Upload 3 files

README.md

@@ -4,12 +4,15 @@ emoji: 🖼️
 colorFrom: blue
 colorTo: green
 sdk: gradio
-sdk_version: 4.28.3 # requirements.txt と合わせるか確認
+sdk_version: 4.28.3 # Make sure this matches your gradio version
 app_file: app.py
-license: apache-2.0 # または適切なライセンス
-# Pinned Hardware: T4 small (GPU) or CPU upgrade (CPU)
-# pinned: false # 必要に応じてTrueに
-# hardware: cpu-upgrade # or cuda-t4-small
+license: apache-2.0 # Or your preferred license
+# Hardware Selection:
+# For CPU execution (recommended if GPU isn't strictly needed):
+# hardware: cpu-upgrade 
+# For GPU execution (requires compatible CUDA setup):
+# hardware: cuda-t4-small 
+# pinned: false # Set to true if you want to pin the hardware
 # hf_token: YOUR_HF_TOKEN # Use secrets instead!
 ---
 
@@ -28,4 +31,5 @@ Model Repository: [celstk/wd-eva02-lora-onnx](https://huggingface.co/celstk/wd-e
 
 **Note:**
 - This Space uses a model from a **private** repository (`celstk/wd-eva02-lora-onnx`). You might need to duplicate this space and add your Hugging Face token (`HF_TOKEN`) to the Space secrets to allow downloading the model files.
-- Image pasting behavior might vary across browsers. 
+- Image pasting behavior might vary across browsers.
+- If you require GPU acceleration, uncomment the `hardware: cuda-t4-small` line above and ensure the environment has the necessary CUDA libraries compatible with `onnxruntime-gpu`. The current setup defaults to CPU due to potential CUDA library mismatches in the standard Spaces environment. 

requirements.txt

@@ -1,4 +1,4 @@
-onnxruntime-gpu>=1.16.0 # または onnxruntime>=1.16.0 (CPUのみの場合)
+onnxruntime>=1.16.0 # CPU版
 numpy
 Pillow
 matplotlib