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

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

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*):

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*):

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]`): prompt

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(int)`): prompt

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]`): prompt

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]`): prompt

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*):

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

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*):

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]`): prompt

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

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

Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`.

Load a model from a directory or the HF Hub. Arguments: model_id (`str` or `Path`): Directory from

If DIFFUSERS_VERBOSITY env var is set to one of the valid choices return that as the new default level. If it is not - fall back to `_defau

r""" Gets the noise prediction using the `unet` and performs classifier-free guidance, if necessary.

r"""Infers the batch size and multiplier depending on mode and supplied arguments to `__call__`.

r""" Infer the generation task ('mode') from the inputs to `__call__`. If the mode has been manually set, the set mode will be used.

Identical to the XLM create_sinusoidal_embeddings except features are not interleaved. The cos features are in the 2nd half of the

r""" Load pretrained attention processor layers for [`CLIPTextModel`](https://huggingface.co/docs/transformers/model_doc/clip#transf

x: [b, h, l, d] y: [h or 1, m, d] ret: [b, h, l, m]

x: [b, h, l, m] y: [h or 1, m, d] ret: [b, h, l, d]

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

r""" Monkey-patches the forward passes of attention modules of the text encoder. Parameters: attn_processors: Dict[st

Merge sequence input: [B, N, K, S] gap: padding length output: [B, N, L]

padding the audio times K: chunks of length P: hop size input: [B, N, L]

Performs the iterative latent refinement introduced in the paper. Here, we continuously update the latent code according to our los

Multi-head dot product attention with a limited number of queries.

x: [b, h, l, 2*l-1] ret: [b, h, l, l]

Revert the image_unet `DualTransformer2DModel` blocks back to `Transformer2DModel` with image_unet weights Call this function if yo