CogVideoXTransformer3DModel
A Diffusion Transformer model for 3D data from CogVideoX was introduced in CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer by Tsinghua University & ZhipuAI.
The model can be loaded with the following code snippet.
from diffusers import CogVideoXTransformer3DModel
vae = CogVideoXTransformer3DModel.from_pretrained("THUDM/CogVideoX-2b", subfolder="transformer", torch_dtype=torch.float16).to("cuda")CogVideoXTransformer3DModel
class diffusers.CogVideoXTransformer3DModel
< source >( num_attention_heads: int = 30 attention_head_dim: int = 64 in_channels: Optional = 16 out_channels: Optional = 16 flip_sin_to_cos: bool = True freq_shift: int = 0 time_embed_dim: int = 512 text_embed_dim: int = 4096 num_layers: int = 30 dropout: float = 0.0 attention_bias: bool = True sample_width: int = 90 sample_height: int = 60 sample_frames: int = 49 patch_size: int = 2 temporal_compression_ratio: int = 4 max_text_seq_length: int = 226 activation_fn: str = 'gelu-approximate' timestep_activation_fn: str = 'silu' norm_elementwise_affine: bool = True norm_eps: float = 1e-05 spatial_interpolation_scale: float = 1.875 temporal_interpolation_scale: float = 1.0 )
Parameters
- num_attention_heads (
int, optional, defaults to 16) — The number of heads to use for multi-head attention. - attention_head_dim (
int, optional, defaults to 88) — The number of channels in each head. - in_channels (
int, optional) — The number of channels in the input. - out_channels (
int, optional) — The number of channels in the output. - num_layers (
int, optional, defaults to 1) — The number of layers of Transformer blocks to use. - dropout (
float, optional, defaults to 0.0) — The dropout probability to use. - cross_attention_dim (
int, optional) — The number ofencoder_hidden_statesdimensions to use. - attention_bias (
bool, optional) — Configure if theTransformerBlocksattention should contain a bias parameter. - sample_size (
int, optional) — The width of the latent images (specify if the input is discrete). This is fixed during training since it is used to learn a number of position embeddings. - patch_size (
int, optional) — The size of the patches to use in the patch embedding layer. - activation_fn (
str, optional, defaults to"geglu") — Activation function to use in feed-forward. - num_embeds_ada_norm (
int, optional) — The number of diffusion steps used during training. Pass if at least one of the norm_layers isAdaLayerNorm. This is fixed during training since it is used to learn a number of embeddings that are added to the hidden states. During inference, you can denoise for up to but not more steps thannum_embeds_ada_norm. - norm_type (
str, optional, defaults to"layer_norm") — The type of normalization to use. Options are"layer_norm"or"ada_layer_norm". - norm_elementwise_affine (
bool, optional, defaults toTrue) — Whether or not to use elementwise affine in normalization layers. - norm_eps (
float, optional, defaults to 1e-5) — The epsilon value to use in normalization layers. - caption_channels (
int, optional) — The number of channels in the caption embeddings. - video_length (
int, optional) — The number of frames in the video-like data.
A Transformer model for video-like data in CogVideoX.
Transformer2DModelOutput
class diffusers.models.modeling_outputs.Transformer2DModelOutput
< source >( sample: torch.Tensor )
Parameters
- sample (
torch.Tensorof 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 theencoder_hidden_statesinput. If discrete, returns probability distributions for the unnoised latent pixels.
The output of Transformer2DModel.