Zejun-Yang
After 40 minutes still stays on 0%
I installed everything perfectly. But when I run the command :
python -m scripts.pose2vid --config ./configs/prompts/animation.yaml -W 512 -H 512
the process stops here forever:
E:\AI\AniPortrait\AniPortrait\src\pipelines\pipeline_pose2vid_long.py:408: FutureWarning: Accessing config attribute in_channels directly via 'UNet3DConditionModel' object attribute is deprecated. Please access 'in_channels' over 'UNet3DConditionModel's config object instead, e.g. 'unet.config.in_channels'. num_channels_latents = self.denoising_unet.in_channels 0%| | 0/25 [00:00<?, ?it/s]
What is exactly the issue? What is messing? My Gfx Card is RTX 3070 Ti 8 GB vRams. Any help please?
Perhaps the pose video is too long. Consider using the command -L 300 to obtain a shorter video.
Thanks for the reply.
I added the -L 300 to the command line, and finally some improvements.
After around 30 minutes, it did 4%.
Actually, the video is the sample that comes with the package (48 sec).
Is there a way to increase the speed of the process? Or any tweaks here and there?
https://huggingface.co/spaces/ZJYang/AniPortrait_official
We recommend you to use our gradio demo on hugging face.
the demo on hugging face doesn't seem to work? I've been trying for two days but it just gives an error after a few hours
the demo on hugging face doesn't seem to work? I've been trying for two days but it just gives an error after a few hours
We have updated a new version with frame interpolation acceleration. You can have a try.