TheMadFaker
DF Pleb
Can anyone post some good examples of different face/background style power settings?
papolk said:0 and 0
TheMadFaker said:After more reading around I see others starting with 10 / 10 and then lowering to 0.1 / 4 or something. What is the logic behind doing that? I'm trying to understand more but testing things takes VERY long
TheMadFaker said:After more reading around I see others starting with 10 / 10 and then lowering to 0.1 / 4 or something. What is the logic behind doing that? I'm trying to understand more but testing things takes VERY long
TheMadFaker said:After more reading around I see others starting with 10 / 10 and then lowering to 0.1 / 4 or something. What is the logic behind doing that? I'm trying to understand more but testing things takes VERY long
deep88 said:I started with 10 / 10 and now I switched to 0.1 / 4.
Does the face style power have anything to do with that the face on my preview has grey area on it? ...and it sometimes seems too "art like", not natural.
See photo attached.
Will it recover with the new 0.1 / 4 settings?
dpfks said:deep88 said:I started with 10 / 10 and now I switched to 0.1 / 4.
Does the face style power have anything to do with that the face on my preview has grey area on it? ...and it sometimes seems too "art like", not natural.
See photo attached.
Will it recover with the new 0.1 / 4 settings?
Kinda, the longer you train with higher style power, the more it will look like your destination model (skin tone included). The grey around the face is because the data_dst skin color is different. Background style is at 4 and will likely be adding to the greyness around the mask.
If you want to have the same skin color as your data_dst, just train with random color transfer = y
deep88 said:dpfks said:deep88 said:I started with 10 / 10 and now I switched to 0.1 / 4.
Does the face style power have anything to do with that the face on my preview has grey area on it? ...and it sometimes seems too "art like", not natural.
See photo attached.
Will it recover with the new 0.1 / 4 settings?
Kinda, the longer you train with higher style power, the more it will look like your destination model (skin tone included). The grey around the face is because the data_dst skin color is different. Background style is at 4 and will likely be adding to the greyness around the mask.
If you want to have the same skin color as your data_dst, just train with random color transfer = y
Ok, I am going to try this.
I have 2 more questions that I haven't found an answer for:
1. What does 'ca_weights' mean? It is not mentioned in the tutorial.
2. There is a slight zoom in the destination video, meaning the person's face is getting closer. In this case the source face becomes a little blurry. Can it be resolved somehow?
Thanks for the help.
deep88 said:What is the way of training in high resolution?
I have used youtube videos at least 720p for my source data.
TheMadFaker said:How many iterations in are you? In your first example you're just over 8000. You won't get good results until at least 100000
dpfks said:train until 130k+ and it'll be nice.
The number of images in data_dst isn't important.
deep88 said:I started with 10 / 10 and now I switched to 0.1 / 4.
Does the face style power have anything to do with that the face on my preview has grey area on it? ...and it sometimes seems too "art like", not natural.
See photo attached.
Will it recover with the new 0.1 / 4 settings?
TheMadFaker said:How many iterations in are you? In your first example you're just over 8000. You won't get good results until at least 100000
VirginBoI said:deep88 said:I started with 10 / 10 and now I switched to 0.1 / 4.
Does the face style power have anything to do with that the face on my preview has grey area on it? ...and it sometimes seems too "art like", not natural.
See photo attached.
Will it recover with the new 0.1 / 4 settings?
Bruh make face style power and background style power both 0.0 as they basically do more loss than good.
Apply random colour transfer to SRC dataset should be your choice cause it basically not only gives the skin tone but also less GPU intensive and more stable.
Face style power = colour/skin tone
Background style power = skin morphing to date face
Both being constant values need to be monitored else the change will be drastic and within 5-6k iterations you will not recognise your src face.