Super-squash branch 'main' using huggingface_hub

.gitattributes

@@ -0,0 +1,41 @@
+*.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
+autoencoder.jit filter=lfs diff=lfs merge=lfs -text
+decoder.jit filter=lfs diff=lfs merge=lfs -text
+encoder.jit filter=lfs diff=lfs merge=lfs -text
+tokenizer/autoencoder.jit filter=lfs diff=lfs merge=lfs -text
+tokenizer/decoder.jit filter=lfs diff=lfs merge=lfs -text
+tokenizer/encoder.jit filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,54 @@
+---
+license: apache-2.0
+tags:
+  - video
+  - relighting
+  - inverse-rendering
+  - diffusion
+  - cosmos
+pipeline_tag: image-to-image
+---
+
+# World Inverse Renderer
+
+Video inverse rendering model based on NVIDIA Cosmos 7B video diffusion transformer, fine-tuned on [custom dataset](https://github.com/ShandaAI/AlayaRenderer?tab=readme-ov-file).
+
+## Model Description
+
+This model performs **inverse rendering** on images and videos: given an input RGB frame, it estimates physically-based G-buffer maps:
+
+- **Basecolor** (albedo)
+- **Normal** (surface normals)
+- **Depth**
+- **Roughness**
+- **Metallic**
+
+These G-buffers can then be used with a forward renderer to relight the scene under arbitrary environment lighting (HDRI maps).
+
+## Architecture
+
+- Based on NVIDIA Cosmos 7B video diffusion transformer
+- Fine-tuned on [custom dataset](https://github.com/ShandaAI/AlayaRenderer?tab=readme-ov-file)
+- Supports both single-image and multi-frame video inverse rendering
+
+## Usage
+
+```bash
+# Inverse rendering on images
+CUDA_HOME=$CONDA_PREFIX PYTHONPATH=$(pwd) python cosmos_predict1/diffusion/inference/inference_inverse_renderer.py \
+    --checkpoint_dir checkpoints --diffusion_transformer_dir Diffusion_Renderer_Inverse_Cosmos_7B \
+    --dataset_path=your_input_images/ --num_video_frames 1 --group_mode webdataset \
+    --video_save_folder=output/ --save_video=False
+
+# Inverse rendering on video frames
+CUDA_HOME=$CONDA_PREFIX PYTHONPATH=$(pwd) python cosmos_predict1/diffusion/inference/inference_inverse_renderer.py \
+    --checkpoint_dir checkpoints --diffusion_transformer_dir Diffusion_Renderer_Inverse_Cosmos_7B \
+    --dataset_path=your_video_frames/ --num_video_frames 57 \
+    --video_save_folder=output/
+```
+
+## Requirements
+
+- Python 3.10
+- NVIDIA GPU with >= 16GB VRAM (48GB+ recommended)
+- CUDA 12.0+

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d29e1ebc916fd704e81b2f32eb9b3098568647ea0220143367a2e715e235835e
+size 28940339610