diffusers/pr_12762/en/api/models/mochi_transformer3d.md

MochiTransformer3DModel

A Diffusion Transformer model for 3D video-like data was introduced in Mochi-1 Preview by Genmo.

The model can be loaded with the following code snippet.

from diffusers import MochiTransformer3DModel

transformer = MochiTransformer3DModel.from_pretrained("genmo/mochi-1-preview", subfolder="transformer", torch_dtype=torch.float16).to("cuda")

MochiTransformer3DModel[[diffusers.MochiTransformer3DModel]]

diffusers.MochiTransformer3DModel[[diffusers.MochiTransformer3DModel]]

Source

A Transformer model for video-like data introduced in Mochi.

Parameters:

patch_size (int, defaults to 2) : The size of the patches to use in the patch embedding layer.

num_attention_heads (int, defaults to 24) : The number of heads to use for multi-head attention.

attention_head_dim (int, defaults to 128) : The number of channels in each head.

num_layers (int, defaults to 48) : The number of layers of Transformer blocks to use.

in_channels (int, defaults to 12) : The number of channels in the input.

out_channels (int, optional, defaults to None) : The number of channels in the output.

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

text_embed_dim (int, defaults to 4096) : Input dimension of text embeddings from the text encoder.

time_embed_dim (int, defaults to 256) : Output dimension of timestep embeddings.

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

max_sequence_length (int, defaults to 256) : The maximum sequence length of text embeddings supported.

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.