|
本帖最后由 liangzr1976 于 2024-6-18 07:03 编辑
太难了。
参考连接。
https://blog.csdn.net/yyz_1987/article/details/133632123
让照片人物开口说话,SadTalker 安装及使用(避坑指南) By 特立独行的猫a @ 2023-10-08
https://avoid.overfit.cn/post/e667c6d98cb945e7895fea5eb69f62eb
照片会说话?开源AI数字人工具SadTalker环境搭建和使用教程
https://zhuanlan.zhihu.com/p/642603593
AI绘画:最新SDW+单图换脸+单图说话汉化软件包
https://weibo.com/ttarticle/p/show?id=2309404968321983578653
AI数字人制作工具 SadTalker 支持本地生成数字人及虚拟主播 二花虚拟资源 作者: 二花虚拟资源网 2023-11-15
他链接到:
https://erhua.cc/Chajian_view_id ... fd996b5ca07141f0fa5
AI数字人制作工具 SadTalker 支持本地生成数字人及虚拟主播 免费软件 / 视频软件2023年11月23日分享到:
下载地址:见链接的百度网盘,是压缩包,不排除是收费服务
隔壁论坛标题:不依赖SD,让图片唱歌说话的sadtalker项目!。2024/06/18早上,下载完毕,可以直接运行,但提示如下(文件太大,转载30天 如下:https://zhuanlan.zhihu.com/p/642603593
AI绘画:最新SDW+单图换脸+单图说话汉化软件包
):
using safetensor as default
Traceback (most recent call last):
File ".\inference.py", line 144, in <module>
main(args)
File ".\inference.py", line 36, in main
preprocess_model = CropAndExtract(sadtalker_paths, device)
File "E:\a\SadTalker\SadTalker\SadTalkerv2\src\utils\preprocess.py", line 49, in __init__
self.propress = Preprocesser(device)
File "E:\a\SadTalker\SadTalker\SadTalkerv2\src\utils\croper.py", line 21, in __init__
self.predictor = KeypointExtractor(device)
File "E:\a\SadTalker\SadTalker\SadTalkerv2\src\face3d\extract_kp_videos_safe.py", line 27, in __init__
self.detector = init_alignment_model('awing_fan',device=device, model_rootpath=root_path)
File "E:\a\SadTalker\SadTalker\SadTalkerv2\python38\lib\site-packages\facexlib\alignment\__init__.py", line 19, in init_alignment_model
model.load_state_dict(torch.load(model_path)['state_dict'], strict=True)
File "E:\a\SadTalker\SadTalker\SadTalkerv2\python38\lib\site-packages\torch\serialization.py", line 795, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "E:\a\SadTalker\SadTalker\SadTalkerv2\python38\lib\site-packages\torch\serialization.py", line 1012, in _legacy_load
result = unpickler.load()
File "E:\a\SadTalker\SadTalker\SadTalkerv2\python38\lib\site-packages\torch\serialization.py", line 958, in persistent_load
wrap_storage=restore_location(obj, location),
File "E:\a\SadTalker\SadTalker\SadTalkerv2\python38\lib\site-packages\torch\serialization.py", line 215, in default_restore_location
result = fn(storage, location)
File "E:\a\SadTalker\SadTalker\SadTalkerv2\python38\lib\site-packages\torch\serialization.py", line 182, in _cuda_deserialize
device = validate_cuda_device(location)
File "E:\a\SadTalker\SadTalker\SadTalkerv2\python38\lib\site-packages\torch\serialization.py", line 166, in validate_cuda_device
raise RuntimeError('Attempting to deserialize object on a CUDA '
RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.
|
|