entry points |
+| --- | --- |
+| `DiffHDR.safetensors` | `infer_video.py`, `infer_image.py`, and `infer_long_video.py` |
+| `DiffHDR_Pano.safetensors` | `infer_hdri.py` for 360-degree HDR panoramas |
+
+## Setup
+
+Clone and install the inference code:
+
+```bash
+git clone https://github.com/Eyeline-Labs/DiffHDR.git
+cd DiffHDR
+
+conda create -n diffhdr python=3.10 -y
+conda activate diffhdr
+
+pip install torch==2.6.0 torchvision==0.21.0 torchaudio==2.6.0 \
+    --index-url https://download.pytorch.org/whl/cu118
+pip install -e .
+pip install -r requirements.txt
+```
+
+Download the base model and the DiffHDR adapters:
+
+```bash
+hf download Wan-AI/Wan2.1-VACE-14B \
+    --local-dir models/Wan-AI/Wan2.1-VACE-14B
+
+hf download ZhengmingYu/DiffHDR --local-dir models
+```
+
+The Wan2.1-VACE-14B download is approximately 75 GB and is not included in this
+repository. Set `MODEL_BASE` if you store the base model somewhere other than
+`models/`.
+
+## Inference
+
+Minimal video example:
+
+```bash
+python infer_video.py \
+    --lora_path models/DiffHDR.safetensors \
+    --input_path demo/room_window.mp4 \
+    --output_dir results/video_mp4 \
+    --prompt "" \
+    --num_inference_steps 10 \
+    --add_mask --use_under_exposure_mask --crop_and_resize --srgb_to_lg
+```
+
+Additional entry points:
+
+```bash
+# Single image
+python infer_image.py \
+    --lora_path models/DiffHDR.safetensors \
+    --input_path demo/sample_image.png \
+    --output_dir results/image_output \
+    --prompt ""
+
+# Long video using overlapping temporal windows
+python infer_long_video.py \
+    --lora_path models/DiffHDR.safetensors \
+    --input_path demo/long_video_frames \
+    --output_dir results/long_video_output \
+    --prompt "" \
+    --window_size 33 --window_stride 16 \
+    --use_prev_window_reference \
+    --add_mask --crop_and_resize --srgb_to_lg
+
+# 360-degree LDR panorama to HDR panorama
+python infer_hdri.py \
+    --lora_path models/DiffHDR_Pano.safetensors \
+    --input_path demo/sample_pano.png \
+    --output_dir results/hdri_output
+```
+
+The inference scripts write linear HDR OpenEXR output. Video inference writes
+one EXR file per frame; panorama inference writes `predicted.exr`. See the
+[code repository README](https://github.com/Eyeline-Labs/DiffHDR#inference) for
+text conditioning, reference-image conditioning, arguments, and additional
+examples.
+
+## Intended use
+
+DiffHDR is intended for research and creative LDR-to-HDR reconstruction,
+including:
+
+- reconstructing HDR video or still images from LDR input;
+- recovering plausible highlight and shadow content for display and
+  post-production workflows;
+- text- or reference-image-guided HDR reconstruction; and
+- reconstructing HDR environment panoramas.
+
+## Limitations and responsible use
+
+- Detail in clipped or quantized regions is generated by the model. It is a
+  plausible reconstruction and is not guaranteed to reproduce the original
+  scene radiance.
+- Outputs may contain hallucinated detail, temporal inconsistency, color
+  shifts, or exposure artifacts, especially on inputs outside the training
+  distribution.
+- Results can vary with prompts, reference images, random seeds, and inference
+  settings.
+- The model inherits limitations and potential biases from its base model and
+  training data.
+- Do not use generated output as a calibrated radiometric measurement, as
+  forensic evidence, or in safety-critical decisions.
+- Users are responsible for ensuring that their input media and intended use
+  comply with applicable rights, licenses, and laws.
+
+## Training and evaluation
+
+DiffHDR is trained as a LoRA adapter on top of Wan2.1-VACE-14B. The training
+approach uses synthetic HDR video data derived from static HDR environment maps
+to address the scarcity of paired HDR video data. Method details, experimental
+settings, and comparisons are reported in the
+[paper](https://arxiv.org/abs/2604.06161).
+
+## License
+
+The DiffHDR LoRA adapter weights in this repository are released under the
+[Apache License 2.0](LICENSE).
+
+The Wan2.1-VACE-14B base weights are distributed separately and remain subject
+to their own license and model-card guidance. This license does not grant rights
+to third-party code, datasets, or user-supplied input content.
+
+## Citation
+
+```bibtex
+@article{yu2026diffhdr,
+  title={DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models},
+  author={Yu, Zhengming and Ma, Li and He, Mingming and Isikdogan, Leo and Xu, Yuancheng and Smirnov, Dmitriy and Salamanca, Pablo and Mi, Dao and Delgado, Pablo and Yu, Ning and others},
+  journal={arXiv preprint arXiv:2604.06161},
+  year={2026}
+}
+```
+
+## Acknowledgements
+
+DiffHDR builds on
+[Wan2.1-VACE-14B](https://huggingface.co/Wan-AI/Wan2.1-VACE-14B) and
+[DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio). Please also
+credit and follow the license terms of these upstream projects.