Closed adilhasan927 closed 1 week ago
Hi, we follow the parameter setting as in latent diffusion. eta=1.0 is something that the open-sourced LDM-ImageNet used in training, while eta=0.0 is the setting they used for sampling. Under our case, you can ignore the -e argument for ImageNet. Sorry for the confusion.
Different parameters can lead to different FID, but I can't guarantee how great the impact is.
Ah ok, thank you, that makes sense.
In sample_diffusion_ldm_imagenet.py:
why do we set ddim_eta=0.0 and ignore the eta=1.0 supplied in the arguments?
especially since, the recommended command line setting for imagenet LDM is:
where we can note -e 1.0 -> eta=1.0.
Does this affect the FID expected for the generated images?