Update README with better feature descriptions and GPU info

README.md

@@ -16,13 +16,20 @@ hardware: cpu-basic
 Virtual staining of H&E histopathology images to IHC (HER2, Ki67, ER, PR) using a single unified 42M-parameter SPADE-UNet conditioned on dense spatial tokens from a frozen UNI pathology foundation model.
 
 ## Features
-- **Upload** an H&E image and generate IHC stains in real-time
-- **Cross-stain comparison**: Generate all 4 stains from a single input
-- **Gallery**: Browse pre-computed examples (no GPU needed)
+
+- **Gallery** — Browse 16 pre-computed examples from BCI and MIST datasets (no GPU needed)
+- **Virtual Staining** — Upload an H&E image and generate any IHC stain (GPU required)
+- **Cross-Stain Comparison** — Generate all 4 stains from a single H&E input (GPU required)
 
 ## Architecture
+
 | Component | Details |
 |-----------|---------|
 | Generator | SPADE-UNet with UNI spatial conditioning + FiLM stain embeddings |
 | UNI Features | 4x4 sub-crop tiling → UNI ViT-L/16 → 32x32 spatial tokens (1024-dim) |
 | Parameters | 42M (generator), UNI frozen (303M) |
+
+## GPU Support
+
+- **Gallery tab** works on CPU (default hardware)
+- **Live inference** requires GPU — set Space hardware to ZeroGPU (HF Pro) or run locally with `python app.py`