search

harlanhong / CVPR2022-DaGAN

Official code for CVPR2022 paper: Depth-Aware Generative Adversarial Network for Talking Head Video Generation
https://harlanhong.github.io/publications/dagan.html
Other
964 stars 126 forks source link

Hello, I was wondering what's wrong with my example, I follow the instruction but get different result #19

Closed twilight0718 closed 2 years ago

twilight0718 commented 2 years ago

I follow the instruction, set my parameter as followed:

CUDA_VISIBLE_DEVICES=7 python demo.py
--config config/vox-adv-256.yaml --driving_video source/example.mp4 --source_image source/example.png --checkpoint download/SPADE_DaGAN_vox_adv_256.pth.tar --kp_num 15 --generator SPADEDepthAwareGenerator --result_video results/example_out.mp4 --relative --adapt_scale

https://user-images.githubusercontent.com/37037808/169028484-142f9de3-acd6-45d6-950d-caacae9f593a.mp4

Is there something wrong with my parameters.

harlanhong commented 2 years ago

Hi @twilight0718 , Because you just miss an important parameter: find_best_frame. You can run the demo using the following command:

CUDA_VISIBLE_DEVICES=7 python demo.py --config config/vox-adv-256.yaml --driving_video source/example.mp4 --source_image source/example.png --checkpoint download/SPADE_DaGAN_vox_adv_256.pth.tar --kp_num 15 --generator SPADEDepthAwareGenerator --result_video results/example_out.mp4 --relative --adapt_scale --find_best_frame

twilight0718 commented 2 years ago

Appriciated for your reply!