AI数字人新玩法！EchoMimic V2音频驱动，打造超逼真动态角色|AI Digital Human! EchoMimic V2 Audio-Driven Animation

[@yumingli6173]

这个教程非常详细👍

[@beartina4522]

可以分享一下用到的模型吗？感谢

[@HùngPhạmVănMạnh]

你可以将输出应用为手机图像尺寸 16:9

[@qiwen-od1dk]

name 'AudioFileClip' is not defined，请问这个是什么原因

[@lizheng6668]

这个效果非常好了！！几乎没抖

[@xuande99cn]

请问一下，如果用数字人做一款逼真的，两个人坐着闲聊的节目，这个Ai 可能实现吗 ❤

[@sunleyan_2021]

可以

[@lizheng6668]

讲的这么好，不发一份到B站？国外翻墙有门槛，哈哈

[@tribuzeus]

How about a video tutorial to install EchoMimic v2 on Google Colab?

[@IAFlux]

suludos desde Bolivia, Sensei...

[@sunleyan_2021]

thanks

[@suyilei]

请教一下：4090运行成功但生成的视频画面有问题，提示如下：Pipelines loaded with `dtype=torch.float16` cannot run with `cpu` device. It is not recommended to move them to `cpu` as running them will fail. Please make sure to use an accelerator to run the pipeline in inference, due to the lack of support for`float16` operations on this device in PyTorch. Please, remove the `torch_dtype=torch.float16` argument, or use another device for inference. 配置： Total VRAM 24564 MB, total RAM 65349 MB pytorch version: 2.5.1+cu124 xformers version: 0.0.28.post3 Set vram state to: NORMAL_VRAM Device: cuda:0 NVIDIA GeForce RTX 4090 : cudaMallocAsync

[@sunleyan_2021]

检查你的有些节点是不再cpu上跑了，把设备宣称GPU

[@TuherLopet]

下模型费劲啊

[@sunleyan_2021]

我只能说 加油

[@MichaelatSydney]

请问一下，手的姿势能不能多一点呢

[@sunleyan_2021]

可以，自己需要制作pkl文件

[@ssrvpn]

这个目前能达到实用吗，我丢给它一段10分钟的视频，能否直接生成10分钟的视频。还是说，必须得分割成多少秒的一段段的去做

[@sunleyan_2021]

还是要分段的，10分钟太长了

[@ssrvpn]

@@sunleyan_2021 能否实现自动化分段，我丢给它一段10分钟的语音，然后实现自动分段转视频，最后自动合并。

[@sunleyan_2021]

@@ssrvpn 这个是可以的

[@sunleyan_2021]

但需要自己写程序来分段

[@ssrvpn]

@@sunleyan_2021 感谢播主的回复，看来如果自己不会写程序就没办法了。目前除了这个，文字或语音转视频，能够商业应用的还是 HeyGen 能实用，但HeyGen 的手和胳膊不会动，播主还有没有其它推荐

[@makisekurisu_jp]

這已經是當下最強的開放模型所能達到的虛擬人像結果了，但和hengen azure比起來還差很遠

[@sunleyan_2021]

别着急，让子弹再飞一会儿

[@李万金-t9y]

为什么我用40秒的音频驱动生成的视频最多只有13秒，length设置成2000了，官方不是说能生成50秒的吗

[@sunleyan_2021]

我也遇到了同样的问题，我怀疑是第三方的程序是不是没有完美适配。如果的确需要，先把音频分割一下

[@WendyWongn]

is there any chance for 3060 12gb ?

[@sunleyan_2021]

reduce length or use lowram mode

[@lizheng6668]

gan loss v4这个lora在哪里下载呢？

[@sunleyan_2021]

我自己练的，换成你自己的就行

[@ChangTanAi]

腊兄，你的显卡是多少显存的？

[@sunleyan_2021]

3070 ts 16G

[@vichikaru]

那我的4060ti16 有機會了

[@占酷]

Cannot process installed package torchsde 0.2.5 in 'h:\\comfyui-aki-v1.2\\python\\lib\\site-packages' because it has an invalid requirement: │ .* suffix can only be used with `==` or `!=` operators │ numpy (>=1.19.*) ; python_version >= "3.7" │ ~~~~~~~^ ╰─> Starting with pip 24.1, packages with invalid requirements can not be processed.

[@sunleyan_2021]

把你的numpy升级到1.19以上 python升级到3.7以上

[@yorkane123]

The FluxGuidance should be 3.0

[@sunleyan_2021]

use depth control in flux tools the flux guidance should be 30

[@dleon9781]

感谢大佬分享！ 在comfyui中出现报错： got prompt when use echo v2,need choice a pose dir,using default pose for testing ! ***** infer length is 120 poses_tensor:torch.Size([1, 3, 120, 768, 768]) !!! Exception during processing !!! [WinError 2] 系统找不到指定的文件。 Traceback (most recent call last): File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 324, in execute output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 199, in get_output_data return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 170, in _map_node_over_list process_inputs(input_dict, i) File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 159, in process_inputs results.append(getattr(obj, func)(**inputs)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_EchoMimic\EchoMimic_node.py", line 463, in em_main output_video=process_video_v2(image, audio_file, width, height, length, seed, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_EchoMimic\utils.py", line 149, in process_video_v2 video = pipe( ^^^^^ File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_EchoMimic\echomimic_v2\src\pipelines\pipeline_echomimicv2.py", line 466, in __call__ whisper_feature = self.audio_guider.audio2feat(audio_path) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_EchoMimic\src\models\whisper\audio2feature.py", line 100, in audio2feat result = self.model.transcribe(audio_path) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_EchoMimic\src\models\whisper\whisper\transcribe.py", line 85, in transcribe mel = log_mel_spectrogram(audio) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_EchoMimic\src\models\whisper\whisper\audio.py", line 111, in log_mel_spectrogram audio = load_audio(audio) ^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_EchoMimic\src\models\whisper\whisper\audio.py", line 44, in load_audio .run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\ffmpeg\_run.py", line 313, in run process = run_async( ^^^^^^^^^^ File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\ffmpeg\_run.py", line 284, in run_async return subprocess.Popen( ^^^^^^^^^^^^^^^^^ File "subprocess.py", line 1026, in __init__ File "subprocess.py", line 1538, in _execute_child FileNotFoundError: [WinError 2] 系统找不到指定的文件。 请问大佬哪里出问题了呢？

[@sunleyan_2021]

echomimicv2升级到最新版，那个posedir别填，让他用系统的

[@dleon9781]

@@sunleyan_2021 已经是最新的了····

[@dleon9781]

@@sunleyan_2021 把ffmpeg安好后就搞定了！ 谢谢！