Question about the result in DreamVideo

Open RongPiKing opened this issue 1 year ago • 3 comments

Why are my results after training inference so poor? The example I use is “a * is playing guitar” https://github.com/ali-vilab/VGen/assets/67503039/83b3358e-3385-40d6-b6c4-7d1739bf5ae8

Jun 12 '24 09:06 RongPiKing

The results appear to show that the subject ID is overly preserved. You might try reducing the identity_adapter_index and increasing the motion_adapter_index during inference.

Jun 13 '24 04:06 weilllllls

Thank you for your answer！I did not modify any code, so do I need to adjust the parameters in the code myself to achieve the effect in the paper?

Jun 13 '24 06:06 RongPiKing

Yes, you will need to adjust the hyperparameters to suit your specific cases and we also provide some examples.

Jun 13 '24 12:06 weilllllls