Faceswap Forum

[mention]torzdf[/mention] you have written in the training manual that :- Dfaker (64/128px input, 128/256px output).

So when does it take 128px as input.
Does it happen when we select 256px as output?

Similarly in DFL-SAE (64-256px input, 64-256px output) & Unbalanced (64-512px input, 64-512px output) model configuration, we are only allowed to change the input size, so there also does selecting an input size results in the same output size?

Yes. the models referenced there have the input size and output size linked. Do for Dfaker (for example) input size is also 1/2 of the output size.