通过webui能正常生成视频 通过api接口无法生成

[anyunzhong]

using safetensor as default
{'checkpoint': 'checkpoints/SadTalker_V0.0.2_256.safetensors', 'dir_of_BFM_fitting': 'src/config', 'audio2pose_yaml_path': 'src/config/auido2pose.yaml', 'audio2exp_yaml_path': 'src/config/auido2exp.yaml', 'use_safetensor': True, 'mappingnet_checkpoint': 'checkpoints/mapping_00229-model.pth.tar', 'facerender_yaml': 'src/config/facerender.yaml'}
/tmp/gradio/6410032a78b420aa486a26de7f21e7d6285745ebb00e9484f599aa63cf5e7313/a15acedbbfe86dfc67cb301ba18d5565.png
Traceback (most recent call last):
File "/root/miniconda3/envs/sadtalker/lib/python3.8/site-packages/gradio/queueing.py", line 536, in process_events
response = await route_utils.call_process_api(
File "/root/miniconda3/envs/sadtalker/lib/python3.8/site-packages/gradio/route_utils.py", line 322, in call_process_api
output = await app.get_blocks().process_api(
File "/root/miniconda3/envs/sadtalker/lib/python3.8/site-packages/gradio/blocks.py", line 1935, in process_api
result = await self.call_function(
File "/root/miniconda3/envs/sadtalker/lib/python3.8/site-packages/gradio/blocks.py", line 1520, in call_function
prediction = await anyio.to_thread.run_sync( # type: ignore
File "/root/miniconda3/envs/sadtalker/lib/python3.8/site-packages/anyio/to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
File "/root/miniconda3/envs/sadtalker/lib/python3.8/site-packages/anyio/_backends/_asyncio.py", line 2364, in run_sync_in_worker_thread
return await future
File "/root/miniconda3/envs/sadtalker/lib/python3.8/site-packages/anyio/_backends/_asyncio.py", line 864, in run
result = context.run(func, *args)
File "/root/miniconda3/envs/sadtalker/lib/python3.8/site-packages/gradio/utils.py", line 826, in wrapper
response = f(*args, **kwargs)
File "/root/SadTalker/src/gradio_demo.py", line 96, in test
first_coeff_path, crop_pic_path, crop_info = self.preprocess_model.generate(pic_path, first_frame_dir, preprocess, True, size)
File "/root/SadTalker/src/utils/preprocess.py", line 113, in generate
frames_pil = [Image.fromarray(cv2.resize(frame,(pic_size, pic_size))) for frame in x_full_frames]
File "/root/SadTalker/src/utils/preprocess.py", line 113, in
frames_pil = [Image.fromarray(cv2.resize(frame,(pic_size, pic_size))) for frame in x_full_frames]
cv2.error: OpenCV(4.10.0) 👎 error: (-5:Bad argument) in function 'resize'

Overload resolution failed:

• Can't parse 'dsize'. Sequence item with index 0 has a wrong type
• Can't parse 'dsize'. Sequence item with index 0 has a wrong type

这是调用接口代码
client = Client("http://xxxxxx:80/")
result = client.predict(
source_image=handle_file('https://xxx.com/image/a15acedbbfe86dfc67cb301ba18d5565.png'),
driven_audio=handle_file('https://xxx.com/file/voice.mp3'),
preprocess="crop",
still_mode=False,
use_enhancer=False,
batch_size=2,
size="256",
pose_style=0,
api_name="/test"
)
print(result)

[tission]

same problem.