MuseTalk - 一键创建高质量数字人（对口型）一键整合包，新增批量处理

无言***

haidai 发表于 2024-9-2 14:43
更多好玩的AI应用，
MuseTalk WebUI正在启动中，请稍后
---------------------------------------------- ...

这不是报错，根据显卡和视频时长不同，生成时间不等。你先看看显卡是否符合要求，还有，贴出的信息是否完整。

cuish***

运行一键启动批处理后，结果是这样的，这是什么原因啊？
Traceback (most recent call last):
  File "D:\MuseTalk\python310\lib\runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "D:\MuseTalk\python310\lib\runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "D:\MuseTalk\scripts\inference.py", line 12, in <module>
    from musetalk.utils.utils import get_file_type,get_video_fps,datagen
ModuleNotFoundError: No module named 'musetalk'
请按任意键继续. . .

无言***

cuishuxuan 发表于 2024-9-26 23:22
运行一键启动批处理后，结果是这样的，这是什么原因啊？
Traceback (most recent call last):
  File "D:\M ...

复制软件目录下的 musetalk
到 MuseTalk\python310\Lib\site-packages这个目录下

ppg***

回复一下做个标记

heia***

-----------------------------------------------

To create a public link, set `share=True` in `launch()`.
IMPORTANT: You are using gradio version 4.26.0, however version 4.29.0 is available, please upgrade.
--------
Exception in callback _ProactorBasePipeTransport._call_connection_lost(None)
handle: <Handle _ProactorBasePipeTransport._call_connection_lost(None)>
Traceback (most recent call last):
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\asyncio\events.py", line 80, in _run
    self._context.run(self._callback, *self._args)
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\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。
Exception in callback _ProactorBasePipeTransport._call_connection_lost(None)
handle: <Handle _ProactorBasePipeTransport._call_connection_lost(None)>
Traceback (most recent call last):
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\asyncio\events.py", line 80, in _run
    self._context.run(self._callback, *self._args)
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\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。
IMAGEIO FFMPEG_WRITER WARNING: input image is not divisible by macro_block_size=16, resizing from (1920, 1080) to (1920, 1088) to ensure video compatibility with most codecs and players. To prevent resizing, make your input image divisible by the macro_block_size or set the macro_block_size to 1 (risking incompatibility).
video in 25.0 FPS, audio idx in 50FPS
提取 landmarks...耐心等待
reading images...
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('./results/output\outputxxx_10鏈?get key_landmark and face bounding boxes with the default value
Traceback (most recent call last):
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\gradio\queueing.py", line 527, in process_events
    response = await route_utils.call_process_api(
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\gradio\route_utils.py", line 261, in call_process_api
    output = await app.get_blocks().process_api(
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\gradio\blocks.py", line 1786, in process_api
    result = await self.call_function(
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\gradio\blocks.py", line 1338, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\anyio\_backends\_asyncio.py", line 2144, in run_sync_in_worker_thread
    return await future
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\anyio\_backends\_asyncio.py", line 851, in run
    result = context.run(func, *args)
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\gradio\utils.py", line 759, in wrapper
    response = f(*args, **kwargs)
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\gradio\utils.py", line 759, in wrapper
    response = f(*args, **kwargs)
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "app.py", line 176, in inference
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\musetalk\utils\preprocessing.py", line 97, in get_landmark_and_bbox
    results = inference_topdown(model, np.asarray(fb)[0])
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\mmpose\apis\inference.py", line 165, in inference_topdown
    h, w = img.shape[:2]
AttributeError: 'NoneType' object has no attribute 'shape'

最后生成视频一直报错，咋回事？

heia***

下载的最新版的，还需要打补丁吗？

无言***

heianwei 发表于 2024-10-2 23:09
下载的最新版的，还需要打补丁吗？

视频不要超过1080P，帧率在25帧左右

heia***

无言以对 发表于 2024-10-2 23:22
视频不要超过1080P，帧率在25帧左右

试了1080P和720P，都是25帧的，都不行，显示错误

heia***

video in 25.0 FPS, audio idx in 50FPS
提取 landmarks...耐心等待
reading images...
get key_landmark and face bounding boxes with the default value
Traceback (most recent call last):
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\gradio\queueing.py", line 527, in process_events
    response = await route_utils.call_process_api(
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\gradio\route_utils.py", line 261, in call_process_api
    output = await app.get_blocks().process_api(
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\gradio\blocks.py", line 1786, in process_api
    result = await self.call_function(
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\gradio\blocks.py", line 1338, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\anyio\_backends\_asyncio.py", line 2144, in run_sync_in_worker_thread
    return await future
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\anyio\_backends\_asyncio.py", line 851, in run
    result = context.run(func, *args)
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\gradio\utils.py", line 759, in wrapper
    response = f(*args, **kwargs)
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\gradio\utils.py", line 759, in wrapper
    response = f(*args, **kwargs)
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "app.py", line 176, in inference
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\musetalk\utils\preprocessing.py", line 97, in get_landmark_and_bbox
    results = inference_topdown(model, np.asarray(fb)[0])
  File "E:\BaiduNetdiskDownload\MuseTalk\MuseTalk\python310\lib\site-packages\mmpose\apis\inference.py", line 165, in inference_topdown
    h, w = img.shape[:2]
AttributeError: 'NoneType' object has no attribute 'shape'

heia***

FFmpge需要配置这个编码吗？