Upload README.md with huggingface_hub

README.md

@@ -37,6 +37,22 @@ compdiff_pipeline.py        # turnkey CompDiffPipeline (demographic-conditioned
 training_config.yaml        # full training configuration
 ```
 
+## Requirements
+
+```bash
+pip install "diffusers>=0.35" transformers accelerate huggingface_hub safetensors pillow
+```
+
+Install **torch to match your CUDA driver** — a bare `pip install torch` may pull a build
+newer than your driver supports (e.g. a `cu130` wheel on a CUDA 12.4 driver fails with
+"NVIDIA driver too old" / `cuda available: False`). Pick the wheel for your CUDA version
+from [pytorch.org](https://pytorch.org/get-started/locally/). Tested combo (A100, driver
+550.x / CUDA 12.4):
+
+```bash
+pip install torch==2.6.0 --index-url https://download.pytorch.org/whl/cu124
+```
+
 ## Quickstart (demographic-conditioned)
 
 The bundled `compdiff_pipeline.py` reproduces the exact generation used in the paper —