Loads or creates a model card. Args: repo_id_or_path (`str`): The repo id (e.g., "runwayml/stable-diffusion-v1-5") or lo

Populates the `model_card` with library name and optional tags.

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

r""" Resets the device maps (if any) to None.

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

r""" Sets the attention processor to use to compute attention. Parameters: processor (`dict` of `AttentionProcessor` or o

r"""Manually set the generation mode to unconditional joint image-text generation.

Moves the LoRAs listed in `adapter_names` to a target device. Useful for offloading the LoRA to the CPU in case you want to load mult

Set the verbosity level for the 🤗 Diffusers' root logger. Args: verbosity (`int`): Logging level which can be one of:

Initialize an empty AttentionStore :param step_index: used to visualize only a specific step in the diffusion process

Aggregates the attention for each token and computes the max activation value for each token to alter.

Helper method to cast floating-point values of given parameter `PyTree` to given `dtype`.

r""" Combines a latent image img_vae of shape (B, C, H, W), a CLIP-embedded image img_clip of shape (B, L_img, clip_img_dim), and a te

Computes the attend-and-excite loss using the maximum attention value for each token.

r""" Splits a flattened embedding x of shape (B, C * H * W + clip_img_dim) into two tensors of shape (B, C, H, W) and (B, 1, clip_img_

r""" Splits a flattened embedding x of shape (B, C * H * W + clip_img_dim + text_seq_len * text_dim] into (img_vae, img_clip, text) wh

Unwraps a model.

Perform backward process given list of time steps Args: latents: Latents at time timesteps[0].

Perform backward process given list of time steps. Args: latents: Latents at time timesteps[0].

Batched version of the `step` function, to be able to reverse the SDE for multiple samples/timesteps at once. Also, does not add any

Create a mask. Args: image (`PIL.Image.Image`): The image input, should be a PIL image. Returns

Checks if the LoRA layers are correctly set with peft

Context manager that checks out a given commit when entered, but gets back to the reference it was at on exit. Args: repo (`git.Repo

Cleans the table of content of the model documentation by removing duplicates and sorting models alphabetically.

Convert the model output to the corresponding type the data_prediction/noise_prediction algorithm needs. Noise_prediction is designed

r""" Converts a state dict to the PEFT format The state dict can be from previous diffusers format (`OLD_DIFFUSERS`), or new diffusers format

r""" Converts a state dict from UNet format to diffusers format - i.e. by removing some keys

Args: Deletes the LoRA layers of `adapter_name` for the unet and text-encoder(s). adapter_names (`Union[List[str], str]`)

r""" Disable sliced attention computation. If `enable_attention_slicing` was previously called, attention is computed in one step.

Disables the FreeInit mechanism if enabled.

r""" Disable sliced VAE decoding. If `enable_slicing` was previously enabled, this method will go back to computing decoding in one st

One step for the first-order DPMSolver (equivalent to DDIM). Args: model_output (`torch.Tensor`): The di

Sets the attention processor to use [feed forward chunking](https://huggingface.co/blog/reformer#2-chunked-feed-forward-layers).

Enables the FreeInit mechanism as in https://arxiv.org/abs/2312.07537. This implementation has been adapted from the [official repository](ht

r""" Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to compute decoding in sev

Reverse the denoising step process to recover a noisy image from the generated image. Args: images (`List[PIL Image]`):

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*):

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

Freeze the weights of the parts belonging to the base UNet2DConditionModel, and leave everything else unfrozen for fine tuning.

Enables fused QKV projections. For self-attention modules, all projection matrices (i.e., query, key, value) are fused. For cross-att

r""" Generate a latent mask given a mask prompt, a target prompt, and an image. Args: image (`PIL.Image.Image`):

grid_size: int of the grid height and width return: pos_embed: [grid_size*grid_size, embed_dim] or [1+grid_size*grid_size, embed_dim] (w/ or

Gets the list of the current active adapters. Example: ```python from diffusers import DiffusionPipeline p