Instructions to use baker76/imageback-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- BiRefNet
How to use baker76/imageback-models with BiRefNet:
# Option 1: use with transformers from transformers import AutoModelForImageSegmentation birefnet = AutoModelForImageSegmentation.from_pretrained("baker76/imageback-models", trust_remote_code=True)# Option 2: use with BiRefNet # Install from https://github.com/ZhengPeng7/BiRefNet from models.birefnet import BiRefNet model = BiRefNet.from_pretrained("baker76/imageback-models") - Notebooks
- Google Colab
- Kaggle
Correct file sizes
Browse files
README.md
CHANGED
|
@@ -23,10 +23,10 @@ the original MIT licence.
|
|
| 23 |
|
| 24 |
| Folder | Size | Weights |
|
| 25 |
| --- | --- | --- |
|
| 26 |
-
| `birefnet-fp16/` |
|
| 27 |
-
| `birefnet-int8/` |
|
| 28 |
-
| `birefnet-int4/` |
|
| 29 |
-
| `birefnet-fp32/` |
|
| 30 |
|
| 31 |
Each folder holds `model.onnx` and `config.json` (input size and normalisation).
|
| 32 |
|
|
|
|
| 23 |
|
| 24 |
| Folder | Size | Weights |
|
| 25 |
| --- | --- | --- |
|
| 26 |
+
| `birefnet-fp16/` | 490 MB | Half precision. Best choice on a GPU (recommended download) |
|
| 27 |
+
| `birefnet-int8/` | 309 MB | 8-bit. Closest to full precision of the small ones |
|
| 28 |
+
| `birefnet-int4/` | 209 MB | 4-bit backbone, 8-bit elsewhere. Smallest |
|
| 29 |
+
| `birefnet-fp32/` | 973 MB | Full precision; the source for quantizing |
|
| 30 |
|
| 31 |
Each folder holds `model.onnx` and `config.json` (input size and normalisation).
|
| 32 |
|