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
Add BiRefNet fp32, fp16, int8 and int4 models
Browse files- birefnet-fp16/config.json +16 -0
- birefnet-fp16/model.onnx +3 -0
- birefnet-fp32/config.json +16 -0
- birefnet-fp32/model.onnx +3 -0
- birefnet-int4/config.json +21 -0
- birefnet-int4/model.onnx +3 -0
- birefnet-int8/config.json +21 -0
- birefnet-int8/model.onnx +3 -0
birefnet-fp16/config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model": "BiRefNet",
|
| 3 |
+
"source": "onnx-community/BiRefNet-ONNX",
|
| 4 |
+
"dtype": "fp16",
|
| 5 |
+
"input_size": 1024,
|
| 6 |
+
"mean": [
|
| 7 |
+
0.485,
|
| 8 |
+
0.456,
|
| 9 |
+
0.406
|
| 10 |
+
],
|
| 11 |
+
"std": [
|
| 12 |
+
0.229,
|
| 13 |
+
0.224,
|
| 14 |
+
0.225
|
| 15 |
+
]
|
| 16 |
+
}
|
birefnet-fp16/model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd10c27655eafe25e611f5f34c273cc50fd5474112d637d0d65dd8533275c953
|
| 3 |
+
size 489709532
|
birefnet-fp32/config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model": "BiRefNet",
|
| 3 |
+
"source": "onnx-community/BiRefNet-ONNX",
|
| 4 |
+
"dtype": "fp32",
|
| 5 |
+
"input_size": 1024,
|
| 6 |
+
"mean": [
|
| 7 |
+
0.485,
|
| 8 |
+
0.456,
|
| 9 |
+
0.406
|
| 10 |
+
],
|
| 11 |
+
"std": [
|
| 12 |
+
0.229,
|
| 13 |
+
0.224,
|
| 14 |
+
0.225
|
| 15 |
+
]
|
| 16 |
+
}
|
birefnet-fp32/model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2319451f92fbcb4ed677b0782bb307d1d659ccc9287d3cdf7eed9aa7e07b9f01
|
| 3 |
+
size 972710176
|
birefnet-int4/config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model": "BiRefNet",
|
| 3 |
+
"source": "onnx-community/BiRefNet-ONNX",
|
| 4 |
+
"dtype": "int4",
|
| 5 |
+
"input_size": 1024,
|
| 6 |
+
"mean": [
|
| 7 |
+
0.485,
|
| 8 |
+
0.456,
|
| 9 |
+
0.406
|
| 10 |
+
],
|
| 11 |
+
"std": [
|
| 12 |
+
0.229,
|
| 13 |
+
0.224,
|
| 14 |
+
0.225
|
| 15 |
+
],
|
| 16 |
+
"quantization": {
|
| 17 |
+
"matmul_bits": 4,
|
| 18 |
+
"block_size": 32,
|
| 19 |
+
"rest": "int8"
|
| 20 |
+
}
|
| 21 |
+
}
|
birefnet-int4/model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:590b3233756b05d87ff86353efb473ddbda018d231bf74d528ef6f82d14e79ce
|
| 3 |
+
size 209026653
|
birefnet-int8/config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model": "BiRefNet",
|
| 3 |
+
"source": "onnx-community/BiRefNet-ONNX",
|
| 4 |
+
"dtype": "int8",
|
| 5 |
+
"input_size": 1024,
|
| 6 |
+
"mean": [
|
| 7 |
+
0.485,
|
| 8 |
+
0.456,
|
| 9 |
+
0.406
|
| 10 |
+
],
|
| 11 |
+
"std": [
|
| 12 |
+
0.229,
|
| 13 |
+
0.224,
|
| 14 |
+
0.225
|
| 15 |
+
],
|
| 16 |
+
"quantization": {
|
| 17 |
+
"matmul_bits": 8,
|
| 18 |
+
"block_size": 32,
|
| 19 |
+
"rest": "int8"
|
| 20 |
+
}
|
| 21 |
+
}
|
birefnet-int8/model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8aba17b0a0ad4de727aa29c31538fe1dac3ac3c6865ab34801d2580d732f5e20
|
| 3 |
+
size 309389016
|