FaceFusion 3.4.0 一键换脸软件，支持图片换脸/视频换脸/直播换脸 支持50系显卡 一键整合包下载

38***

3.4.1整合包出了吗

b***

这个是不是也支持VR视频

无言***

bio 发表于 2025-10-24 09:46
这个是不是也支持VR视频

支持，但人脸不要太小扭曲太厉害，否则识别不了

b***

跟RoopUnleashed相比，处理VR视频哪个好用 谢谢

无言***

bio 发表于 2025-10-24 09:54
跟RoopUnleashed相比，处理VR视频哪个好用 谢谢

RU停更了，很多模型都很老，FF人脸检测更强，VR我没试过，所以没法对比
你可以对比下

Merc***

[mov,mp4,m4a,3gp,3g2,mj2 @ 0000011f46b83dc0] moov atom not found
[mov,mp4,m4a,3gp,3g2,mj2 @ 0000011f46b83dc0] moov atom not found
[mov,mp4,m4a,3gp,3g2,mj2 @ 0000011f46b83dc0] moov atom not found
[mov,mp4,m4a,3gp,3g2,mj2 @ 0000011f46b83dc0] moov atom not found
Exception in callback _ProactorBasePipeTransport._call_connection_lost(None)
handle: <Handle _ProactorBasePipeTransport._call_connection_lost(None)>
Traceback (most recent call last):
  File "E:\AI\FaceFusion-3.4.0\deepface\lib\asyncio\events.py", line 80, in _run
    self._context.run(self._callback, *self._args)
  File "E:\AI\FaceFusion-3.4.0\deepface\lib\asyncio\proactor_events.py", line 165, in _call_connection_lost
    self._sock.shutdown(socket.SHUT_RDWR)
ConnectionResetError: [WinError 10054] 远程主机强迫关闭了一个现有的连接。
[mov,mp4,m4a,3gp,3g2,mj2 @ 0000011f46b83dc0] moov atom not found
Traceback (most recent call last):
  File "E:\AI\FaceFusion-3.4.0\deepface\lib\site-packages\gradio\queueing.py", line 626, in process_events
    response = await route_utils.call_process_api(
  File "E:\AI\FaceFusion-3.4.0\deepface\lib\site-packages\gradio\route_utils.py", line 350, in call_process_api
    output = await app.get_blocks().process_api(
  File "E:\AI\FaceFusion-3.4.0\deepface\lib\site-packages\gradio\blocks.py", line 2250, in process_api
    result = await self.call_function(
  File "E:\AI\FaceFusion-3.4.0\deepface\lib\site-packages\gradio\blocks.py", line 1757, in call_function
    prediction = await anyio.to_thread.run_sync(  # type: ignore
  File "E:\AI\FaceFusion-3.4.0\deepface\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
  File "E:\AI\FaceFusion-3.4.0\deepface\lib\site-packages\anyio\_backends\_asyncio.py", line 2476, in run_sync_in_worker_thread
    return await future
  File "E:\AI\FaceFusion-3.4.0\deepface\lib\site-packages\anyio\_backends\_asyncio.py", line 967, in run
    result = context.run(func, *args)
  File "E:\AI\FaceFusion-3.4.0\deepface\lib\site-packages\gradio\utils.py", line 917, in wrapper
    response = f(*args, **kwargs)
  File "E:\AI\FaceFusion-3.4.0\facefusion\uis\components\preview_options.py", line 59, in update_preview_frame_slider
    video_frame_total = count_video_frame_total(state_manager.get_item('target_path'))
  File "E:\AI\FaceFusion-3.4.0\facefusion\vision.py", line 94, in count_video_frame_total
    if video_capture.isOpened():
AttributeError: 'NoneType' object has no attribute 'isOpened'

Merc***

Mercerys 发表于 2025-10-24 14:03
[mov,mp4,m4a,3gp,3g2,mj2 @ 0000011f46b83dc0] moov atom not found
[mov,mp4,m4a,3gp,3g2,mj2 @ 0000011f ...

