G-force78

Too complex for a hobbyist like me but I found these that explain it https://openaccess.thecvf.com/content/CVPR2023/supplemental/Zhang_SadTalker_Learning_Realistic_CVPR_2023_supplemental.pdf https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_SadTalker_Learning_Realistic_3D_Motion_Coefficients_for_Stylized_Audio-Driven_Single_CVPR_2023_paper.pdf Figure 3. The structure of our ExpNet. We involve a monocular 3D face reconstruction...

> I use the example motion02，and the result is uploaded as data.zip,the face is collapse。 LOL..funny video, its because stable diffusion doesn't do faces very well unless its up close

Hi, many thanks for the work on this voice cloning is super interesting, I am trying to test tortoise mrq version in the 4bit colab on free tier but failing...

I've tried a few different videos and found the size of the face in the image/video should be less than 400 as the entire masked area is 512px which can...

No it cant, close the space in the file manager and it works the same

I had similar issue, I fixed it by adding this in before the command line , obviously your file path may need to be changed !git apply --ignore-whitespace /content/stable-diffusion-webui/extensions/sd-webui-two-shot/0001-Adding-after_ui_callback-for-scripts.patch

Check you have the same as this here https://huggingface.co/spaces/ZJYang/AniPortrait_official/tree/main/pretrained_model

The flickering could be down to poor interpolation and or a frame rate out of sync with the pose video. I think it would be best to lock the FPS...

No I pressed nothing

https://github.com/harisreedhar/Swap-Mukham or automatic1111 roop extension