Diffusers 文件
AllegroTransformer3DModel
並獲得增強的文件體驗
開始使用
AllegroTransformer3DModel
RhymesAI 在 Allegro: Open the Black Box of Commercial-Level Video Generation Model 中介紹了來自 Allegro 的 3D 資料擴散 Transformer 模型。
該模型可以透過以下程式碼片段載入。
from diffusers import AllegroTransformer3DModel
transformer = AllegroTransformer3DModel.from_pretrained("rhymes-ai/Allegro", subfolder="transformer", torch_dtype=torch.bfloat16).to("cuda")AllegroTransformer3DModel
class diffusers.AllegroTransformer3DModel
< 源 >( patch_size: int = 2 patch_size_t: int = 1 num_attention_heads: int = 24 attention_head_dim: int = 96 in_channels: int = 4 out_channels: int = 4 num_layers: int = 32 dropout: float = 0.0 cross_attention_dim: int = 2304 attention_bias: bool = True sample_height: int = 90 sample_width: int = 160 sample_frames: int = 22 activation_fn: str = 'gelu-approximate' norm_elementwise_affine: bool = False norm_eps: float = 1e-06 caption_channels: int = 4096 interpolation_scale_h: float = 2.0 interpolation_scale_w: float = 2.0 interpolation_scale_t: float = 2.2 )
Transformer2DModelOutput
class diffusers.models.modeling_outputs.Transformer2DModelOutput
< 源 >( sample: torch.Tensor )
引數
- sample（形狀為
(batch_size, num_channels, height, width)的torch.Tensor；如果 Transformer2DModel 是離散的，則為(batch size, num_vector_embeds - 1, num_latent_pixels)） — 基於encoder_hidden_states輸入的隱藏狀態輸出。如果是離散的，則返回未去噪潛在畫素的機率分佈。
Transformer2DModel 的輸出。