Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,26 +1,10 @@
|
|
| 1 |
---
|
| 2 |
-
title: CL EVA02
|
| 3 |
emoji: 🖼️
|
| 4 |
colorFrom: purple
|
| 5 |
colorTo: blue
|
| 6 |
sdk: gradio
|
| 7 |
-
sdk_version: 5.
|
| 8 |
app_file: app.py
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
# WD EVA02 LoRA ONNX Tagger (CPU)
|
| 12 |
-
|
| 13 |
-
This Space is a duplicate/fork of https://huggingface.co/spaces/cella110n/cl_tagger and it demonstrates image tagging using a fine-tuned WD EVA02 model (converted to ONNX format).
|
| 14 |
-
|
| 15 |
-
**How to Use:**
|
| 16 |
-
1. Upload an image using the upload button.
|
| 17 |
-
2. Alternatively, paste an image URL into the browser (experimental paste handling).
|
| 18 |
-
3. Adjust the tag thresholds if needed.
|
| 19 |
-
4. Choose the output mode (Tags only or include visualization).
|
| 20 |
-
5. Click the "Predict" button.
|
| 21 |
-
|
| 22 |
-
**Note:**
|
| 23 |
-
- ~~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.~~
|
| 24 |
-
- This space uses a model from the public https://huggingface.co/cella110n/cl_tagger repo.
|
| 25 |
-
- Unlike the original repo which runs on Zero-GPU hardware, this one runs on CPU only.
|
| 26 |
-
- Image pasting behavior might vary across browsers.
|
|
|
|
| 1 |
---
|
| 2 |
+
title: CL EVA02 Tagger (CPU-ONNX)
|
| 3 |
emoji: 🖼️
|
| 4 |
colorFrom: purple
|
| 5 |
colorTo: blue
|
| 6 |
sdk: gradio
|
| 7 |
+
sdk_version: 6.5.1
|
| 8 |
app_file: app.py
|
| 9 |
+
short_description: (Anime) Image tagger using Danbooru tags
|
| 10 |
+
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|