diffusers/pr_12762/en/api/models/ltx_video_transformer3d.md

LTXVideoTransformer3DModel

A Diffusion Transformer model for 3D data from LTX was introduced by Lightricks.

The model can be loaded with the following code snippet.

from diffusers import LTXVideoTransformer3DModel

transformer = LTXVideoTransformer3DModel.from_pretrained("Lightricks/LTX-Video", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")

LTXVideoTransformer3DModel[[diffusers.LTXVideoTransformer3DModel]]

diffusers.LTXVideoTransformer3DModel[[diffusers.LTXVideoTransformer3DModel]]

Source

A Transformer model for video-like data used in LTX.

Parameters:

in_channels (int, defaults to 128) : The number of channels in the input.

out_channels (int, defaults to 128) : The number of channels in the output.

patch_size (int, defaults to 1) : The size of the spatial patches to use in the patch embedding layer.

patch_size_t (int, defaults to 1) : The size of the tmeporal patches to use in the patch embedding layer.

num_attention_heads (int, defaults to 32) : The number of heads to use for multi-head attention.

attention_head_dim (int, defaults to 64) : The number of channels in each head.

cross_attention_dim (int, defaults to 2048 ) : The number of channels for cross attention heads.

num_layers (int, defaults to 28) : The number of layers of Transformer blocks to use.

activation_fn (str, defaults to "gelu-approximate") : Activation function to use in feed-forward.

qk_norm (str, defaults to "rms_norm_across_heads") : The normalization layer to use.

Transformer2DModelOutput[[diffusers.models.modeling_outputs.Transformer2DModelOutput]]

diffusers.models.modeling_outputs.Transformer2DModelOutput[[diffusers.models.modeling_outputs.Transformer2DModelOutput]]

Source

The output of Transformer2DModel.

Parameters:

sample (torch.Tensor of shape (batch_size, num_channels, height, width) or (batch size, num_vector_embeds - 1, num_latent_pixels) if Transformer2DModel is discrete) : The hidden states output conditioned on the encoder_hidden_states input. If discrete, returns probability distributions for the unnoised latent pixels.