Question regarding index_for_timestep in EDM euler scheduler

[odieXin]

# Copied fromdiffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler.index_for_timestep
    def index_for_timestep(self, timestep, schedule_timesteps=None):
        if schedule_timesteps is None:
            schedule_timesteps = self.timesteps

        indices = (schedule_timesteps == timestep).nonzero()

        # The sigma index that is taken for the **very** first `step`
        # is always the second index (or the last index if there is only 1)
        # This way we can ensure we don't accidentally skip a sigma in
        # case we start in the middle of the denoising schedule (e.g. for image-to-image)
        pos = 1 if len(indices) > 1 else 0

        return indices[pos].item()

Here pos = 1 if len(indices) > 1 else 0 in what cases will len(indices) > 1? Aren't sigmas strictly monotonic? I don't quite follow the comments, can someone help explain? Thanks!

[tolgacangoz]

As of my understanding, some image-to-image pipelines may have duplicated timesteps. Could you examine this issue and its successors: #5687.

[odieXin]

Thanks!! @StandardAI

[tolgacangoz]

Also Cc: @yiyixuxu.