r""" Pipeline to generate image variations from an input image using Stable Diffusion. This model inherits from [`DiffusionPipeline`]. Check

A class that represents an implementation of the Elo Rating System

A 2D Transformer model for image-like data. Parameters: num_attention_heads (`int`, *optional*, defaults to 16): The number of heads

Subclass torch's LayerNorm to handle fp16.

r""" A basic Transformer block. Parameters: dim (`int`): The number of channels in the input and output. num_attention_heads

Quoting from https://arxiv.org/abs/2302.05543: "Stable Diffusion uses a pre-processing method similar to VQ-GAN [11] to convert the entire da

The output of [`ControlNetModel`]. Args: down_block_res_samples (`tuple[torch.Tensor]`): A tuple of downsample activatio

r""" Metric calculator

The output of [`Transformer2DModel`]. Args: sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` or `(ba

The output of [`UNet2DConditionModel`]. Args: sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):

r""" Default processor for performing attention-related computations.

A class to represent a player in the Elo Rating System

Modified from https://github.com/threestudio-project/threestudio/blob/main/threestudio/utils/callbacks.py#L60

A ControlNet model. Args: in_channels (`int`, defaults to 4): The number of channels in the input sample. flip_s

r""" A conditional 2D UNet model that takes a noisy sample, conditional state, and a timestep and returns a sample shaped output. This mo