SadTalker icon indicating copy to clipboard operation
SadTalker copied to clipboard

TypeError: cannot unpack non-iterable NoneType object

Open pk5ls20 opened this issue 1 year ago • 4 comments

env:Windows11 当尝试使用python app.py生成时报错

C:\Users\pk5ls\AppData\Local\Temp\522882b377634f2b601b0a1d0f86207d7ee54fdb\tmpkvypcmaj.png
Traceback (most recent call last):
  File "C:\Users\pk5ls\anaconda3\envs\sadtalker\lib\site-packages\gradio\routes.py", line 393, in run_predict
    output = await app.get_blocks().process_api(
  File "C:\Users\pk5ls\anaconda3\envs\sadtalker\lib\site-packages\gradio\blocks.py", line 1108, in process_api
    result = await self.call_function(
  File "C:\Users\pk5ls\anaconda3\envs\sadtalker\lib\site-packages\gradio\blocks.py", line 915, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "C:\Users\pk5ls\anaconda3\envs\sadtalker\lib\site-packages\anyio\to_thread.py", line 31, in run_sync
    return await get_asynclib().run_sync_in_worker_thread(
  File "C:\Users\pk5ls\anaconda3\envs\sadtalker\lib\site-packages\anyio\_backends\_asyncio.py", line 937, in run_sync_in_worker_thread
    return await future
  File "C:\Users\pk5ls\anaconda3\envs\sadtalker\lib\site-packages\anyio\_backends\_asyncio.py", line 867, in run
    result = context.run(func, *args)
  File "E:\ai-draw\SadTalker\src\gradio_demo.py", line 101, in test
    first_coeff_path, crop_pic_path, crop_info = self.preprocess_model.generate(pic_path, first_frame_dir)
  File "E:\ai-draw\SadTalker\src\utils\preprocess.py", line 84, in generate
    x_full_frames, crop, quad = self.croper.crop(x_full_frames, xsize=pic_size)
TypeError: cannot unpack non-iterable NoneType object

stable-diffusion的插件中使用同样报错

pk5ls20 avatar Apr 08 '23 10:04 pk5ls20

C:\Users\pk5ls\AppData\Local\Temp\522882b377634f2b601b0a1d0f86207d7ee54fdb\tmpkvypcmaj.png 这张图可以上传我看看吗

vinthony avatar Apr 08 '23 10:04 vinthony

哦对...看上去在我这里,它处理二次元型图片会报错,而处理2.5d/三次元图片(也就是webui下面Examples那样)则不会报错 附图: 1

pk5ls20 avatar Apr 08 '23 10:04 pk5ls20

我们的模型是在真实数据训练的,太二次元的检测不到人脸~ 可能后续会集成tha2/tha3的功能,就可以处理anime了

vinthony avatar Apr 08 '23 10:04 vinthony

我们的模型是在真实数据训练的,太二次元的检测不到人脸~ 可能后续会集成tha2/tha3的功能,就可以处理anime了

好的好的🥰

pk5ls20 avatar Apr 08 '23 11:04 pk5ls20