Queries the hash table for a given key and returns the aggregated output. Args: key (torch.Tensor): Key tensor of the fo

Render the scene. Background tensor (bg_color) must be on GPU!

Updates paths inside resnets to the new naming scheme (local renaming)

Updates paths inside resnets to the new naming scheme (local renaming)

Zero out the parameters of a module and return it.

Evaluate a function without caching intermediate activations, allowing for reduced memory at the expense of extra compute in the backward pas

r""" Offloads all models to CPU using accelerate, reducing memory usage with a low impact on performance. Compared to `enable_sequenti

r""" Offloads all models to CPU using accelerate, reducing memory usage with a low impact on performance. Compared to `enable_sequenti

r""" Offloads all models to CPU using accelerate, reducing memory usage with a low impact on performance. Compared to `enable_sequenti

r""" Offloads all models to CPU using accelerate, significantly reducing memory usage. When called, unet, text_encoder, vae and safety

r""" Enable memory efficient attention from [xFormers](https://facebookresearch.github.io/xformers/). When this option is enabled, you

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

python code from: https://github.com/ronaldosena/imagens-medicas-2/blob/40171a6c259edec7827a6693a93955de2bd39e76/Aulas/aula_2_-_uniform_filte

python code from: https://github.com/ronaldosena/imagens-medicas-2/blob/40171a6c259edec7827a6693a93955de2bd39e76/Aulas/aula_2_-_uniform_filte

:param x: img of size (bs, c, h, w) :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])

Updates paths inside attentions to the new naming scheme (local renaming)

Updates paths inside attentions to the new naming scheme (local renaming)