Spaces:
Running
Running
schirrmacher
commited on
Upload folder using huggingface_hub
Browse files- app.py +4 -1
- explanation.jpg +0 -0
app.py
CHANGED
@@ -62,7 +62,10 @@ title = "Open Remove Background Model (ormbg)"
|
|
62 |
description = r"""
|
63 |
This model is a <strong>fully open-source background remover</strong> optimized for images with humans.
|
64 |
It is based on [Highly Accurate Dichotomous Image Segmentation research](https://github.com/xuebinqin/DIS).
|
65 |
-
|
|
|
|
|
|
|
66 |
|
67 |
This is the first iteration of the model, so there will be improvements!
|
68 |
If you identify cases where the model fails, <a href='https://huggingface.co/schirrmacher/ormbg/discussions' target='_blank'>upload your examples</a>!
|
|
|
62 |
description = r"""
|
63 |
This model is a <strong>fully open-source background remover</strong> optimized for images with humans.
|
64 |
It is based on [Highly Accurate Dichotomous Image Segmentation research](https://github.com/xuebinqin/DIS).
|
65 |
+
|
66 |
+
The model was trained with the synthetic [Human Segmentation Dataset](https://huggingface.co/datasets/schirrmacher/humans). A dataset crafted with [LayerDiffuse](https://github.com/layerdiffusion/LayerDiffuse) and [IC-Light](https://github.com/lllyasviel/IC-Light).
|
67 |
+
|
68 |
+
<img src="explanation.jpg" alt="Background Remover Model" style="width:100%;height:auto;">
|
69 |
|
70 |
This is the first iteration of the model, so there will be improvements!
|
71 |
If you identify cases where the model fails, <a href='https://huggingface.co/schirrmacher/ormbg/discussions' target='_blank'>upload your examples</a>!
|
explanation.jpg
ADDED