MuseTalk

MuseTalk copied to clipboard

FileNotFoundError: ./models/dwpose/dw-ll_ucoco_384.pth can not be found.

2

(musetalk) H:\MuseTalk\MuseTalk> python -m scripts.inference --inference_config configs/inference/test.yaml please download ffmpeg-static and export to FFMPEG_PATH. For example: export FFMPEG_PATH=/musetalk/ffmpeg-4.4-amd64-static Loads checkpoint by local backend from path: ./models/dwpose/dw-ll_ucoco_384.pth Traceback (most recent call...

Asukaandjst

请问一下，python -m scripts.realtime_inference --inference_config configs/inference/realtime.yaml --skip_save_images这个命令运行后的作用，我没有只找到了对应的pkl文件，没有看到对应的视频，应该怎么使用这种流式的？

1

hjj-lmx

嘴巴和胡子对于口型识别的影响

1

目前有的形象有胡子 ，但是都有基本的嘴部特征，最后输出的效果 有的嘴部就糊了. 请问有什么办法可以针对性的调优,或者训练 以应对可能的情况

mmlingyu

应该如何提速，我在A100上生成40s的视频需要5、6分钟，有点慢，大佬们，有解决方案吗？

3

hjj-lmx

About the relationship between Whisper vs pretrained UNet SDv1.4

2

In this work, the author adopted Whisper-tiny (d_model=384) to extract audio feature, while training UNet from scratch. I guess the reason behind training from scratch instead of loading pretrained SDv1.4...

huyduong7101

ZeroDivisionError

2

``` please download ffmpeg-static and export to FFMPEG_PATH. For example: export FFMPEG_PATH=/musetalk/ffmpeg-4.4-amd64-static Loads checkpoint by local backend from path: ./models/dwpose/dw-ll_ucoco_384.pth cuda start Downloading: "https://www.adrianbulat.com/downloads/python-fan/s3fd-619a316812.pth" to /root/.cache/torch/hub/checkpoints/s3fd-619a316812.pth 0%| | 0.00/85.7M [00:00

tmfql123

卡在这里·过不去了，帮忙看一下

1


Battlecraft369

Inference API for MuseTalk with improvements!

9

Hey guys, really cool work! I'm an engineer at [Sieve](http://sievedata.com/) and we've been working with lip-syncing tech for some time now. We were quite impressed by the capabilities of MuseTalk...

gaurangbharti1

您好，请问为什么导出onnx文件会把所有算子的权重都导出？

5

您好，我写了一个onnx导出脚本，只导出unet.model，然而导出后文件并不是保存在一个model.onnx中，，而是model.onnx只保存文件结构，而权重保存成零散的文件？ 导出代码如下: ``` # ===============================构建算子 import onnxscript ## Assuming you use opset18 from onnxscript.onnx_opset import opset18 as op custom_opset = onnxscript.values.Opset(domain="torch.onnx", version=17) @onnxscript.script(custom_opset) def ScaledDotProductAttention( query, key, value, dropout_p, ):...

DestoryVIP

"Bbox shift" has a significant impact on the output. Hence, does anyone try to use "bbox shift" as augmentation in training?

huyduong7101