r""" Instantiate a pretrained MultiControlNet model from multiple pre-trained controlnet models. The model is set in evaluation mode

This does the final conversion step: take locally converted weights and apply a global renaming to them. It splits attention layers, and take

r""" Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and en

Load LoRA weights specified in `pretrained_model_name_or_path_or_dict` into self.unet and self.text_encoder. All kwargs are forwarde

r""" Disable tiled VAE decoding. If `enable_tiling` was previously enabled, this method will go back to computing decoding in one step

r""" Download and cache a PyTorch diffusion pipeline from pretrained pipeline weights. Parameters: pretrained_model_name

Activates gradient checkpointing for the current model (may be referred to as *activation checkpointing* or *checkpoint activations*

Step function propagating the sample with the linear multi-step method. This has one forward pass with multiple times to approximate

Step function propagating the sample with the Runge-Kutta method. RK takes 4 forward passes to approximate the solution to the differ

This does the final conversion step: take locally converted weights and apply a global renaming to them. It splits attention layers, and take

This does the final conversion step: take locally converted weights and apply a global renaming to them. It splits attention layers, and take

This matches the implementation in Denoising Diffusion Probabilistic Models: Create sinusoidal timestep embeddings. :param timesteps: a 1-D

Checking for safetensors compatibility: - By default, all models are saved with the default pytorch serialization, so we use the list of defa

r""" Load pretrained attention processor layers into [`UNet2DConditionModel`]. Attention processor layers have to be defined in

r""" Save an attention processor to a directory so that it can be reloaded using the [`~loaders.UNet2DConditionLoadersMixin.load_attn_

Walks through a series of prompts and seeds, interpolating between them and saving the results to disk. Args: prompts (`

This does the final conversion step: take locally converted weights and apply a global renaming to them. It splits attention layers, and take

This does the final conversion step: take locally converted weights and apply a global renaming to them. It splits attention layers, and take

r""" Load textual inversion embeddings into the text encoder of [`StableDiffusionPipeline`] (both 🤗 Diffusers and Automatic1111 format

r""" Maybe convert a prompt into a "multi vector"-compatible prompt. If the prompt includes a token that corresponds to a multi-vector

Check whether the module was compiled with torch.compile()

Normalize an image array to [-1,1].

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

Copy current averaged parameters into given collection of parameters. Args: parameters: Iterable of `torch.nn.Parameter`;

r""" Save the LoRA parameters corresponding to the UNet and text encoder. Arguments: save_directory (`str` or `os.PathLik

Removes segments. Positive values shave the first segments, negative shave the last segments.

r""" Instantiate a [`DiffusionPipeline`] from pretrained pipeline weights saved in the `.ckpt` format. The pipeline is set in evaluati