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

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

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

Serializes this instance to a Python dictionary. Returns: `Dict[str, Any]`: Dictionary of all the attributes that make up this co

r""" Reverses the effect of [`pipe.fuse_lora()`](https://huggingface.co/docs/diffusers/main/en/api/loaders#diffusers.loaders.LoraBaseM

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.

A thin wrapper around the template functions / dictionaries that live elsewhere, plus variable substitution.

Return *q* scaled to unit length (handles zeros gracefully).

Rotate the agent_state by a specified angle. :param agent_state: The state of the agent to be updated. :param curr_rotation: Current rot

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.

Get a term for the variational lower-bound. The resulting units are bits (rather than nats, as one might expect). This allows

Update the *latest row* of ``self.state_traj`` at column ``key``. mode : {'replace', 'extend'}, default 'replace' - repla

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].

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

Create an ArgumentParser pre-populated with common solver args. Args: world_model_choices: Optional[List[str]] of allowed world model typ

Check if the input_dict contains the expected keys and types.

r""" Returns the binned height and width based on the aspect ratio. Args: height (`int`): The height of the image.

s: is_success p: traj_dist l: demo_dist

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

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

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

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

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.

For each (rgb_img, mask_img) pair, compute a bounding box from the mask, optionally rescale it according to 'scale_factor', and draw the boun

RoPE for image tokens with 2d structure. Args: embed_dim: (`int`): The embedding dimension size crops_coords (`Tuple[int]`)