If you have figured it out, you should keep it to yourself - you don't know whether the person you are sharing it with is just a coomer or a psychopath who wants to ruin someone's life.
如果你已经搞清楚了，你应该自己保留 - 你不知道与你分享的人是一个仅仅是一个过度自慰者（Coomer）还是一个想要毁掉别人生活的精神变态。

1.如题colab受限于UI,没法像本地版本那样用上下键调节替换对象。
2.但图片中的人脸是有数字取值的，最右边的人脸是0，往左的脸依次加值。
3.可不可以在云端提供多图换多脸的选项呢？
4.感谢博主。

问题

没有生成out.mp4

开始换脸log

cmd:run.py --execution-provider cuda -s /content/my/mm1.jpg -t /content/my/m_2.mp4 -o /content/my/out.mp4 --frame-processor face_swapper --video-encoder libx264 --video-quality 18  --keep-audio  
Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}, 'CUDAExecutionProvider': {'device_id': '0', 'gpu_mem_limit': '18446744073709551615', 'gpu_external_alloc': '0', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'cudnn_conv_algo_search': 'EXHAUSTIVE', 'cudnn_conv1d_pad_to_nc1d': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'do_copy_in_default_stream': '1', 'enable_cuda_graph': '0', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0', 'enable_skip_layer_norm_strict_mode': '0', 'tunable_op_tuning_enable': '0'}}
find model: /root/.insightface/models/buffalo_l/1k3d68.onnx landmark_3d_68 ['None', 3, 192, 192] 0.0 1.0
Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}, 'CUDAExecutionProvider': {'device_id': '0', 'gpu_mem_limit': '18446744073709551615', 'gpu_external_alloc': '0', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'cudnn_conv_algo_search': 'EXHAUSTIVE', 'cudnn_conv1d_pad_to_nc1d': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'do_copy_in_default_stream': '1', 'enable_cuda_graph': '0', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0', 'enable_skip_layer_norm_strict_mode': '0', 'tunable_op_tuning_enable': '0'}}
find model: /root/.insightface/models/buffalo_l/2d106det.onnx landmark_2d_106 ['None', 3, 192, 192] 0.0 1.0
Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}, 'CUDAExecutionProvider': {'device_id': '0', 'gpu_mem_limit': '18446744073709551615', 'gpu_external_alloc': '0', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'cudnn_conv_algo_search': 'EXHAUSTIVE', 'cudnn_conv1d_pad_to_nc1d': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'do_copy_in_default_stream': '1', 'enable_cuda_graph': '0', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0', 'enable_skip_layer_norm_strict_mode': '0', 'tunable_op_tuning_enable': '0'}}
find model: /root/.insightface/models/buffalo_l/det_10g.onnx detection [1, 3, '?', '?'] 127.5 128.0
Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}, 'CUDAExecutionProvider': {'device_id': '0', 'gpu_mem_limit': '18446744073709551615', 'gpu_external_alloc': '0', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'cudnn_conv_algo_search': 'EXHAUSTIVE', 'cudnn_conv1d_pad_to_nc1d': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'do_copy_in_default_stream': '1', 'enable_cuda_graph': '0', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0', 'enable_skip_layer_norm_strict_mode': '0', 'tunable_op_tuning_enable': '0'}}
find model: /root/.insightface/models/buffalo_l/genderage.onnx genderage ['None', 3, 96, 96] 0.0 1.0
Applied providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}, 'CUDAExecutionProvider': {'device_id': '0', 'gpu_mem_limit': '18446744073709551615', 'gpu_external_alloc': '0', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'cudnn_conv_algo_search': 'EXHAUSTIVE', 'cudnn_conv1d_pad_to_nc1d': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'do_copy_in_default_stream': '1', 'enable_cuda_graph': '0', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0', 'enable_skip_layer_norm_strict_mode': '0', 'tunable_op_tuning_enable': '0'}}
find model: /root/.insightface/models/buffalo_l/w600k_r50.onnx recognition ['None', 3, 112, 112] 127.5 127.5
set det-size: (640, 640)
100% 1594/1594 [00:08<00:00, 181.75it/s]

