Calculate the keypoint transformation from image 1 to image 2. Args: img1_desc (torch.Tensor): The patch descriptors for image 1.

r""" Simply iterates over the state dict and replaces the patterns in `mapping` with the corresponding values. Args: state_dict (`dic

Create the code for the dummy object corresponding to `name`.

r""" Enable npu flash attention from torch_npu

r""" Offloads all models to CPU using accelerate, significantly reducing memory usage. When called, unet, text_encoder, vae and safety

r""" Offloads all models (`unet`, `text_encoder`, `vae`, and `safety checker` state dicts) to CPU using 🤗 Accelerate, significantly re

r""" Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and en

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*):

Return [min_id, max_id] for an event type.

Takes a state dict and returns the state dict for a particular sub-model.

Find one (or multiple) backend in a code line of the init.

Find one (or multiple) backend in a code line of the init.

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

Generates a sequence of hidden-states from the language model, conditioned on the embedding inputs. Parameters: inputs_

Get dummy components with x8 VAE downscaling and 4 UNet down blocks. These dummy components are intended to fully-exercise the T2I-Adapter

For some tests we also need the underlying ControlNetXS-Adapter. For these, we'll build the UNetControlNetXSModel from the UNet and ControlNetXS-Adapt