This repository was archived by the owner on Nov 27, 2024. It is now read-only.
File tree 5 files changed +30
-16
lines changed
5 files changed +30
-16
lines changed Original file line number Diff line number Diff line change @@ -9,12 +9,17 @@ python -m pip install -r requirements.txt
9
9
10
10
## Usage
11
11
``` bash
12
- convert.py --optimize -- model_input ' ..\stable-diffusion-v1-5' --model_output ' ..\converted ' --controlnet
12
+ python convert.py --model_input ' ..\stable-diffusion-v1-5' --controlnet
13
13
```
14
- ` --optimize ` - Run the model optimization
15
14
16
15
` --model_input ` - Safetensor model to convert
17
16
18
- ` --model_output ` - Output for converted ONNX model (NOTE: This folder is deleted before each run)
17
+ ` --model_output ` - Output for converted ONNX model
18
+
19
+ ` --clean ` - Clear convert/optimize model cache
20
+
21
+ ` --tempDir ` - Directory for temp Olive files
22
+
23
+ ` --only_unet ` - Only convert UNET model
19
24
20
25
` --controlnet ` - Create a ControlNet enabled Unet model
Original file line number Diff line number Diff line change @@ -9,15 +9,17 @@ python -m pip install -r requirements.txt
9
9
10
10
## Usage
11
11
``` bash
12
- convert.py --model_input " D:\Models\LCM_Dreamshaper_v7" --controlnet
12
+ python convert.py --model_input " D:\Models\LCM_Dreamshaper_v7" --controlnet
13
13
```
14
14
15
15
` --model_input ` - Safetensor model to convert
16
16
17
17
` --model_output ` - Output for converted ONNX model
18
18
19
- ` --controlnet ` - Create a ControlNet enabled Unet model
20
-
21
19
` --clean ` - Clear convert/optimize model cache
22
20
23
- ` --tempDir ` - Directory for temp Olive files
21
+ ` --tempDir ` - Directory for temp Olive files
22
+
23
+ ` --only_unet ` - Only convert UNET model
24
+
25
+ ` --controlnet ` - Create a ControlNet enabled Unet model
Original file line number Diff line number Diff line change @@ -9,12 +9,17 @@ python -m pip install -r requirements.txt
9
9
10
10
## Usage
11
11
``` bash
12
- convert.py --optimize -- model_input ' ..\ stable-cascade' --image_encoder
12
+ python convert.py --model_input " D:\Models\ stable-cascade" --image_encoder
13
13
```
14
- ` --optimize ` - Run the model optimization
15
14
16
15
` --model_input ` - Safetensor model to convert
17
16
18
- ` --model_output ` - Output for converted ONNX model (NOTE: This folder is deleted before each run)
17
+ ` --model_output ` - Output for converted ONNX model
18
+
19
+ ` --clean ` - Clear convert/optimize model cache
20
+
21
+ ` --tempDir ` - Directory for temp Olive files
22
+
23
+ ` --only_unet ` - Only convert UNET model
19
24
20
25
` --image_encoder ` - Convert the optional image encoder
Original file line number Diff line number Diff line change @@ -9,15 +9,17 @@ python -m pip install -r requirements.txt
9
9
10
10
## Usage
11
11
``` bash
12
- convert.py --model_input " D:\Models\stable-diffusion-v1-5" --controlnet
12
+ python convert.py --model_input " D:\Models\stable-diffusion-v1-5" --controlnet
13
13
```
14
14
15
15
` --model_input ` - Safetensor model to convert
16
16
17
17
` --model_output ` - Output for converted ONNX model
18
18
19
- ` --controlnet ` - Create a ControlNet enabled Unet model
20
-
21
19
` --clean ` - Clear convert/optimize model cache
22
20
23
- ` --tempDir ` - Directory for temp Olive files
21
+ ` --tempDir ` - Directory for temp Olive files
22
+
23
+ ` --only_unet ` - Only convert UNET model
24
+
25
+ ` --controlnet ` - Create a ControlNet enabled Unet model
Original file line number Diff line number Diff line change @@ -16,14 +16,14 @@ python convert.py --model_input "D:\Models\stable-diffusion-xl-base-1.0" --contr
16
16
17
17
` --model_output ` - Output for converted ONNX model
18
18
19
- ` --controlnet ` - Create a ControlNet enabled Unet model
20
-
21
19
` --clean ` - Clear convert/optimize model cache
22
20
23
21
` --tempDir ` - Directory for temp Olive files
24
22
25
23
` --only_unet ` - Only convert UNET model
26
24
25
+ ` --controlnet ` - Create a ControlNet enabled Unet model
26
+
27
27
## Extra Requirements
28
28
To successfully optimize SDXL models you will need the patched ` vae ` from repository below otherwise you may get black image results
29
29
You can’t perform that action at this time.
0 commit comments