Open red-sponge opened 1 year ago
同样问题,怎么解决?
I am getting error too
Same here
which version of the facexlib are you using?
facexlib introduces this new argument in v0.3.0. Here, I fixed it by adding a self FAN function in the new version: https://github.com/OpenTalker/SadTalker/commit/ae0b26359d44c9379450a8e02a38b45eeec15549. You can try to update the code.
facexlib introduces this new argument in v0.3.0. Here, I fixed it by adding a self FAN function in the new version: ae0b263. You can try to update the code.
Hello friend In my case, I already had this argument in my version of extract_kp_videos_safe.py, so I decided to replace all my_awing_arch.py with the one in the link you posted and it worked perfectly.
Thanks for the idea!
I have got this error when generate in SD Webui. Do you have any solution?
version: v1.4.0 • python: 3.10.6 • torch: 2.0.1+cu118 • xformers: 0.0.20 • gradio: 3.32.0 • checkpoint: e4a30e4607
using safetensor as default {'checkpoint': 'C:\Users\USER\Documents\stable-diffusion-webui\extensions\SadTalker\checkpoints\SadTalker_V0.0.2_256.safetensors', 'dir_of_BFM_fitting': 'C:\Users\USER\Documents\stable-diffusion-webui/extensions/SadTalker/src/config', 'audio2pose_yaml_path': 'C:\Users\USER\Documents\stable-diffusion-webui/extensions/SadTalker/src/config\auido2pose.yaml', 'audio2exp_yaml_path': 'C:\Users\USER\Documents\stable-diffusion-webui/extensions/SadTalker/src/config\auido2exp.yaml', 'use_safetensor': True, 'mappingnet_checkpoint': 'C:\Users\USER\Documents\stable-diffusion-webui\extensions\SadTalker\checkpoints\mapping_00229-model.pth.tar', 'facerender_yaml': 'C:\Users\USER\Documents\stable-diffusion-webui/extensions/SadTalker/src/config\facerender.yaml'} Traceback (most recent call last): File "C:\Users\USER\Documents\stable-diffusion-webui\venv\lib\site-packages\gradio\routes.py", line 422, in run_predict output = await app.get_blocks().process_api( File "C:\Users\USER\Documents\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1323, in process_api result = await self.call_function( File "C:\Users\USER\Documents\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1051, in call_function prediction = await anyio.to_thread.run_sync( File "C:\Users\USER\Documents\stable-diffusion-webui\venv\lib\site-packages\anyio\to_thread.py", line 31, in run_sync return await get_asynclib().run_sync_in_worker_thread( File "C:\Users\USER\Documents\stable-diffusion-webui\venv\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_worker_thread return await future File "C:\Users\USER\Documents\stable-diffusion-webui\venv\lib\site-packages\anyio_backends_asyncio.py", line 867, in run result = context.run(func, args) File "C:\Users\USER\Documents\stable-diffusion-webui\modules\call_queue.py", line 13, in f res = func(args, **kwargs) File "C:\Users\USER\Documents\stable-diffusion-webui/extensions/SadTalker\src\gradio_demo.py", line 50, in test self.preprocess_model = CropAndExtract(self.sadtalker_paths, self.device) File "C:\Users\USER\Documents\stable-diffusion-webui/extensions/SadTalker\src\utils\preprocess.py", line 49, in init self.propress = Preprocesser(device) File "C:\Users\USER\Documents\stable-diffusion-webui/extensions/SadTalker\src\utils\croper.py", line 21, in init self.predictor = KeypointExtractor(device) File "C:\Users\USER\Documents\stable-diffusion-webui/extensions/SadTalker\src\face3d\extract_kp_videos_safe.py", line 45, in init self.detector = init_alignment_model('awing_fan',device=device, model_rootpath=root_path) File "C:\Users\USER\Documents\stable-diffusion-webui/extensions/SadTalker\src\face3d\extract_kp_videos_safe.py", line 21, in init_alignment_model model = FAN(num_modules=4, num_landmarks=98, device=device) TypeError: FAN.init() got an unexpected keyword argument 'device'