peizhiluo007
peizhiluo007
失效了,再发一下
可能你需要更新下 1、comfyUI更新到最新版本,有支持audio的load和save操作,是一致了。 2、或者ComfyUI-VideoHelperSuite 更新到最新版本,也可以。
可以用的,而且挺好用的。 代码也写的不错,如果遇到报错,打开代码看下。 如果,能把几个权重文件放什么位置写的清楚写就更好了。
自己到 huggingface 去搜索下 openvoice,下载下就行了。
def load_pipeline(self, weight_dtype): if weight_dtype == "float32": weight_dtype = torch.float32 elif weight_dtype == "float16": weight_dtype = torch.float16 elif weight_dtype == "bfloat16": weight_dtype = torch.bfloat16 noise_scheduler = DDPMScheduler.from_pretrained( WEIGHTS_PATH, subfolder="scheduler" )...
> Wow that's awesome! Thanks! Could you open a PR with these changes? ok,i have submitted for review. and i think It's better to add the lowvram option , so.
你可以试试在crop_info后面加入Retargeting节点,并且将lip和eye设置成False
Select Scenes