Flattens the audio latent tensor along time. Use `get_patch_grid_bounds` to derive timestamps for each latent frame based on the conf

This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch, num_key_value_heads, seqlen, he

Rotates half the hidden dims of the input.

Run features through the middle block.

Decode a latent tensor into video frames using tiled processing. Splits the latent tensor into tiles, decodes each tile individually,

Restores the `(B, C, T, F)` spectrogram tensor from flattened patches. Use `get_patch_grid_bounds` to recompute the timestamps that d

Decode and accumulate all tiles of a temporal group into a local buffer. The buffer is local to the group and always starts at time 0

Adjust output shape to match target dimensions for variable-length audio. This function handles the common case where decoded audio s

Build unified sequence: x, cap, and optionally siglip. Basic mode order: [x, cap]; Omni mode order: [cap, x, siglip]

Builds a `(B, 1, T, 2)` tensor containing timestamps for each latent frame. This helper method underpins `get_patch_grid_bounds` for

dynamic RoPE layers should recompute `inv_freq` in the following situations: 1 - growing beyond the cached sequence length (allow sca

Forward pass for LTX models. Returns: Processed output tensors

Get the number of images and videos for each sample to calculate the separation length of the sample tensor. These parameters are not

Group tiles by their temporal output slice.

Initialize audio-specific components.

Initialize audio-video cross-attention components.

Initialize transformer blocks for LTX.

Initialize video-specific components.

Apply the RMSNorm normalization to the input tensor. Args: x (torch.Tensor): The input tensor. Returns:

Apply the RMSNorm normalization to the input tensor. Args: x (torch.Tensor): The input tensor. Returns:

Normalize and flatten multi-layer hidden states, respecting padding. Performs per-batch, per-layer normalization using masked mean and range,

Normalize encoder latents using per-channel statistics. When the encoder is configured with ``double_z=True``, the final conv

Patchify a single image tensor: (C, F, H, W) -> (num_patches, patch_dim).

Prepare attention mask.

Prepare the audio stream for writing.

Prepare context for transformer blocks.

Prepare cross attention timestep embeddings.

Prepare timestep embeddings.

Encode a given string into feature tensors suitable for downstream tasks. Args: text (str): Input string to encode.

Process transformer blocks for LTXAV.

r"""Encode a batch of images using a tiled encoder. When this option is enabled, the VAE will split the input tensor into tiles to compute en