Iván de Prado

@croqaz well, I have some doubts regarding the fix. By one side, I would say that it should be the user using `extruct` the one with the responsibility to filter...

I think the problem is that `torch` is imported in `setup.py` (see here https://github.com/facebookresearch/xformers/blob/main/setup.py#L23). This is problematic when installing all the dependencies of a project from scratch in an environment....

@yiyixuxu Unfortunately, it is not possible to implement it using `callback_on_the_step_end`. The reasons are: * The property `do_classifier_free_guidance` returns False when a distilled LCM model is used. But we need...

Something to keep in mind. Even if the `callback_on_step_begin` is introduced, two other changes are still required so that the goal feature in the PR is possible: * Add a...

I'm working on changing the code. Particularly, I propose to add the following parameters: ``` callback_on_step_end_also_before_start (`bool`, *optional*, defaults to False): If `True`, the `callback_on_step_end` function will also be called...

@yiyixuxu this is ready for a re-review. I've removed the old parameters, and introduced the following ones that are also backward compatible: ``` callback_on_step_end_also_at_init (`bool`, *optional*, defaults to False): If...

@a-r-r-o-w note that you could obtain almost the same effect that you get with `callback_on_step_begin` by using a `callback_on_step_end` with `callback_on_step_end_also_at_init` but ignoring the last invocation of the callback. For...

Hi @yiyixuxu I've already implemented the suggested changes. It would be nice if you can have a look.