A2H

I tried to run google colab demo, but it give me this info: No module named 'demo' specificly this: `--------------------------------------------------------------------------- ModuleNotFoundError Traceback (most recent call last) [](https://localhost:8080/#) in ----> 1...

CUDA bfloat16 problem

4

``` 2023-10-23 10:49:30,409 WARNING: logs/HiFiSVC doesn't exist yet! Global seed set to 594461 Using bfloat16 Automatic Mixed Precision (AMP) GPU available: True (cuda), used: True TPU available: False, using: 0...

I found this video: https://www.youtube.com/watch?v=VGxt5XghRdw It's called x-portrait, the source code is not released yet, but... I thought maybe the video could be somehow informative to improve aniportrait. It seems...

as in the title. after using: ``` python face_recon_videos.py \ --input_dir path_to_videos \ --keypoint_dir path_to_keypoint \ --output_dir output_dir \ --inference_batch_size 100 \ --name=model_name \ --epoch=20 \ --model facerecon ``` I've...

(IDEA/REQUEST) Possible consistancy for Face Reenactment and better animation

1

I was searching through github to find solutions for face animation and the consistancy od face resemblence and I found that project DreamTalk was made with Alibaba contribution so maybe...

Body movements + jittery + artifacts issues

2

Thank you for your incredible work on this! I was testing the program and it's settings to get the best results out of it and I found some things and...

As in the title. The denoiser script makes input audio very distorted, too loud and clipping. According to guide i used this script: ``` python tools/diffusion/inference.py --config configs/denoiser_cn_hubert.py \ --checkpoint...