This will load the LoRA layers specified in `state_dict` into `text_encoder` Parameters: state_dict (`dict`):

This will load the LoRA layers specified in `state_dict` into `unet` Parameters: state_dict (`dict`): A

Reads a checkpoint file, returning properly formatted errors if they arise.

r""" Return state dict for lora weights <Tip warning={true}> We support loading A1111 formatted LoRA checkpoints in a limite

Concatenate x and its positional encodings, following NeRF. Reference: https://arxiv.org/pdf/2210.04628.pdf

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

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

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

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

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

Sets the noise scales used for the diffusion chain. Supporting function to be run before inference. The sigmas control the weight of

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

Sort a list of `objects` following the rules of isort. `key` optionally maps an object to a str.

Serializes the configuration instance to a JSON string. Returns: `str`: String containing all the attrib

Constructs the noise schedule of Karras et al. (2022).

Fused `Conv2d()` followed by `downsample_2d()`. Padding is performed only once at the beginning, not between the operations. The fused op is c

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*):

Translates coordinates in pixel space to coordinates in latent space

Swap the `Transformer2DModel` blocks between the image and text UNets