## LatteTransformer3DModel

Model Diffusion Transformer untuk data 3D dari [Latte](https://github.com/Vchitect/Latte).

## LatteTransformer3DModel[[diffusers.LatteTransformer3DModel]]

#### diffusers.LatteTransformer3DModel[[diffusers.LatteTransformer3DModel]]

```python
diffusers.LatteTransformer3DModel(num_attention_heads: int = 16, attention_head_dim: int = 88, in_channels: int | None = None, out_channels: int | None = None, num_layers: int = 1, dropout: float = 0.0, cross_attention_dim: int | None = None, attention_bias: bool = False, sample_size: int = 64, patch_size: int | None = None, activation_fn: str = 'geglu', num_embeds_ada_norm: int | None = None, norm_type: str = 'layer_norm', norm_elementwise_affine: bool = True, norm_eps: float = 1e-05, caption_channels: int = None, video_length: int = 16)
```

[Sumber](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/transformers/latte_transformer_3d.py#L27)

#### forward[[diffusers.LatteTransformer3DModel.forward]]

```python
forward(hidden_states: Tensor, timestep: typing.Optional[torch.LongTensor] = None, encoder_hidden_states: typing.Optional[torch.Tensor] = None, encoder_attention_mask: typing.Optional[torch.Tensor] = None, enable_temporal_attentions: bool = True, return_dict: bool = True)
```

[Sumber](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/transformers/latte_transformer_3d.py#L166)

**Parameter:**

hidden_states (`torch.Tensor` dengan bentuk `(batch size, channel, num_frame, height, width)`) : Input `hidden_states`.

timestep ( `torch.LongTensor`, *opsional*) : Digunakan untuk menunjukkan langkah denoising. Timestep opsional yang diterapkan sebagai embedding di `AdaLayerNorm`.

encoder_hidden_states ( `torch.FloatTensor` dengan bentuk `(batch size, sequence len, embed dims)`, *opsional*) : Embedding kondisional untuk lapisan cross attention. Jika tidak diberikan, cross-attention secara default menggunakan self-attention.

encoder_attention_mask ( `torch.Tensor`, *opsional*) : Mask cross-attention yang diterapkan pada `encoder_hidden_states`. Dua format didukung:  * Mask `(batcheight, sequence_length)` True = simpan, False = buang. * Bias `(batcheight, 1, sequence_length)` 0 = simpan, -10000 = buang.  Jika `ndim == 2`: akan diinterpretasikan sebagai mask, kemudian dikonversi menjadi bias yang konsisten dengan format di atas. Bias ini akan ditambahkan ke skor cross-attention.

enable_temporal_attentions : (`bool`, *opsional*, defaultnya `True`): Apakah akan mengaktifkan temporal attentions.

return_dict (`bool`, *opsional*, defaultnya `True`) : Apakah akan mengembalikan `~models.unet_2d_condition.UNet2DConditionOutput` alih-alih tuple biasa.

**Mengembalikan:**

Jika `return_dict` bernilai True, sebuah `~models.transformer_2d.Transformer2DModelOutput` akan dikembalikan, selain itu sebuah `tuple` di mana elemen pertama adalah tensor sampel.

Metode forward dari [LatteTransformer3DModel](/docs/diffusers/v0.43.0/id/api/models/latte_transformer3d#diffusers.LatteTransformer3DModel).