显示错误

无言***

Mercerys 发表于 2025-10-24 14:04
显示错误

换个视频试试，这个看着像是视频文件破损或格式问题导致

b***

execution_providers=['cuda']]
Traceback (most recent call last):
  File "G:\Gaisoft\FaceFusion-3.4.0\deepface\lib\site-packages\gradio\queueing.py", line 626, in process_events
    response = await route_utils.call_process_api(
  File "G:\Gaisoft\FaceFusion-3.4.0\deepface\lib\site-packages\gradio\route_utils.py", line 350, in call_process_api
    output = await app.get_blocks().process_api(
  File "G:\Gaisoft\FaceFusion-3.4.0\deepface\lib\site-packages\gradio\blocks.py", line 2250, in process_api
    result = await self.call_function(
  File "G:\Gaisoft\FaceFusion-3.4.0\deepface\lib\site-packages\gradio\blocks.py", line 1757, in call_function
    prediction = await anyio.to_thread.run_sync(  # type: ignore
  File "G:\Gaisoft\FaceFusion-3.4.0\deepface\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
  File "G:\Gaisoft\FaceFusion-3.4.0\deepface\lib\site-packages\anyio\_backends\_asyncio.py", line 2476, in run_sync_in_worker_thread
    return await future
  File "G:\Gaisoft\FaceFusion-3.4.0\deepface\lib\site-packages\anyio\_backends\_asyncio.py", line 967, in run
    result = context.run(func, *args)
  File "G:\Gaisoft\FaceFusion-3.4.0\deepface\lib\site-packages\gradio\utils.py", line 917, in wrapper
    response = f(*args, **kwargs)
  File "G:\Gaisoft\FaceFusion-3.4.0\facefusion\uis\components\instant_runner.py", line 82, in run
    create_and_run_job(step_args)
  File "G:\Gaisoft\FaceFusion-3.4.0\facefusion\uis\components\instant_runner.py", line 97, in create_and_run_job
    return job_manager.create_job(job_id) and job_manager.add_step(job_id, step_args) and job_manager.submit_job(job_id) and job_runner.run_job(job_id, process_step)
  File "G:\Gaisoft\FaceFusion-3.4.0\facefusion\jobs\job_runner.py", line 11, in run_job
    if run_steps(job_id, process_step) and finalize_steps(job_id):
  File "G:\Gaisoft\FaceFusion-3.4.0\facefusion\jobs\job_runner.py", line 72, in run_steps
    if not run_step(job_id, index, step, process_step):
  File "G:\Gaisoft\FaceFusion-3.4.0\facefusion\jobs\job_runner.py", line 58, in run_step
    if job_manager.set_step_status(job_id, step_index, 'started') and process_step(job_id, step_index, step_args):
  File "G:\Gaisoft\FaceFusion-3.4.0\facefusion\core.py", line 319, in process_step
    error_code = conditional_process()
  File "G:\Gaisoft\FaceFusion-3.4.0\facefusion\core.py", line 334, in conditional_process
    return process_video(start_time)
  File "G:\Gaisoft\FaceFusion-3.4.0\facefusion\core.py", line 450, in process_video
    future.result()
  File "G:\Gaisoft\FaceFusion-3.4.0\deepface\lib\concurrent\futures\_base.py", line 451, in result
    return self.__get_result()
  File "G:\Gaisoft\FaceFusion-3.4.0\deepface\lib\concurrent\futures\_base.py", line 403, in __get_result
    raise self._exception
  File "G:\Gaisoft\FaceFusion-3.4.0\deepface\lib\concurrent\futures\thread.py", line 58, in run
    result = self.fn(*self.args, **self.kwargs)
  File "G:\Gaisoft\FaceFusion-3.4.0\facefusion\core.py", line 529, in process_temp_frame
    temp_vision_frame = processor_module.process_frame(
  File "G:\Gaisoft\FaceFusion-3.4.0\facefusion\processors\modules\face_swapper.py", line 691, in process_frame
    temp_vision_frame = swap_face(source_face, target_face, temp_vision_frame)
  File "G:\Gaisoft\FaceFusion-3.4.0\facefusion\processors\modules\face_swapper.py", line 537, in swap_face
    paste_vision_frame = paste_back(temp_vision_frame, crop_vision_frame, crop_mask, affine_matrix)
  File "G:\Gaisoft\FaceFusion-3.4.0\facefusion\face_helper.py", line 111, in paste_back
    paste_vision_frame = paste_vision_frame * (1 - inverse_mask) + inverse_vision_frame * inverse_mask
numpy.core._exceptions._ArrayMemoryError: Unable to allocate 7.99 MiB for an array with shape (591, 591, 3) and data type float64

处理到20%左右跳出来的

无言***

bio 发表于 2025-10-24 15:59
execution_providers=['cuda']]
Traceback (most recent call last):
  File "G:\Gaisoft\FaceFusion-3.4.0 ...

显存不足
显卡差的，一次不要换太长，尤其是超过2K的画质，比如4K画质或者高帧率的