facefusion每次都报这个错误，是内存不够还是什么原因？

huohuanye

RUNTIME_EXCEPTION : Exception during initialization: D:\a\_work\1\s\onnxruntime\core\framework\bfc_arena.cc:376 onnxruntime::BFCArena::AllocateRawInternal Failed to allocate memory for requested buffer of size 2097152

meiyouruguo

提示这个错误是因为你处理的视频太长了，你的显卡不足以处理这个长的视频，换个二十秒的短视频,这错误翻译一下就知道显存不足，视频太长的原因

huohuanye

meiyouruguo 发表于 2024-5-20 21:30
提示这个错误是因为你处理的视频太长了，你的显卡不足以处理这个长的视频，换个二十秒的短视频,这错误翻译 ...

Traceback (most recent call last):
  File "D:\facefusion\Facefusion3.5.3_AIBL_VIP\python310\lib\site-packages\gradio\queueing.py", line 407, in call_prediction
    output = await route_utils.call_process_api(
  File "D:\facefusion\Facefusion3.5.3_AIBL_VIP\python310\lib\site-packages\gradio\route_utils.py", line 226, in call_process_api
    output = await app.get_blocks().process_api(
  File "D:\facefusion\Facefusion3.5.3_AIBL_VIP\python310\lib\site-packages\gradio\blocks.py", line 1550, in process_api
    result = await self.call_function(
  File "D:\facefusion\Facefusion3.5.3_AIBL_VIP\python310\lib\site-packages\gradio\blocks.py", line 1185, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "D:\facefusion\Facefusion3.5.3_AIBL_VIP\python310\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
  File "D:\facefusion\Facefusion3.5.3_AIBL_VIP\python310\lib\site-packages\anyio\_backends\_asyncio.py", line 2144, in run_sync_in_worker_thread
    return await future
  File "D:\facefusion\Facefusion3.5.3_AIBL_VIP\python310\lib\site-packages\anyio\_backends\_asyncio.py", line 851, in run
    result = context.run(func, *args)
  File "D:\facefusion\Facefusion3.5.3_AIBL_VIP\python310\lib\site-packages\gradio\utils.py", line 661, in wrapper
    response = f(*args, **kwargs)
  File "E:\www_aibl.vip888\Facefusion3.5.2_AIBL_VIP\facefusion\uis\components\output.py", line 70, in process
  File "E:\www_aibl.vip888\Facefusion3.5.2_AIBL_VIP\facefusion\core.py", line 258, in conditional_process
  File "E:\www_aibl.vip888\Facefusion3.5.2_AIBL_VIP\facefusion\core.py", line 361, in process_video
  File "E:\www_aibl.vip888\Facefusion3.5.2_AIBL_VIP\facefusion\processors\frame\modules\face_swapper.py", line 373, in process_video
  File "E:\www_aibl.vip888\Facefusion3.5.2_AIBL_VIP\facefusion\processors\frame\core.py", line 87, in multi_process_frames
  File "D:\facefusion\Facefusion3.5.3_AIBL_VIP\python310\lib\concurrent\futures\_base.py", line 451, in result
    return self.__get_result()
  File "D:\facefusion\Facefusion3.5.3_AIBL_VIP\python310\lib\concurrent\futures\_base.py", line 403, in __get_result
    raise self._exception
  File "D:\facefusion\Facefusion3.5.3_AIBL_VIP\python310\lib\concurrent\futures\thread.py", line 58, in run
    result = self.fn(*self.args, **self.kwargs)
  File "E:\www_aibl.vip888\Facefusion3.5.2_AIBL_VIP\facefusion\processors\frame\modules\face_swapper.py", line 348, in process_frames
  File "E:\www_aibl.vip888\Facefusion3.5.2_AIBL_VIP\facefusion\processors\frame\modules\face_swapper.py", line 333, in process_frame
  File "E:\www_aibl.vip888\Facefusion3.5.2_AIBL_VIP\facefusion\face_analyser.py", line 531, in find_similar_faces
  File "E:\www_aibl.vip888\Facefusion3.5.2_AIBL_VIP\facefusion\face_analyser.py", line 515, in get_many_faces
  File "E:\www_aibl.vip888\Facefusion3.5.2_AIBL_VIP\facefusion\face_analyser.py", line 347, in create_faces
  File "E:\www_aibl.vip888\Facefusion3.5.2_AIBL_VIP\facefusion\face_analyser.py", line 403, in detect_face_landmark_68
  File "D:\facefusion\Facefusion3.5.3_AIBL_VIP\python310\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 220, in run
    return self._sess.run(output_names, input_feed, run_options)
onnxruntime.capi.onnxruntime_pybind11_state.Fail: [ONNXRuntimeError] : 1 : FAIL : D:\a\_work\1\s\onnxruntime\core\providers\cuda\cuda_call.cc:121 onnxruntime::CudaCall D:\a\_work\1\s\onnxruntime\core\providers\cuda\cuda_call.cc:114 onnxruntime::CudaCall CUBLAS failure 3: CUBLAS_STATUS_ALLOC_FAILED ; GPU=0 ; hostname=LAPTOP-II28553D ; file=D:\a\_work\1\s\onnxruntime\core\providers\cuda\cuda_stream_handle.cc ; line=73 ; expr=cublasCreate(&cublas_handle_);

我把它改成十几秒，然后跑了没几分钟又出现个错误，再给看看吧

huohuanye

meiyouruguo 发表于 2024-5-20 21:30
提示这个错误是因为你处理的视频太长了，你的显卡不足以处理这个长的视频，换个二十秒的短视频,这错误翻译 ...

嗯 我的1050ti 只能产出不到2秒的视频

416914453

2060显卡能处理多久的

a664559

GPU爆显存了，把GPU线程数调小，显卡越好线程调大时间越快反之调小时间越久