从12月以来 用GPU加速 后台的GPU RAM占用一直是0GB处理 不加速

换脸后容易闪烁，是不是相似度问题，哪里修改？

如题

目前看来只能合成7s左右的视频，模版视频有13s，7s之后就定格在某一帧上，不知道是使用姿势有问题，还是脚本本身做了限制。(环境：mbp 2.3 GHz 四核Intel Core i5 Intel Iris Plus Graphics 655 1536 MB)

cmd:/content/roop/run.py --execution-provider cuda -s /content/roop_colab/1.jpg -t /content/roop_colab/2.mp4 -o /content/roop_colab/out.mp4 --frame-processor face_swapper face_enhancer --output-video-encoder libx264 --output-video-quality 35 --keep-fps --temp-frame-format jpg --temp-frame-quality 0
Traceback (most recent call last):
File "/content/roop/run.py", line 6, in
core.run()
File "/content/roop/roop/core.py", line 213, in run
if not frame_processor.pre_check():
File "/content/roop/roop/processors/frame/face_swapper.py", line 37, in pre_check
conditional_download(download_directory_path, ['https://huggingface.co/henryruhs/roop/resolve/main/inswapper_128.onnx'])
File "/content/roop/roop/utilities.py", line 142, in conditional_download
request = urllib.request.urlopen(url) # type: ignore[attr-defined]
File "/usr/lib/python3.10/urllib/request.py", line 216, in urlopen
return opener.open(url, data, timeout)
File "/usr/lib/python3.10/urllib/request.py", line 525, in open
response = meth(req, response)
File "/usr/lib/python3.10/urllib/request.py", line 634, in http_response
response = self.parent.error(
File "/usr/lib/python3.10/urllib/request.py", line 563, in error
return self._call_chain(*args)
File "/usr/lib/python3.10/urllib/request.py", line 496, in _call_chain
result = func(*args)
File "/usr/lib/python3.10/urllib/request.py", line 643, in http_error_default
raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 401: Unauthorized

下载以来后运行提示这个
Windows PowerShell
版权所有 (C) 2009 Microsoft Corporation。保留所有权利。

PS D:\Code\Python\roop-main> & C:/Users/Administrator/AppData/Local/Programs/Pyt
hon/Python38/python.exe d:/Code/Python/roop-main/run.py
Traceback (most recent call last):
File "d:/Code/Python/roop-main/run.py", line 2, in
from roop import core
File "d:\Code\Python\roop-main\roop\core.py", line 18, in
import onnxruntime
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38\lib\site-p
ackages\onnxruntime_init_.py", line 56, in
raise import_capi_exception
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38\lib\site-p
ackages\onnxruntime_init_.py", line 23, in
from onnxruntime.capi._pybind_state import ExecutionMode # noqa: F401
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38\lib\site-p
ackages\onnxruntime\capi_pybind_state.py", line 32, in
from .onnxruntime_pybind11_state import * # noqa
ImportError: DLL load failed while importing onnxruntime_pybind11_state: 找不到
指定的程序。

The following error occurred while I was processing the video :
Error
Unexpected token '<', " <h"... is not valid JSON

（using colab）

(venv) C:\temp\Tony\tonyff>python run.py
Frame processor frame_enhancer could not be loaded

(venv) C:\temp\Tony\tonyff>python -V
Python 3.11.0

(venv) C:\temp\Tony\tonyff>ver

Microsoft Windows [版本 10.0.19043.985]

--
After erase whole folder, and pull again, still showing the same message.

C:\temp\Tony\tonyff> python -v run.py 2> log.txt
as attachment

log.txt

cmd:run.py --execution-provider cuda -s /content/drive/MyDrive/1.jpg -t /content/drive/MyDrive/11.mp4 -o /content/drive/MyDrive/out/out11.mp4 --frame-processor face_swapper --output-video-encoder libx264 --output-video-quality 35 --keep-fps --many-faces --temp-frame-format jpg --temp-frame-quality 0
EP Error /onnxruntime_src/onnxruntime/core/providers/cuda/cuda_call.cc:121 std::conditional_t<THRW, void, onnxruntime::common::Status> onnxruntime::CudaCall(ERRTYPE, const char*, const char*, ERRTYPE, const char*, const char*, int) [with ERRTYPE = cudaError; bool THRW = true; std::conditional_t<THRW, void, onnxruntime::common::Status> = void] /onnxruntime_src/onnxruntime/core/providers/cuda/cuda_call.cc:114 std::conditional_t<THRW, void, onnxruntime::common::Status> onnxruntime::CudaCall(ERRTYPE, const char*, const char*, ERRTYPE, const char*, const char*, int) [with ERRTYPE = cudaError; bool THRW = true; std::conditional_t<THRW, void, onnxruntime::common::Status> = void] CUDA failure 35: CUDA driver version is insufficient for CUDA runtime version ; GPU=-412879360 ; hostname=a1e2af3b9974 ; file=/onnxruntime_src/onnxruntime/core/providers/cuda/cuda_execution_provider.cc ; line=238 ; expr=cudaSetDevice(info_.device_id);

