FaceSwapLab - **ERROR** - Failed to swap face in postprocess method

[Barzing0]

2023-08-03 12:43:08,484 - FaceSwapLab - INFO - Try to use model : D:\A1111\stable-diffusion-webui\models\faceswaplab\inswapper_128.onnx█████| 20/20 [00:02<00:00, 9.21it/s] 2023-08-03 12:43:09,410 - FaceSwapLab - INFO - blend all faces together 2023-08-03 12:43:09,413 - FaceSwapLab - INFO - Load analysis model, will take some time. Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}} find model: D:\A1111\stable-diffusion-webui\models\faceswaplab\analysers\models\buffalo_l\1k3d68.onnx landmark_3d_68 ['None', 3, 192, 192] 0.0 1.0 Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}} find model: D:\A1111\stable-diffusion-webui\models\faceswaplab\analysers\models\buffalo_l\2d106det.onnx landmark_2d_106 ['None', 3, 192, 192] 0.0 1.0 Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}} find model: D:\A1111\stable-diffusion-webui\models\faceswaplab\analysers\models\buffalo_l\det_10g.onnx detection [1, 3, '?', '?'] 127.5 128.0 Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}} find model: D:\A1111\stable-diffusion-webui\models\faceswaplab\analysers\models\buffalo_l\genderage.onnx genderage ['None', 3, 96, 96] 0.0 1.0 Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}} find model: D:\A1111\stable-diffusion-webui\models\faceswaplab\analysers\models\buffalo_l\w600k_r50.onnx recognition ['None', 3, 112, 112] 127.5 127.5 2023-08-03 12:43:10,291 - FaceSwapLab - ERROR - Failed to swap face in postprocess method : This ORT build has ['TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider'] enabled. Since ORT 1.9, you are required to explicitly set the providers parameter when instantiating InferenceSession. For example, onnxruntime.InferenceSession(..., providers=['TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider'], ...) Total progress: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:04<00:00, 4.49it/s] Total progress: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:04<00:00, 9.21it/s]

To Reproduce nothing special, just start A1111 with --medvram --xformers --administrator --api --no-half-vae --theme dark Once UI loadeded, i prompt "portrait of a woman", i generate with a face to swap (no parameter modified) i also tried without --medvram i had same result While roop 0.0.2 (also installed) works each time

Desktop (please complete the following information):

• OS: Windows 10 with 32gb RAM and Nvidia Geforce RTX 3070 Ti
• Browser : Edge & Opera GX (tried with both)

[glucauze]

It's very strange because my loading method isn't very different. I'm not sure what could be causing this.

Maybe a corrupted inswapper file?

Or maybe it's a problem of installed dependencies. Could you look at the onnx and onnxruntime versions installed with pip list?

This is done by activating the stable diffusion environment: venv/Scripts/activate.bat (or activate.ps1) under Windows

Did you install onnxruntime-gpu ?

[Barzing0]

onnx 1.14.0 onnxruntime-gpu 1.12.1 onnxruntime 1.15.0

(venv) D:\A1111\stable-diffusion-webui\venv\Lib\site-packages>pip install onnxruntime-gpu WARNING: Ignoring invalid distribution -rotobuf (d:\a1111\stable-diffusion-webui\venv\lib\site-packages) Requirement already satisfied: onnxruntime-gpu in d:\a1111\stable-diffusion-webui\venv\lib\site-packages (1.12.1) Requirement already satisfied: coloredlogs in d:\a1111\stable-diffusion-webui\venv\lib\site-packages (from onnxruntime-gpu) (15.0.1) Requirement already satisfied: flatbuffers in d:\a1111\stable-diffusion-webui\venv\lib\site-packages (from onnxruntime-gpu) (2.0.7) Requirement already satisfied: numpy>=1.21.0 in d:\a1111\stable-diffusion-webui\venv\lib\site-packages (from onnxruntime-gpu) (1.23.5) Requirement already satisfied: packaging in d:\a1111\stable-diffusion-webui\venv\lib\site-packages (from onnxruntime-gpu) (23.1) Requirement already satisfied: protobuf in d:\a1111\stable-diffusion-webui\venv\lib\site-packages (from onnxruntime-gpu) (3.20.3) Requirement already satisfied: sympy in d:\a1111\stable-diffusion-webui\venv\lib\site-packages (from onnxruntime-gpu) (1.11.1) Requirement already satisfied: humanfriendly>=9.1 in d:\a1111\stable-diffusion-webui\venv\lib\site-packages (from coloredlogs->onnxruntime-gpu) (10.0) Requirement already satisfied: mpmath>=0.19 in d:\a1111\stable-diffusion-webui\venv\lib\site-packages (from sympy->onnxruntime-gpu) (1.3.0) Requirement already satisfied: pyreadline3 in d:\a1111\stable-diffusion-webui\venv\lib\site-packages (from humanfriendly>=9.1->coloredlogs->onnxruntime-gpu) (3.4.1) WARNING: Ignoring invalid distribution -rotobuf (d:\a1111\stable-diffusion-webui\venv\lib\site-packages) DEPRECATION: torchsde 0.2.5 has a non-standard dependency specifier numpy>=1.19.*; python_version >= "3.7". pip 23.3 will enforce this behaviour change. A possible replacement is to upgrade to a newer version of torchsde or contact the author to suggest that they release a version with a conforming dependency specifiers. Discussion can be found at https://github.com/pypa/pip/issues/12063

(venv) D:\A1111\stable-diffusion-webui\venv\Lib\site-packages>

Is this warning could be the problem ?

[glucauze]

Ok I think the problem comes from the fact that onnxruntime-gpu 1.12.1 is installed in your environment. I'm not managing the GPU at the moment.

I'll try to uninstall it to see (unless you need it):

pip uninstall onnxruntime-gpu

[Barzing0]

ok i uninstalled onxruntime-gpu and i had to uninstall onxruntime too. onxruntime-gpu was coming from another extension i installed and unisntalled sometime (probably deepfaceLab), cause i never installed this manually. Now it works !

[glucauze]

I'll have to find a solution to manage the GPU too later on. Otherwise, certain frameworks could cause problems. I'll close it for now.