"Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the prediction of x_0 at t

"Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the prediction of x_0 at t

"Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the prediction of x_0 at t

"Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the prediction of x_0 at t

"Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the prediction of x_0 at t

Update the latent according to the computed loss.

Fused `upsample_2d()` followed by `Conv2d()`. Padding is performed only once at the beginning, not between the operations. The fused op is co

Add tokens to the tokenizer and set the initial value of token embeddings

Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of (1-beta) over time from t = [

Takes a state dict and a config, and returns a converted checkpoint.

Takes a state dict and a config, and returns a converted checkpoint.

Create the content of the dummy files.

Creates a dynamic module in the cache directory for modules.

Creates a config for the diffusers based on the config of the LDM model.

Creates a config for the diffusers based on the config of the LDM model.

Decodes a given array of latents into pixel space

Denormalize an image array to [0,1].

Load a Stable Diffusion pipeline object from a CompVis-style `.ckpt`/`.safetensors` file and (ideally) a `.yaml` config file. Although m

takes in text and turns it into text embeddings

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

r""" Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to compute decoding in se

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*):

Encodes the previously tokenized prompt for this diffusion region using a given encoder