when using ['CUDAExecutionProvider']
Falling back to ['CUDAExecutionProvider', 'CPUExecutionProvider'] and retrying.
Traceback (most recent call last):
File "/usr/local/lib/python3.10/dist-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 383, in init
self._create_inference_session(providers, provider_options, disabled_optimizers)
File "/usr/local/lib/python3.10/dist-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 435, in create_inference_session
sess.initialize_session(providers, provider_options, disabled_optimizers)
RuntimeError: /onnxruntime_src/onnxruntime/core/providers/cuda/cuda_call.cc:121 std::conditional_t<THRW, void, onnxruntime::common::Status> onnxruntime::CudaCall(ERRTYPE, const char*, const char*, ERRTYPE, const char*, const char*, int) [with ERRTYPE = cudaError; bool THRW = true; std::conditional_t<THRW, void, onnxruntime::common::Status> = void] /onnxruntime_src/onnxruntime/core/providers/cuda/cuda_call.cc:114 std::conditional_t<THRW, void, onnxruntime::common::Status> onnxruntime::CudaCall(ERRTYPE, const char*, const char*, ERRTYPE, const char*, const char*, int) [with ERRTYPE = cudaError; bool THRW = true; std::conditional_t<THRW, void, onnxruntime::common::Status> = void] CUDA failure 35: CUDA driver version is insufficient for CUDA runtime version ; GPU=-412879360 ; hostname=a1e2af3b9974 ; file=/onnxruntime_src/onnxruntime/core/providers/cuda/cuda_execution_provider.cc ; line=238 ; expr=cudaSetDevice(info.device_id);

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "/content/roop/run.py", line 6, in
core.run()
File "/content/roop/roop/core.py", line 217, in run
start()
File "/content/roop/roop/core.py", line 133, in start
if not frame_processor.pre_start():
File "/content/roop/roop/processors/frame/face_swapper.py", line 45, in pre_start
elif not get_one_face(cv2.imread(roop.globals.source_path)):
File "/content/roop/roop/face_analyser.py", line 30, in get_one_face
many_faces = get_many_faces(frame)
File "/content/roop/roop/face_analyser.py", line 41, in get_many_faces
return get_face_analyser().get(frame)
File "/content/roop/roop/face_analyser.py", line 18, in get_face_analyser
FACE_ANALYSER = insightface.app.FaceAnalysis(name='buffalo_l', providers=roop.globals.execution_providers)
File "/usr/local/lib/python3.10/dist-packages/insightface/app/face_analysis.py", line 31, in init
model = model_zoo.get_model(onnx_file, kwargs)
File "/usr/local/lib/python3.10/dist-packages/insightface/model_zoo/model_zoo.py", line 96, in get_model
model = router.get_model(providers=providers, provider_options=provider_options)
File "/usr/local/lib/python3.10/dist-packages/insightface/model_zoo/model_zoo.py", line 40, in get_model
session = PickableInferenceSession(self.onnx_file, kwargs)
File "/usr/local/lib/python3.10/dist-packages/insightface/model_zoo/model_zoo.py", line 25, in init
super().init(model_path, kwargs)
File "/usr/local/lib/python3.10/dist-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 394, in init
raise fallback_error from e
File "/usr/local/lib/python3.10/dist-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 389, in init
self._create_inference_session(self._fallback_providers, None)
File "/usr/local/lib/python3.10/dist-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 435, in _create_inference_session
sess.initialize_session(providers, provider_options, disabled_optimizers)
RuntimeError: /onnxruntime_src/onnxruntime/core/providers/cuda/cuda_call.cc:121 std::conditional_t<THRW, void, onnxruntime::common::Status> onnxruntime::CudaCall(ERRTYPE, const char, const char, ERRTYPE, const char, const char, int) [with ERRTYPE = cudaError; bool THRW = true; std::conditional_t<THRW, void, onnxruntime::common::Status> = void] /onnxruntime_src/onnxruntime/core/providers/cuda/cuda_call.cc:114 std::conditional_t<THRW, void, onnxruntime::common::Status> onnxruntime::CudaCall(ERRTYPE, const char, const char, ERRTYPE, const char*, const char*, int) [with ERRTYPE = cudaError; bool THRW = true; std::conditional_t<THRW, void, onnxruntime::common::Status> = void] CUDA failure 35: CUDA driver version is insufficient for CUDA runtime version ; GPU=637870059 ; hostname=a1e2af3b9974 ; file=/onnxruntime_src/onnxruntime/core/providers/cuda/cuda_execution_provider.cc ; line=238 ; expr=cudaSetDevice(info_.device_id);

Hello,

First of all I'd like to say that your work is great.

I'm using the "roop_v1.3" version on Google Colab using their GPU to generate images from images.

My only concern is the speed of the program: 30 seconds to generate an image, I think that's a lot compared to other deepfake (usually no more than 5 seconds for example sberswap).

Is it possible to make the tool faster? And if so, how?

Maybe for future versions.

Thanks

这效果模糊不说。。。 头随便转个角度各种问题 。。。