ZJYang
ZJYang
Thank you for your interest! The flickering issue may be attributed to the diffusion model, and we are actively working to address this in the future.
https://github.com/kkroening/ffmpeg-python/issues/251 Maybe you can refer this issue. I hope this will be helpful!
We just released the demo page.
We have finetuned the weight of SD1.5 in AniPortrait. Therefore, directly replacing it with SDXL without retraining will result in poor performance. So you need to finetune SDXL on training...
Thank you for your interest! We have also noticed this work. And we are trying to apply LCM in our framework to speed up the inference process. We think it...