search

hxngiee / DiffFace

DiffFace: Diffusion-based Face Swapping with Facial Guidance
Other
278 stars 17 forks source link

model performance #12

Open Bruc3Xu opened 1 year ago

Bruc3Xu commented 1 year ago

it seems that the model didn't work well when source and target face have different mask orientation. output_i_0_b_0

hxngiee commented 1 year ago

As shown in the figure below, it basically works even if the source and target have different poses.

The reason for incorrect samples seems to be attributed to the following factors:

  1. ID loss is set too large
  2. Target-preserving blending time is set too short.

It is recommended to lower the loss weight in the next line or decrease the time duration through masking_threshold argument.

output_i_0_b_0

Bruc3Xu commented 1 year ago

thanks for your reply, I changed the parameter setting including IDloss weight, mask_threshold, but still cannot get good result.The follwing images were used for testing. 004 004_target

luoxyhappy commented 11 months ago

same question, do you solve it now?

akankshasingh25 commented 10 months ago

Were you able to solve it @luoxyhappy @Bruc3Xu ? The face swaps are not of good quality even after manipulating loss parameters and hyperparameters.

luoxyhappy commented 10 months ago

Were you able to solve it @luoxyhappy @Bruc3Xu ? The face swaps are not of good quality even after manipulating loss parameters and hyperparameters.

Not yet.... And i have already given up trying now.

akankshasingh25 commented 9 months ago

Not yet.... And i have already given up trying now.

Same, I have been at it for a few months now. I couldn't find a way yet. @hxngiee, any help would be appreciated.