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

r""" Return state dict for lora weights and the network alphas. <Tip warning={true}> We support loading A1111 formatted LoRA

r""" Args: Restore the parameters stored with the `store` method. Useful to validate the model with EMA parameters without: af

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 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 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

Computes SNR as per https://github.com/TiankaiHang/Min-SNR-Diffusion-Training/blob/521b624bd70c67cee4bdf49225915f5945a872e3/guided_diffusion/

Downsamples the provided mask tensor to match the expected dimensions for scaled dot-product attention. If the aspect ratio of the ma

r""" Instantiate a pretrained MultiAdapter model from multiple pre-trained adapter models. The model is set in evaluation mode by def

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

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

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

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

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

Sets the begin index for the scheduler. This function should be run from pipeline before the inference. Args: begin_inde

r""" Returns: `torch.device`: The torch device on which the pipeline is located.

r""" Enable sliced attention computation. When this option is enabled, the attention module splits the input tensor in slices to comp

Args: Compares the current Accelerate version to a given reference with an operation. operation (`str`): A string represe

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

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

Runs `command` with `subprocess.check_output` and will potentially return the `stdout`. Will also properly capture if an error occurred while

Sets the conditioning scale between text and image. Example: ```py pipeline.set_ip_adapter_scale(0.5) ```

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

Prepares a single grid of images. Useful for visualization purposes.

Convert a NumPy image to a PyTorch tensor.