Update README.md
Browse files
README.md
CHANGED
@@ -1,31 +1,29 @@
|
|
1 |
-
---
|
2 |
-
title:
|
3 |
-
emoji: 🖼️
|
4 |
-
colorFrom: blue
|
5 |
-
colorTo: green
|
6 |
-
sdk: gradio
|
7 |
-
sdk_version: 4.43.0 # requirements.txt と合わせるか確認
|
8 |
-
app_file: app.py
|
9 |
-
license: apache-2.0 # または適切なライセンス
|
10 |
-
# Pinned Hardware: T4 small (GPU) or CPU upgrade (CPU)
|
11 |
-
# pinned: false # 必要に応じてTrueに
|
12 |
-
# hardware: cpu-upgrade # or cuda-t4-small
|
13 |
-
# hf_token: YOUR_HF_TOKEN # Use secrets instead!
|
14 |
-
---
|
15 |
-
|
16 |
-
#
|
17 |
-
|
18 |
-
This Space demonstrates image tagging using a fine-tuned WD EVA02 model (converted to ONNX format).
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
**Note:**
|
30 |
-
- 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.
|
31 |
- Image pasting behavior might vary across browsers.
|
|
|
1 |
+
---
|
2 |
+
title: CL EVA02 LoRA ONNX Tagger
|
3 |
+
emoji: 🖼️
|
4 |
+
colorFrom: blue
|
5 |
+
colorTo: green
|
6 |
+
sdk: gradio
|
7 |
+
sdk_version: 4.43.0 # requirements.txt と合わせるか確認
|
8 |
+
app_file: app.py
|
9 |
+
# license: apache-2.0 # または適切なライセンス
|
10 |
+
# Pinned Hardware: T4 small (GPU) or CPU upgrade (CPU)
|
11 |
+
# pinned: false # 必要に応じてTrueに
|
12 |
+
# hardware: cpu-upgrade # or cuda-t4-small
|
13 |
+
# hf_token: YOUR_HF_TOKEN # Use secrets instead!
|
14 |
+
---
|
15 |
+
|
16 |
+
# CL EVA02 LoRA ONNX Tagger
|
17 |
+
|
18 |
+
This Space demonstrates image tagging using a fine-tuned WD EVA02 model (converted to ONNX format).
|
19 |
+
|
20 |
+
**How to Use:**
|
21 |
+
1. Upload an image using the upload button.
|
22 |
+
2. Alternatively, paste an image URL into the browser (experimental paste handling).
|
23 |
+
3. Adjust the tag thresholds if needed.
|
24 |
+
4. Choose the output mode (Tags only or include visualization).
|
25 |
+
5. Click the "Predict" button.
|
26 |
+
|
27 |
+
**Note:**
|
28 |
+
- 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.
|
|
|
|
|
29 |
- Image pasting behavior might vary across browsers.
|